Computers and Electronics in Agriculture 173 (2020) 105441 Contents lists available at ScienceDirect Computers and Electronics in Agriculture journal homepage: www.elsevier.com/locate/compag A review on monitoring and advanced control strategies for precision irrigation T Emmanuel Abiodun Abioyea,b, Mohammad Shukri Zainal Abidina, , Mohd Saiful Azimi Mahmuda, Salinda Buyamina, Mohamad Hafis Izran Ishaka, Muhammad Khairie Idham Abd Rahmana, Abdulrahaman Okino Otuozec, Patrick Onotub, Muhammad Shahrul Azwan Ramlid ⁎ a Control and Mechatronics Engineering Department, School of Electrical Engineering, Universiti Teknologi Malaysia, Malaysia Department of Electrical/Electronic Engineering, Akanu Ibiam Federal Polytechnic, Unwana, Ebonyi State, Nigeria c Department of Electrical and Electronic Engineering, University of Ilorin, Ilorin, Kwara State, Nigeria d Faculty of Science, Universiti Putra Malaysia, Malaysia b A R TICL E INFO A BSTR A CT Keywords: Monitoring Advanced control Precision irrigation Internet of things Sensors Water-saving The demand for freshwater is on the increase due to the rapid growth in the world’s population while the effect of global warming and climate change cause severe threat to water use and food security. Consequently, irrigation systems are tremendously utilized by many farmers all over the world with its associated high amount of water consumption from various sources posing a major concern. This necessitates the increased focus on improving the efficiency of water usage in irrigation agriculture. The advent and rapid successes of the Internet of Things (IoT) and advanced control strategies are being leveraged to achieve improved monitoring and control of irrigation farming. In this review, a thorough search for literature on irrigation monitoring and advanced control systems highlighting the research works within the past ten years are presented. Attention is paid on recent research works related to the monitoring and advance control concepts for precision irrigation. It is expected that this review paper will serve as a useful reference to enhance reader’s knowledge on monitoring and advanced control opportunities related to irrigation agriculture as well as assist researchers in identifying directions and gaps to future research works in this field. 1. Introduction Agriculture serves as a significant source of food production and job creation to the growing demand of the human population all over the world upon which most economies survive. It is also part of the key economic sector, significantly contributing to the gross domestic product (GDP) of most countries. The success of this crucial sector relies absolutely on water supplies as crop cultivation naturally thrives on the availability of water. However, the scarcity of freshwater poses significant threats to food security and sustainable developments in some parts of the world. Therefore, efficient use and conservation of water for irrigation is needed to increase food production while equally preventing water scarcity crises (Tsang and Jim, 2016). Rainfall and irrigation are significant sources of water for agriculture. Rainfall is unreliable, and moreover, excess supplies may cause some undesirous effects on crops such as surface runoff and, erosion while it scarcity may even cause drought. Consequently, a controlled system of watering the farm, irrigation, is highly practiced for crop cultivation as an alternative ⁎ to a natural rainfall water source for plants. The irrigation system is an essential agricultural practice where water is artificially applied to the soil to supply a controlled amount of water necessary for plant growth and development (Oborkhale et al., 2015; Shibusawa, 2001). In a conventional irrigation system, farmers apply uniform irrigation across every part of the farm without considering the variabilities on the field and the water need of the crop. Therefore, this method has lesser water-saving capability and can cause over-irrigation in some part of the farm while other parts are under irrigated which may lead to undesired water stress on the plants (Anusha et al., 2017; Kumar et al., 2017; Lakhiar et al., 2018; Say et al., 2018). Also, most of the commercial irrigation controllers available in the market are pre-programmed to supply water at predefined intervals, which offer offline irrigation scheduling based on empirical knowledge of dynamics of weather variables, as well as soil and plant characteristics (Lozoya et al., 2014). Other issues in irrigation systems involve scarcity of water due to the effect of drought and climate change, environmental disturbance, the nonlinear nature of plant dynamics, changing dynamics of Corresponding author. E-mail address: shukri@fke.utm.my (M.S.Z. Abidin). https://doi.org/10.1016/j.compag.2020.105441 Received 26 August 2019; Received in revised form 7 April 2020; Accepted 11 April 2020 0168-1699/ © 2020 Elsevier B.V. All rights reserved. Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. paper combining both monitoring and control strategies for precision irrigation systems, hence necessitating the need for a critical review on precision irrigation with the integration of all the monitoring and control techniques used for water-saving agriculture. Therefore, this paper discusses advanced control and monitoring strategies for precision irrigation system with the integration of irrigation monitoring methods. The control techniques presented in this paper are basically classified into an open and closed-loop control system. The goal is to sort out and abridge a reasonable part of previous research work and further recognize and identify the research trends for precision irrigation control systems. Next, Section 2 discusses the review methodology, and Section 3 discusses the different methods of irrigation systems, while irrigation monitoring based on the Internet of Things is discussed in Section 4. Section 5 explains the integration of advanced control strategies to enhance the precision irrigation system, while the last section discusses the future research direction and conclusion. weather, dynamic crop water uptake of plants (Yusuke, 2018). To address these issues, precision irrigation concept for optimal water-saving and better yield is adopted. Precision irrigation is the integration of information, communication, and control technologies in the irrigation process to obtain optimal usage of water resources while minimizing environmental impact (Shibusawa, 2001; Zacepins et al., 2012). Precision irrigation takes into account the spatial and temporal soil variation, soil structure and hydraulic properties, plant responses to water deficit, changing weather variables through effective monitoring via Internet of Things (IoT), to make better irrigation decisions that have the potential to help achieve high water saving and improved yield (Bitella et al., 2014; Capraro et al., 2018; Zhang et al., 2002). It has been argued that this variability can be managed and economic benefit can be derived by meeting the specific irrigation needs of individual crops and their management zones through precision irrigation approach (Cambra et al., 2018; Chami et al., 2019; Smith et al., 2009). Precision irrigation is an excellent water-saving technique for maximizing yield and providing water at the desired location based on the water needs of the plant (Niu et al., 2015; Evett et al., 2009; Smith and Baillie, 2009). Also implied is the idea that the system will be managed to achieve a specific target by aiding the delivery of nutrients and water directly to the roots of each plant. This keeps the soil moisture at optimal levels to eliminate surface run-off, and deep percolation as the design process is conducted based on the ability of the soil to absorb water and the amount of crop water demand (Daccache et al., 2015). Therefore, this method results in increased productivity and improved quality of yield while ensuring maximum water use efficiency (Tropea, 2014; Smith et al., 2010). However, to provide efficient precision irrigation, the integration of the IoT for data acquisition as well as monitoring, control theory, and decision support technologies must be considered in irrigation management (Pham and Stack, 2018; Zamora-izquierdo et al., 2018). In the context of precision irrigation, control is the ability to reallocate inputs and adjustment of irrigation management according to the crop response deficit while ensuring optimal water-saving and mitigating the effects of disturbance and uncertainties (De Baerdemaeker, 2000; Smith and Baillie, 2009). However, in all cases, there is a need to sense the response of plants to the applied water at a scale appropriate for management as well as deciding for improved irrigation using both real-time and historical information for subsequent irrigation applications at an appropriate spatial level (Shashi et al., 2017). This process requires the application of real-time monitoring and advanced control strategies. In control theory, advanced control strategies refer to a broad range of techniques and technologies implemented within a process and industrial control system, while control theory is referred to as a subfield of electrical engineering and mathematics, which deals with the dynamical behaviour of systems. The attainment of desired dynamical behaviours defines the precision of the output and is determined by the model of the input and the controlled parameters. In precision irrigation, plant properties and weather parameters are relied upon with the use of sensors and several models to provide desired control of irrigation. Several review articles have been published which are related to precision agriculture, as seen in Semananda et al. (2018) and Pierpaoli et al. (2013). In addition, review work on the opportunities in IoT monitoring and how the combination of IoT, big data and data analytics has enabled precision and sustainable agriculture has been discussed (Abhishek and Sanmeet, 2019; Dlodlo and Josephat, 2015; Elijah et al., 2018b; Kamilaris et al., 2017; Martín et al., 2017; Wolfert et al., 2017; Munoth et al., 2016). Also, a review by Ding et al. (2018), described the development of a predictive model for control in agriculture, its challenges and future perspective. While a review of optimization methods and performance evaluation of irrigation projects was carried out by Aliyev (2018); Elshaikh et al. (2018). Presently, there is no review 2. Review methodology The methodology applied in the selection of works of literature that are published on precision irrigation and all its existing control strategies includes an extensive search through a different multidisciplinary online database, such as Science Direct, IEEE Xplore, Springer, Wiley, Taylor & Francis, MDPI, Google Scholar, and other Scopus indexed journals, etc. In such enormous research libraries, numerous research articles related to monitoring and control in irrigation were found. Therefore, in selecting relevant papers for this review, emphases were placed on recent journals, which is from the high-ranking journal and recently published conference papers and reports. The articles were related to the following keywords; irrigation system, monitoring, Internet of Things, predictions, and control system. Considering limited space, the papers were selected carefully, read, and summarised to ensure the continuity of the ideas. Fig. 1 illustrates the number by publication distribution within previous years (2009–2019). It can be seen that most of the selected papers were published between 2014 till date, with the year 2018 recording the highest numbers of published articles cited. Fig. 2 illustrates the distribution of reviewed papers according to application domains. It can be seen that the IoT monitoring domain has the highest number of reviewed articles, and the trend is followed by the advanced control domain. Therefore, the statistics from Fig. 2 has proved the fact that research in IoT monitoring and advanced control domain has become a growing trend in recent years. Fig. 3 shows the proportion of paper reviewed on advance control strategies for precision irrigation. Specifically, the proportion of the control strategies is optimal/adaptive control (45%), Intelligent control (42%), Linear control (8%), and open-loop control (Time/Volume based) have 5%. 3. Classification of irrigation methods For an impressive plant growth and development, appropriate water supply is essential. When rainfall is inadequate, water must be supplied to crops through irrigation (Brouwer et al., 1990b). Different irrigation methods that can be used to provide water to plant is shown in Fig. 4. The irrigation types are categorized into traditional and modern techniques based on their tendency to offer water saving, be precisely monitored, scheduled, and controlled. The quantity of irrigation water to be applied to any plant depends on the method of the irrigation system adopted, plant water demand, and the soil type. Any of the adopted irrigation methods will have an influence on the nutrients, infiltration rate, evaporation rate, water absorption pattern, and deep percolation of the soil. The traditional surface irrigation methods which is classified in Fig. 4, applies and distributes water to the surface of the soil based on the gravity flow without any form of sensing and control action 2 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 1. Distribution of selected papers according to publication year. (Ghodake and Mulani, 2016). The traditional surface irrigation type is the oldest and most common irrigation method, which was practiced all over the world (Yonts, 1994). Examples of the traditional surface irrigation methods such as furrow, flooding, and manual watering are commonly used by peasant farmers. However, these methods require good soil surface levelling to ensure adequate water distribution to prevent the water applied from draining away (Zhang et al., 2004). In addition, the water-saving capacity of these methods is low due to the potential losses of water, which is due to the massive evaporation process and uncontrolled irrigation volume (Gillies, 2017). Traditional surface irrigation is characterised by excessive water supplied to the plants which often leads to surface runoff, deep percolation, which increases the tendency of leaching, reduces the soil nutrients level, and results in reduced crop yield (Adamala et al., 2014). Therefore, surface irrigation can be enhanced to achieve precision irrigation through the adoption of modern water saving technology as well as the needed monitoring and control strategies to increase its water usage efficiency (Koech et al., 2010). In modern water saving methods, which are classified as subsurface (capillary) and surface (drip or sprinkler irrigation). Many studies have investigated subsurface irrigation and found out that it offers higher water-saving and better yield output when compared with other types surface of irrigation (Nalliah and Sri Ranjan, 2010; Li et al., 2018; Ohaba et al., 2015; Shukri Bin Zainal Abidin et al., 2014; Shukri Bin Zainal Abidin et al., 2014; Shukri Bin Zainal Abidin et al., 2012). Subsurface capillary irrigation is a type of subsurface irrigation that works based on the action of gradually supplying water from a source directly to the root area by using a capillary medium. Some capillary mediums which were usually used in this method are wicks, mats, ebbs, porous ceramics, and flows (Semananda et al., 2018; Cai et al., 2017; Wesonga et al., 2014). In the application of the subsurface irrigation method, Rahman et al. (2019) proposed the horizontal and vertical fibrous capillary interface to transfer water from the supply tank to the root zone of the plant. The Fig. 2. Distribution of papers reviewed according to application domains. 3 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 3. Distribution of papers reviewed according to control strategies. subsurface capillary irrigation process works based on a negative pressure to transport water using the capillary interface to the root zone of the plant. Based on the results obtained from both references, it has been shown that the horizontal type interface offers higher water saving potential and the better yield on their test crop compared to the vertical type interface. Other research works on capillary irrigation have also proven the advantage of this method to provide higher water saving in performing irrigation process in agriculture compared to other methods (Kamal et al., 2019; Ferrarezi, 2016; Kinoshita et al., 2010; Masuda, 2008). However, Fujimaki et al. (2018) have observed that the upward movement action of water via capillary can irreversibly accumulate salts in the plant growing medium, thereby increasing the salinity of the soil, which can be reduced only when water leaching occurs in the medium. Therefore, an efficient monitoring and control system for the capillary irrigation method is needed to overcome the soil salinity problem. Surface drip irrigation is one of the modern water saving irrigation methods which supplies water slowly through narrow tubes to provide water to the soil near the plant roots (Brouwer et al., 1990a). This irrigation method reduces the rate of water loss, which occurs due to evaporation that was affected by wind and surface runoff (Pramanik et al., 2016; Bhalage et al., 2015; Rekha et al., 2015). Likewise, Elasbah et al. (2019) have claimed the effectiveness of a drip irrigation method to offer an efficient irrigation system by providing the precise amount of nutrients to the plants to reduce the amount of nutrient leaching. However, to design and manage a surface drip irrigation system, proper knowledge regarding water distribution wetting patterns, spacing between emitters/dripper are needed to avoid a higher amount of water loss due to the evaporation process on the soil surface and water use efficiency (Bajpai and Kaushal, 2020; Hou et al., 2015). Despite several advantages of drip irrigation method, it suffers from a high Fig. 4. Different methods of irrigation. 4 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. et al., 2016; O’Grady and O’Hare, 2017; Rajeswari et al., 2017; Saiful et al., 2020; Uddin et al., 2017). As seen in Fig. 5, IoT and WSN are essential aspects that enhance monitoring process in agriculture as well as the use of other different sensors, where sensed parameters can be transferred through different wireless communication technologies such as ZigBee, Bluetooth, Wi-Fi wireless protocol, and GPRS/3G/4G Technology. Also, Low Power Wide Area (LWPA) wireless technologies like LoRa, LTE Cat-NB1, Sigfox, and LTE Cat M1 have also been used for wide area coverage monitoring (Elijah et al., 2018a; Jawad et al., 2017; Li et al., 2017; Ramesh and Rangan, 2017; Tzounis et al., 2017; Lin et al., 2015; Bitella et al., 2014). Some of the essential parameters that are usually monitored and considered for the design of a precision irrigation control systems are shown in Table 1, while the highlight of the various monitoring and sensing methods towards the achievement of precision irrigation are discussed under the soil, weather and plant-based monitoring as discussed in Sections 4.1, 4.2 and 4.3. setup cost, especially for a more massive farm due to various accessory requirements needed to perform the irrigation process such as pipes, head trickles, and emitters (Bralts and Edwards, 1987). Also, regular maintenance for the emitters is required to avoid any blockage that might affect the water supplied to the plant (Ravina et al., 1992). Sprinkler irrigation is another type of modern irrigation method similar to the pattern of precipitation on the plant. The water sprinkling process is performed by using the spray head and extensive piping system to ensure a large coverage area for irrigation. There are several types of sprinkler irrigation methods, such as the centre pivot, standalone, linear, and lateral move sprinkler, as contained in Fig. 4. This method tends to irrigate a larger land area due to its broader irrigation coverage, as demonstrated in (Evans et al., 2012a; Evans and King, 2012). However, this method suffers from a high operating cost as it requires several accessories such as sprinkler head, high-pressure pump, pipes, and energy supplies for the water pump system such as engine oil and electricity. In addition, sprinkler irrigation is found to be inadequate to be applied in a windy environment due to a high water loss rate as a result of wind drift and evaporation (Xingye et al., 2018; Zhao et al., 2009). Furthermore, this method also requires regular maintenance for nozzle replacement, and pipe connections need to be regularly checked as leakage in pipe connections will reduce the water sprinkling uniformity throughout the farm, thus affecting the crop productivity. Whatever method of irrigation adopted, subsurface, drip, or sprinkler irrigation, there is a necessity to consider improvising for its shortcoming by realtime monitoring and advanced control design aimed at achieving enhanced and desired precision. This is done by the application of relevant sensing devices to measure controlled parameters. The next section outlines the monitoring techniques adopted in literature. 4.1. Soil-based monitoring Soil moisture is one of the most crucial parameters needed for plant growth. High spatiotemporal monitoring of soil moisture content is necessary towards ensuring optimal irrigation scheduling. Several IoTbased soil moisture monitoring for irrigation management using Raspberry Pi and Arduino prototyping board. This is interfaced with different sensors for real-time soil moisture fluxes for monitoring of crop water use for irrigation decision and scheduling (Divya, 2019; Rao and Sridhar, 2018; Krishna, 2017; Anusha et al., 2017; Rajalakshmi and Devi, 2016; Chate and Rana, 2016; Kothawade et al., 2016). The type of soil moisture sensing used is a low-cost capacitance-based type that is based on the dielectric device working principle. According to Shigeta et al. (2018), real-time soil moisture sensing using capacitance-based sensors is applicable for practical measurement of soil moistures fluxes by correlating the volumetric water content (VWC) of the soil and the capacitance of the sensor probes inserted in the soil with reasonable accuracy. A more accurate soil moisture sensing approach can be achieved using a time domain reflectometry (TDR) sensors which comprises of two parallel rods inserted to the soil at the depth at which the moisture content is desired. An electromagnetic pulse is radiated from the sensor rod, from which the rate at which the pulse is conducted into the soil and reflected back to the soil surface is directly related to the soil moisture content. However, a high sampling rate is required for the TDR soil moisture sensors to receive a good signal reflected from the soil hence, making this type of sensor very expensive for farmers to deploy at a large scale for soil moisture monitoring. A low-cost monitoring irrigation system was proposed by Bitella et al. (2014) for multisensory measurement of soil water content at different depths, soil, and air temperatures. The soil sensor probes used for monitoring the soil water content are the dielectric probe operating with a sensing frequency of 80 MHz. The sensors were interfaced with Arduino Uno microcontroller as an analog input while the Wi-Fi module ESP8266 was used to transmit the data to the internet for data logging. Related work using Node MCU was carried out by (Chieochan et al., 2017; Kumar et al., 2017). Similarly, an IoT-based field monitoring was implemented with a cloud base monitoring and data analysis using Arduino as a controller by (Jha et al., 2017; Salvi et al., 2017; Yashaswini et al., 2017). Their findings confirmed that the collected data was used to make a prediction that was used to achieve reduced water consumption and for planning the strategies to get better crop yield. An IoT soil moisture monitoring approach by Hebbar and Golla (2017), took advantage of the wireless networks that utilized GSM network and infrared communications to offer automatic water supply for plants for water-saving. The proposed system was controlled by PIC microcontroller 16F877A to turn the ON/OFF pump using a relay driver after checking the moisture level with the help of a capacitance-based 4. Monitoring in precision irrigation Efficient monitoring system for various parameters that affect the plant growth and development is very vital towards designing an efficient irrigation control system to improve food production with minimum water loss. Monitoring in the context of precision irrigation also involves the collection of data that accurately reflects the real-time status of soil, plant, and weather of the irrigation areas of the plants through the use of wireless sensor networks (WSN) and the Internet of Things (IoT) technology. To develop a real-time monitoring system, the IoT has paved its way for the use of low-cost hardware (sensors/actuators) and communication technologies (Internet) to enhance the monitoring and control system for the irrigation process (FerrándezPastor et al., 2018). Similarly, distributed WSN nodes also play a significant role in real-time monitoring for precision farming. They are a network of sensor nodes interconnected wirelessly to sense, compute, and transmit information of various parameters and designed for large scale and long term deployment (Hamouda, 2017). The implementation of IoT to monitor essential parameters in precision irrigation has become a trend where seamlessly connected sensors, cameras, and Unmanned Aerial Vehicles (UAV), drones as well as satellites for data acquisition and onward data transmission using cloud service platform is used as illustrated in Fig. 5 (Karim et al., 2017; Dubravko Ćulibrk et al., 2014). The cloud platform offers services such as data analysis of sensor monitored parameters for decision making, visualization, and actions (Rajeswari et al., 2017). Farmers and researchers can remotely access the IoT cloud server where the control and monitoring algorithms are deployed using smartphones or fixed devices to provide better insights and to enhance the decision-making process in real-time (Jayaraman et al., 2016; Pongnumkul et al., 2015). Thus, the monitoring process for soils, crops and weather parameters will become more efficient and convenient for farmers, which will further enhance the effectiveness of precision irrigation control system and to ensure a good quality food production (Andrew et al., 2018; Kushwaha et al., 2015; Mohanraj 5 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 5. Overview of IoT- based Monitoring Architecture. Table 1 Summary of basic monitoring and control parameters for precision irrigation system (Lakhiar et al., 2018; Fernández, 2017; Vegetronix, 2016). Parameters Soil monitoring parameters Soil moisture content Salinity Soil water absorption capacity pH Weather monitoring parameters Greenhouse canopy light Crop canopy/air temperature/humidity Environmental weather variables (Rainfall, wind, solar radiation, etc.) Reference Evapotranspiration(ETo) Plant monitoring parameters Normalized difference vegetative Index(NDVI) Leaf Area Index(LAI) Enhanced Vegetation Index(EVI) Crop water stress index (CWSI)) Stem water content Sap flow Leaf turgor pressor Xylem water potential Stomatal conductance Stem Diameter Variation(SDV) Common value/unit Measuring device Gravimetric /Volumetric water content: 0% to 100%/0 m3/m3 to 5 m3/m3 Low: (0–0.15), Medium: (0.51–1.25) Very high: (1.76–2.00 mmhos/cm) Wilting point, field capacity Acidic: 0–6.9, Neutral: 7, Alkaline: 8–14 Soil moisture sensor (VH400, ECH2O EC Sensor, DS200, TDR Probe, tension and neutron sensors, etc.) EC measuring device 0% to 100% 00C to 400C/0% to 100% mm, %, W/m^2 etc. Light dependent resistor (LDR) SHT 11, DHT 22 sensor, handheld infrared thermometer, etc. Weather station(Davis Vantage), etc. 0–1 (mm/s) Lysimeter, IoT- based weather station, etc. Pixels(Images of plant/crops) Low: 0.2–0.4, Mid: 0.4–0.6, High: 0.6 above. 0 (bare ground) to 10 (dense vegetation) (m2/m2) −1 to 1 0(no water stress) to 1(Maximum water stress) cm3 cm−3 m3 m−2 s−1 kPa Mpa mol m−2 s−1 µm Raspberry pi camera, UAV, drones, Satellites imaging, AVHRR Instrument, Decagon’ spectral reflectance sensor, etc. AccuPAR LP-80 Ceptometer, CI-110, 202, 203 Plant canopy imager. MODIS and. Moderate-resolution Imaging Spectroradiometer Satellite, UAV Camera, NIR Spectroscopy, AVHRR Instrument Derived from the measurement of the TDR method soil moisture sensor consisting of two electrodes gauging the resistance of the soil. Also, a soil moisture monitoring using sensor layout network technology was integrated with IOS/Android application by Isik et al. (2017) where data from different DS200 soil moisture/humidity sensors with the accuracy of ± 2% is placed close to the root zone of the plant at a different region of the sensor layouts transmitted via Wi-Fi to a mobile phone-based on IOS/Android to the central control unit for opening and closing condition of electro valves. The electro valve Mini drain system pH meter Derived from the measurement of the TDR method Sap flow Sensor Pressure LPCP probe Scholander-type chambers or with microtensiometers. Porometer Linear variable differential transformers (LVDT) Sensor. controls the amount of water to be supplied to the lateral drip line. Another monitoring domain of soil nutrient was demonstrated by Zhang et al. (2017), with an IoT approach using a portable soil nutrient detector. Other parameters sensed alongside with soil nutrients include soil moisture, air/soil temperature, and humidity using the SHT 17 digital sensor interfaced wirelessly with JN5139 system control node using Zigbee. The sensed parameter was fed into a decision support system (DSS) for decision making for an irrigated citrus cultivation. A 6 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 6. Real-time monitoring and control of Rock melon cultivation experiment via Raspberry Pi camera at Universiti Teknologi Malaysia orchard, Johor Bahru (a) IoT- based Drip irrigation monitoring system (b) IoT- based Capillary irrigation monitoring system. friendly monitoring technology for soil and nutrient sensing, referred to as chameleon, was implemented by Fandika et al. (2019). This approach makes use of chameleon colours to represent the different states of soil moisture and nutrient level as low, moderate, high. This friendly technology has helped local farmers in Malawi get insight from colour for moisture content without using figures from sensor calibration to improve their water management. A design of silicon chip for in-situ monitoring of the soil nitrogen cycle was reported by Joly et al. (2017), using an ion-sensitive field-effect transistor (ISFET) microsensor for measuring soil pH and soil nitrogen content. Likwise, Bah et al. (2012) reviewed and proposed soil nutrient monitoring using on the go sensor technologies deployed for site-specific management of nutrient concentration where the efficient mapping of nutrient variability can be carried out using electromechanical and optical sensors. Another innovative soil moisture monitoring approach was demonstrated by Huuskonen and Oksanen, (2018) through the use of drones camera on aerial surveillance to create soil maps to determining the soil sample location and management zones. After analysis of the images, the result contains soil moisture and nutrient contents of different zones for irrigation planning and scheduling. The quality of water used for irrigation was monitored using the IoT approach and reported by Prasad et al. (2016), where oxidation-reduction potential, conductivity, salinity and potential hydrogen (pH) were sensed in real-time using different types of sensors. Continuous monitoring of these parameters is necessary for maintaining functional health status for plants. 4.2. Weather based monitoring One area of the increased interest of weather-based monitoring is the real-time estimation of the reference evapotranspiration (ETO) using measured weather variables as an indication of water loss from the plant and the soil environment. The rate of water loss largely depends on the precise measurement of solar radiation, air temperature, and wind speed. This data can be measured using IoT- based weather stations and other various types of sensors, as seen in Table 1. One of the most popular technological approaches that are used in precision monitoring of weather and environmental parameters is by 7 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. using WSN (Bauer and Aschenbruck, 2018; Keswani et al., 2018; Difallah et al., 2018; Hamouda, 2017; Mohanraj et al., 2017; Saraf and Gawali, 2017; Viani et al., 2017; Patil and Desai, 2013). The implementations present WSN as an alternative and efficient way in which various sensors are interconnected to monitor physical or surrounding environmental conditions for a large cropping area. The system was reported to achieve real-time monitoring and analysis of data from the sensors in a feedback loop, which activates the control devices based on a pre-calculated threshold value. Wasson et al. (2017) presents an IoT-based weather monitoring system which monitors and analyse the crop environment like air temperature, humidity, solar radiation, wind speed and moisture content in the soil, making use of different weather-based sensors interfaced with wireless communication standard for real-time data transfer and web-based services. A similar approach was demonstrated by Shahzadi et al. (2016), where three sensor networks with each comprising three soil moisture sensors, temperature, and leaf wetness were used for precise and accurate sensing of moisture content, weather and leaf wetness of the farm layout. The sensor nodes intercommunication was established using ZigBee-802.15.4 wasp-mote board with a transmission range of 500 m at 38,400 bps through the gateway to the webserver where an expert system takes irrigation decisions. Villarrubia et al. (2017) demonstrated a multi-agent-based monitoring approach using an open-source platform called PANGEA for collecting various forms of weather variables using sensors for temperature, solar radiation, humidity, pH, wind, and soil moisture. The platform comprises several Master and Slave nodes that are sensor networked to communicate at 433 MHz radiofrequency for sensor data transfer. The collection of various sensor data was fused using a fuzzy expert system to decide the volume of water needed for irrigation. Similarly, Rahman et al. (2019) developed an IoT dashboard for the management of a smart fibrous capillary irrigation system. Several variables, such as soil moisture content, weather, and others plant information are displayed on the dashboard, while the real time capture plant images for estimating leave area index is illustrated in Fig. 6. This helped in enhancing monitoring and control using an IoT system as a critical tool that is targeted at precision irrigation. With the help of realtime monitoring of weather variables, an hourly estimation of reference evapotranspiration, which determines water loss from soil and plant canopies, was computed using an FAO-56 Modified Penman-Monteith equation using a developed Arduino based IoT Davis Vantage Pro 2 weather station. The Penman-Monteith evapotranspiration model is shown in Eq. (1). 0.408 (Rn ) + ETO = the health status of crops as well as potential threat to plant growth and development such as drought, lack of nutrients, and attacks from pest. Some of these optical sensors can be fixed (immovable) closed to the plant or mounted on moving platforms such as drones, UAVs, movable sprinkler machines (Bogue, 2017), and satellites (Nutini et al., 2017). Wireless sensor networks and gateway node approach were developed by Jia et al. (2019) to collect soil moisture content in the tea plantation using captured images of the cultivated plant and soil. The pictures of the tea leaves were gathered for assessment of the tea deficiency by using a high definition camera mounted on the UAV. The proposed system helped in water conservation to a great extent and also reduces soil erosion as only required fertilizers are injected via the drip system. The integration of the IoT together with wireless sensor networks, as demonstrated by Bauer and Aschenbruck (2018), was used for in situ monitoring of the Leaf area index (LAI), a vital crop parameter used for optimal irrigation and crop performance. This was achieved using an optical filter and diffuser for photosynthetically active radiation (PAR) measurement needed to derive a reliable estimate of LAI. The use of UAV equipped with high-resolution cameras for smart aerial monitoring of irrigation area vegetation was presented by (Aleotti et al., 2018; Uddin et al., 2017). This area now has an increased research focus towards achieving precision irrigation. In Aleotti et al. (2018), the UAV with an on board camera containing Sony IMX 219 CMOS sensor was configured to fly over the irrigation field testbed. The integration of multispectral images captured by the UAV cameras with DSS was used to compute the normalized difference vegetation index (NDVI) map used for precise control of the linear sprinkler machine used for irrigation of the tomato cultivated field layout. The authors reported that a higher water saving could be achieved with the integration of NDVI technical index with DSS. Similarly, Harun et al. (2019) proposed an improved indoor farming IoT monitoring for the growth of Brassica Chinensis plant, where remote monitoring of spectrum using light sensors as well as a network of sensors for monitoring of CO2, ambient temperature, humidity, nutrient and Leaf area index was presented. The combination of these conditions was used to apply water to the plant, which was controlled by the pulsewidth modulated (PWM) actuator interfaced with IoT embedded device. The study was able to establish the effect of photoperiod light spectrum and intensity to determine the optimal plant physiology and morphology, such as leaf photosynthesis rate, water used efficiency, leaf stomatal conductance and chlorophyll on Brassica Chinensis. A cyber-physical system model approach for smart monitoring of potatoes vegetation status was demonstrated by Rad et al. (2015). The architecture for the monitoring system was in four layers, namely, physical, network, DSS, and application layers. Real-time information is obtained from sensors mounted on UAV, tractors, and satellites via the physical layer. The network layers help to access and transmit information interfaced with the DSS layer where maps of vegetation (NDVI), soil resources as well as chlorophyll content are computed, and lastly, the application layer forms the interface between the decision layer and the human operator. Lozoya et al. (2016) implemented a sensor network for monitoring and control of green pepper vegetation in four different irrigation area layouts. Each of the irrigation areas was monitored using a 10HS volumetric water content sensor, hunter flow sensor, camera for capturing vegetation images, actuator nodes which contain a rain bird irrigation valve for on/off control of water, as well as IoT-based weather station for estimation of reference evapotranspiration. Likewise, Lozoya et al. (2019) analysed two methods of spectral sensing instruments such as decagon’ spectral reflectance sensor and Mapir’s survey 3 camera’s ability to measure plant health status through NDVI in a greenhouse experiment. It was reported that both methods, achieved similar spectral results on plant health status, which could be combined with soil moisture sensing for optimal irrigation control. Readers are refer to Table 2 for more detail description of various literature on real time monitoring for precision irrigation. 900 U (e ) T + 273 2 2 + (1 + 0.34U2 ) (1) where ETO is the reference evapotranspiration (mm/hour); Δ represents the slope of saturation vapour pressure (kPa°C−1); Rn is the reference crop canopy net radiation (W/m2); λ represent the latent heat of vaporization (kPa°C−1); T represents the mean air temperature in Celsius; U2 is the Mean daily or hourly wind speed at 2-m height (ms−1); e2 represent the stream pressure of saturation vapour (kPa) (Rahman et al., 2018). The estimated reference evapotranspiration can be used to determine the actual evapotranspiration (ETC ), which is the water loss from a particular crop, from where the estimated amount of water to compensate for the water loss is computed for onward application to the plant, based on the crop coefficient (K C ) which varies from one plant to another. ETC = ETO KC (2) 4.3. Plant-Based monitoring Plant-based monitoring using optical sensors has emerged as a widely used approach to assess plant water stress status, determining 8 Computers and Electronics in Agriculture 173 (2020) 105441 Hardware Field implementation Laboratory prototype IoT and WSN based smart farming for large sensor layout IoT- based water management with real-time data logging and analysis. IoT- based irrigation and security system IoT and WSN based DSS WSN monitoring using GSM modem as an interface between users and sensors Cloud-based monitoring via IoT for data analytics IoT- based field monitoring using sensors sensors based monitoring using sensors with cloud-based data logging Aerial imaging using drones for analysis of soil moisture and nutrient content. Irrigation monitoring system using IoT with data logging and analysis. IoT Monitoring using sensors with the data integrated with a machine learning algorithm for prediction. Humidity, temperature, leaf area index, soil moisture Humidity, temperature, soil moisture Humidity, temperature, soil moisture, water. Water stress, soil potential, ETo Soil moisture content, pH Temperature, and humidity Humidity, temperature, soil moisture, light Humidity, temperature, soil moisture Relative humidity, temperature, soil moisture Image of the soil Humidity, temperature, soil moisture Humidity, air temperature, soil moisture, soil temperature, UV light radiation Agale and Gaikwad (2017) Viani et al. (2017) Harun et al. (2015) Salvi et al. (2017) Mohanraj et al. (2016) Nath et al. (2018) Huuskonen and Oksanen (2018) Rajkumar et al. (2017) Goap et al. (2018) Laboratory prototype Hardware Field implementation Laboratory prototype Hardware Field implementation Laboratory prototype Remote IoT monitoring Remote sensing of water quality using IoT for data logging IoT smart irrigation Harun et al. (2019) Prasad et al. (2016) Anusha et al. (2017); Kumar et al. (2017) Bauer and Aschenbruck (2018) Kothawade et al. (2016) Laboratory prototype Simulation based Laboratory prototype Hardware Field implementation Laboratory prototype IoT-based Machine Learning for control of hydroponics Water level, Temperature, Humidity, Light, PPM, pH, nutrient Light, ambient temperature and humidity, CO2 Temperature, pH, ORP trend and EC value Humidity, temperature, soil moisture, light 5. Control techniques for precision irrigation Adopting advanced control techniques in an irrigation system helps to achieve the application of water in the desired proportion to crops at the right time, to achieve high water use efficiency, increased yields, energy-saving, optimise fertilizer use and labour saving (Boman et al., 2015). Therefore, leveraging on the monitoring of several parameters influencing irrigation performance such as air and canopy temperature, rainfall, evapotranspiration, and solar radiation, various control methods have been suggested to improve optimal irrigation systems and to increase their efficiency (Marinescu et al., 2017). It is possible to categorize the irrigation control techniques primarily into closed-loop and open-loop control strategies. Similarly, the combination of both closed-loop and open-loop control method has also been proposed as a hybrid control strategy. The irrigation controllers are examined in this section based on these classifications into different irrigation control techniques, as illustrated in Fig. 7. 5.1. Open loop irrigation control technique In an open-loop irrigation control system, irrigation decisions are made empirically by the operator using both mechanical or electromechanical irrigation timers and the volume of water to be delivered or indirectly via the speed of a movable sprinkler machine. The volume of water and the time for irrigation is often specified and applied based on the knowledge of the operator on perceived crop response, rather than on a precise measurement (Zazueta et al., 2008). Also, irrigation systems control based on open-loop have been broadly used by farmers, and it implies that a pre-set action is done using irrigation timers (Agency, 2017). The parameters set by the system operator are often the time and the volume of water to be supplied, not minding the crop response. An open-loop system is simple to implement because sensors are not required in order to measure the varying parameters affecting the plant, such as soil moisture contents, other weather variables, and also no need for feedback concept, hence saves cost (Harper, 2017). The block diagram of the open-loop irrigation system is illustrated in Fig. 8. A time-based sprinkler and drip irrigation system for coastal horticulture was carried by Sudarmaji et al. (2019) based on the open-loop control approach. The timing was designed using a real-time clock (RTC) interfaced with an Arduino board connected to an actuator for switching on the DC pump for drip and AC pump for sprinkler irrigation. Montesano et al. (2016) implemented a timer-based irrigation system in a greenhouse. The results show that timer-controlled irrigation experienced 18% leaching with a leaser leaf area index when compared to the performance with a closed-loop sensor-based approach. The issue associated with the open-loop irrigation control method is its susceptibility to environmental disturbances. The control input does not generally take the dynamics in the system into consideration. It also cannot automatically react to varying conditions in the environment, development stage requirement of plants, and requires frequent resetting to achieve high levels of irrigation efficiency (Patil and Desai, 2013). Examples of the open-loop irrigation techniques are irrigation timer, volume-based, and conventional approach, as illustrated using the block diagram in Fig. 8. Irrigation timers are simple controllers consisting of clock units capable of activating one or more subunits of the irrigation system at a specific time. Crop Soil Mehra et al., 2018 Weather Monitoring Domain References Table 2 Detailed description of monitoring in precision irrigation. Water Monitored Variable Laboratory prototype Hardware Field implementation Hardware Field implementation Implementation Nature Method/Improvement E.A. Abioye, et al. 5.2. Closed loop irrigation control system The closed-loop irrigation controllers operate based on a feedback control scheme designed to keep the desired output condition by comparing it with some pre-set conditions to decide the duration and amount of water supply to plants. In Klein et al. (2018), a closed-loop irrigation system fully automates the delivery of irrigation and 9 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 7. Classification of different Control techniques for Precision Irrigation System. calculates the water requirement of the plant. The operator creates a general control approach in closed-loop systems, and once the overall approach is formulated, the control system takes over the time and frequency of water supply to plants (Patil and Desai, 2013). The decisions as to when and where to irrigate are dependent and guided by various data obtained from sensors as feedback and compared with the desired set point, as illustrated in Fig. 9. Therefore, sensing of environmental and canopy variables (such as soil moisture, NDVI (images of the plant), LEA index) as well as weather (temperatures, humidity, solar radiation, etc.) as seen in Table 1 are required when designing automatic irrigation controllers (Deng et al., 2018; Adeyemi et al., 2017). The present condition of the decision variables is compared against some certain decision statements, to initiate action on the control of irrigation. Many research works have been published on monitoring and automatic irrigation integrated with the IoT system based on closed-loop irrigation control principles. They made use of a closed-loop control approach, where soil, plant, and weather variables are combined to measure water demand of the crop and for irrigation scheduling and optimization. However, the nonlinear nature and changing dynamics of plants, make control of irrigation extremely cumbersome. Also, due to the necessity of the use of numerous sensors into the irrigation system coupled with the challenges of installations and calibrations, they require immense implementation expenses by farmers and researchers. This survey paper divides the closed-loop control approach to linear control, such as Proportional Integral Derivative controller, intelligent, optimal/adaptive, and other control schemes, as illustrated in Fig. 7. 5.2.1. Linear control 5.2.1.1. Proportional-Integral-Derivative (PID) based irrigation controller. Over the years, classical proportional-integral-derivative popularly known as PID has been widely used for industrial feedback control systems due to their simple structure, extensive control algorithm, and low cost. It offers better efficiency because of its control ability on the actual output of a process to track the set output while minimizing error (Mantri and Kulkarni, 2013). However, classic PID controllers may suffer a setback in control performance when faced with external disturbances, also being a linear controller, it is not suited for systems that are highly nonlinear (Yesil et al., 2014). To achieve good control performance, each component in the control loop can be characterized by tunning appropriate PID controller parameters. Empirical methods are used to evaluate the PID parameters with consideration of how the system functions under open-loop circumstances. An improved PID controller unit was developed, with a constrained integral function, to ensure proper regulation during the diurnal cycle of adequate water to meet the need of the plant (Goodchild et al., 2015). The controller reacts rapidly to varying environmental conditions, including precipitation occasions, which can result in controller windup, under watering, and stress circumstances of the plant. The work shows how a constraint PID controller functions to provide robust and precise irrigation Fig. 8. Block diagram of the open-loop irrigation system. 10 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 9. Block diagram of the closed-loop irrigation system. management watering (Rodríguez et al., 2015). For a similar purpose, to address the linearity and non-linearity of associated with the dynamics of irrigation farming of crops, Zhang et al. (2018), Yubin et al. (2017), Bi and Zheng (2014) proposed a PID fuzzy control strategy of water and fertilizer for precision irrigation. The study shows that reasonable control of water and fertilizer ratio in agricultural irrigation and water conservation was achieved with better controller robustness and stability. For the same purpose, Yubin (2018) demonstrated a control technology based on PID fuzzy algorithm for precise application of water and fertilizer, the PID controller is based on fuzzy rules and rules-based matrix table for real-time self-parameter tuning as well as effectively predicting the water requirement of the crop to achieve precision irrigation. The implementation results show that the PID fuzzy control system has the advantages of high control precision with reducing overshoot by 14.68% and better stability, but the control performance was degraded when the fertilizer density change significantly. A similar result was obtained in Bi and Zheng (2014), where the integration of grey theory, fuzzy rules and PID algorithm for fertilizer and water precision control with very low control overshoot and robust stability was reported. Classical closed-loop control technology such as on/off, proportional (P), proportional-integral (PI), and proportional integral differential (PID) are easy to implement, but are unable to control multivariable and moving processes with time delays, however, by cascading several PID controllers or linking feedback paths, the control performances can be improved to a near adaptive manner (Norhaliza et al., 2011). Furthermore, another challenge of the PID controllers is the improper gain selections of these control systems, which can lead to unstable conditions as the systems are non-linear and have non-modelled dynamics. Since it is hectic to tune a PID controller and considering its inability to handle multivariable control problems such as irrigation systems, there is need for researchers to look towards the direction of tuning the parameters of PID controllers using intelligent algorithms such as particle swarm optimization, genetic algorithm or hybrid fuzzy PID for optimal control of irrigation system. logic-based as well as other evolutional algorithms that have been used for optimizing irrigation as summarised in Table 3 and discussed in the following subsections. 5.2.2.1. Fuzzy logic-based irrigation controller. An extension of traditional Boolean logic, which allows the expression of logical values between true and false and describes the uncertainty and nonlinearity of the real-world problems, is known as fuzzy logic (Hasan et al., 2018). Precision irrigation using fuzzy logic has been utilized in many kinds of literature due to the fact that it does not require an accurate model of the plant object before it can be controlled (Wang and Zhang, 2018; Dela Cruz et al., 2017; Al-Ali et al., 2015; Hussan and Hamouda, 2014; Patil and Desai, 2013; Touati et al., 2013; Patil et al., 2012). In complex systems such as irrigation with its characteristic nonlinearities, it is difficult to obtain the mathematical model that describes the system. Hence, fuzzy controllers have the potential to replace the role of a mathematical model with a fuzzy model based on the rules formulated in an if-else and then format that is inspired by expert knowledge of the process (Ramli et al., 2017). A fuzzy irrigation system was modelled and simulated by Mousa et al. (2014); the computation of evapotranspiration (ETo) was carried out with the help of fuzzy inference system using input variables such as temperature, humidity, wind, and radiation. The results demonstrate that the fuzzy model is a quick and accurate tool for achieving desired evapotranspiration as well as the required net irrigation to compensate for the water loss due to evapotranspiration. In another work, Keswani et al. (2018), proposed variable learning rate gradient descent feed-forward neural network-based pattern classification to forecast soil moisture content, while the valve control commands were processed using a fuzzy logic-based weather condition modelling system to manipulate the control commands by considering different weather conditions. Fengshen et al. (2018) presented the combination of neural network prediction and fuzzy control algorithm, which combines fertilization with irrigation precisely to reduce irrigation water and the waste of chemical fertilizers, save the production resources, reduces the production costs and improves the efficiency of agricultural products enterprise. In order to maximize the efficiency and production for irrigation system, Hussain et al. (2011) developed a fuzzy logic controller to estimate the amount of water of plants in distinct depth using the irrigation model, soil type, environmental conditions of greenhouse and the type of plant that affect the greenhouse irrigation system. A DSSbased on the combination of the wireless sensor and actuation network technology and fuzzy logic theory is proposed to support the irrigation management in agriculture (Viani et al., 2017), while Alomar (2018) developed a fuzzy logic controller leveraging on IoT for smart irrigation. Fuzzy irrigation controller has proved to be a beneficial control algorithm towards ensuring precision irrigation to improve water use efficiency by accurately calculating the amount of irrigation and addressing the non-linearity associated with the process. However, the performance and accuracy of the fuzzy irrigation controller depend on the designer’s knowledge of the dynamics of the process (plant) to help in formulating the fuzzy rules and proves its feasibility using long term data obtained experimentally. 5.2.2. Intelligent control for precision irrigation Artificial Intelligence (AI) is a machine’s ability to learn and execute comparable tasks that characterize human thinking, and it is dedicated to making the machine smarter (Fuentes and Tongson, 2018). It offers the potential for solving complex problems affecting the irrigation system, which are multivariable, non-linear, and time-varying (Su and Ma, 2012). When applied to a specific problem domain, AI algorithms can emulate the process of human decision making. They have been implemented in the form of fuzzy logic, ANN, Support vector machines, and decision trees with significant success to date (Singh and Jha, 2012). Applying machine learning techniques to automatically extract new knowledge in the form of generalized decision rules towards the best management of natural resources such as water to achieve precision irrigation was carried out by Dimitriadis and Goumopoulos (2008). Similarly, different classification and regression algorithms were applied to the collected dataset using various sensors to develop models that could be able to predict an irrigation plan weekly. Also, the potential of applying machine learning on datasets for prediction of yield and disease was reported by Goldstein et al. (2018). In this review, the intelligence-based irrigation controllers discussed are; ANN, fuzzy 5.2.2.2. Artificial neural network based irrigation controller. An Artificial Neural Network (ANN) is an information processing algorithm inspired 11 Computers and Electronics in Agriculture 173 (2020) 105441 Simulation based Simulation based Simulation based Simulation based/ Hardware implementation Laboratory based hardware prototype Laboratory based hardware implementation Simulation based Simulation based by how information is processed by biological nervous systems like the human brain. The human brain consists of billions of neurons that intercommunicate for information processing (Liakos et al., 2018). The artificial neurons in ANN are synonymous with the biological neurons in human being based on the nonlinearity properties of ANN, the input, and output mapping capacity for the prediction of different dependent variables (Tsang and Jim, 2016). ANN-based controllers have been applied in irrigation control systems because of their tendency to learn and adapt to the dynamics of the changing variables affecting irrigation. ANN has also been used as a smart strategy that is important in countering the issue of formulating mathematical models using the first-principles approach. A conceptual framework and estimation of evapotranspiration using computation technique of artificial neural network was carried out by Kelley and Pardyjak (2019); Sharma and Regulwar (2016); Bemani et al. (2013) to be facilitated by matching irrigation rates to crop water demand based on estimates of actual evapotranspiration(ETC), while analysis of error of an ANN controller based on reference evapotranspiration was carried out by Susilo et al. (2014). Other methods of estimation of evapotranspiration were extensively discussed by Obiechefu (2017). To ensure efficient irrigation scheduling, Umair and Muhammad (2015) proposed an ANN-based controller modelled in MATLAB, using weather variables as input parameters. Additionally, Gu et al. (2017) developed a predictive model using an improved backpropagation (BP) neural network, which was tuned by genetic algorithm (GA) to speed up the convergence of the network, preventing it from getting stocked in local minima. Similarly, research work for a step ahead prediction was carried out by Wong et al. (2018), It asserts that Recurrent Neural Networks (RNN), a subclass of ANN, was able to capture highly nonlinear systems dynamics sufficiently which makes it suitable predictive control. Another version of RNN called Long Short-Term Memory (LSTM), was used for predicting water table depth over the long-term in agricultural areas by using collected times series data (Adeyemi et al., 2018c; Jianfeng et al., 2018), the predictive model achieves higher regression coefficient (R2) scores when compared with other machine learning algorithms. The combination of reinforcement learning and ANN for irrigation control system were also carried out by Lijia et al. (2018), where an offline learning simulation of sensors and crop yield data was carried out. The artificial neural network-based fast models for soil water content using DSSAT and crop yield was developed to improve the learning process. The ANN algorithm has proven to be a veritable tool for precision irrigation based on previous research; more work still needs to be carried out in the tuning of the ANN controllers. Most of the reviewed papers are simulation-based, further efforts should be made in the implementation of this artificial intelligence algorithms on embedded system hardware to ensure proper validation of simulation findings. However, the accuracy of the ANN-based prediction model or controller depends on how well the data feed in thoroughly represent the behaviour of the system. Efforts should be made to collect data of needed parameters using good and quality sensors, proper sampling time needs to be chosen during data collection. Smart fuzzy logic Irrigation optimization using Genetic Algorithm Particle Swarm Optimization Algorithm Hybrid meta-heuristic Algorithm Azaza et al. (2016), Hamouda, (2017) Sadati et al. (2014) Liu et al. (2018) Akbari et al. (2018) K nearest neighbor (KNN)Based predictive irrigation Support Vector Regression + KNN based Irrigation ANN Shekhar et al. (2017) Umair, S Muhammad (2015) Neural Network-based irrigation Capraro et al. (2008) Anusha et al. (2017) Fuzzy PID control algorithm Only soil moisture variable were considered, weather and plant variable were not considered. Only the soil moisture and temperature variable was considered, the irrigation prediction accuracy was not explored. The only prediction of irrigation requirement was made without constraint and disturbance management. Simulation-based using input parameters like air temperature, soil moisture, radiations and humidity for modelled. Irrigation decision is based on heuristic rules decided by the expert, which cannot adequately adapt to the changing dynamics of the soil, plant, and weather A nonlinear optimization model using a genetic algorithm based on Rainfall, evapotranspiration and inflow. hydrological balance to determine optimal crop water need as well as copping pattern. Proposed PSO algorithm for optimal irrigation canal discharge rate Irrigation volume management through a better search mechanism to address the problem of other typical metaheuristic algorithms. Design or evaluation of basin, border and furrow irrigation using Irrigation volume the Volume Balance model Implementation of an open-loop fuzzy logic control using mamdani control system Development of dynamic grey prediction model fertigation with PID Fuzzy integration for control of water and fertilizer pump speed for optimal water saving. The irrigation time necessary to take the moisture level up to a userdesired level is determined using a neural network. Intelligent based KNN machine learning algorithm deployed for analyzing the sensor data for prediction to soil irrigation. IoT- based smart irrigation management using a machine learning algorithm Artificial Neural Network (ANN) based intelligent control system for effective irrigation scheduling A fuzzy logic-based irrigation system was introduced and improved with real-time data monitoring Smart irrigation using fuzzy logic Izzuddin et al. (2018), Hussan and Hamouda, (2014) Bi and Zheng, (2014) Requires regular tuning of the rules for the controller to adapt Simulation based to changes in plant, soil, and weather. Pump speed, water, and fertilizer volume control. Simulation based Description Techniques References Table 3 Application of intelligent control for precision irrigation. Control Parameters/Limitation Implementation Nature E.A. Abioye, et al. 5.2.2.3. Expert systems based irrigation system. An expert system is an algorithm that is developed to mimic the problem-solving ability of a human expert on a specific area of expertise by using artificial intelligence. It typically consists of a structure and intuitive knowledge-based component as well as an inference/control component (Mishra et al., 2014). An expert system solves problems using the expert experience who is consulted, relying on intuitive logic, belief, experience as well as the rule of the thumb. An expert system is being used in problem-solving activities such as planning, forecasting, control system, monitoring, fusing, prescribing, and interpreting decision making (Khamkar, 2014). According to Nada et al. (2014). An irrigation system control based on expert system aims to provide 12 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. farmers with irrigation expertise on how to determine the exact amount of crop water need at the right time, weather, and growing medium such as temperature, humidity, and soil types. This was demonstrated in Shahzadi et al. (2016), where an expert system for smart agriculture leveraged on the IoT- based monitoring for real-time input of different sensor data to the server where the expert system algorithm was deployed. The structure of the expert system for the irrigation decision proposed for the cotton crop was programmed using C language integrated production system. This contains the knowledge base with working memory, inference engine as well as a user interface. A similar expert system using a wireless sensor network monitoring approach for the cultivation of plant harnessing and ontology was embarked upon by (Panawong and Namahoot, 2017). The wireless sensor network was applied to collect and transfer data of soil moisture, soil pH, and sunlight, which is further fed into the expert system on the webserver to decide the water and fertilizer requirement of the plant. The expert system was then interfaced with an android smartphone for queries of the decision support in real-time. A rule-based expert system named technical specification of drip irrigation-expert system (TSDIES), developed by Ragab et al. (2018) was used for choosing the right components (such as filters, motor, pumps, fertigation device) for irrigation network control unit to address the shortage of expert for farm automation. The investigation result on the TSDI-ES algorithm shows that proper control unit components can be chosen by the expert DSS. Eid and Abdrabbo, (2018) developed a hybrid expert system for irrigation management using visual basic programming and access software for the database design. The expert system requires data of crop (harvesting date, planting date, crop coefficient (Kc), crop height, and root depth), climatic data (ETo, ETc), physical properties of the soil (field capacity, wilting point etc.) and input project data (such as area, available discharge and irrigation time). The result obtained revealed that the ISM expert system (ES) out performed other ES by 20% in terms of water use efficiency for tomato crop. Similar method was also implemented by Khamkar (2014) for design of expert system for precise drip irrigation of sugarcane in India. Expert system can be used to enhance the precision irrigation, by using different knowledge based input to realise optimal decisions for precision irrigation. However, the performance of an expert system is based on the accuracy of the knowledge input and rules design by the expert. managed using the integration of an evolutionary algorithm in the tuning of an optimal controller, which can enhance the usability of the controller for irrigation. 5.2.2.5. Particle swarm optimization based irrigation controller. Particle Swarm Optimization (PSO) is based on the paradigm of swarm intelligence, and it is motivated by the social behaviour of animals like fishes and birds. It was developed to describe the social behaviour of animals and is capable of handling an optimization test. So, a new optimizer based on the model called Particle Swarm Optimization was proposed (Wang et al., 2018). PSO is an intelligent evolutionary algorithm, which belongs to a class of optimization called metaheuristics. It is also a robust stochastic optimization algorithm that has been successfully applied in various fields such as agriculture, science, and engineering. According to Çam et al. (2015), PSO was developed because of the challenges of using mathematical models in solving optimization problems. This advancement led to the development of heuristic optimization algorithms to drive the events in nature. PSO is an algorithm based on swarm intelligence. The animals moving like swarm can readily achieve their goal. Random movements of swarm creatures make their easy access. Each individual is referred to as particle while the population is called a swarm. Each particle sets its position to the best position according to their previous experience. Moubarak et al. (2018) demonstrated the tuning of PI control of irrigation pump speed using the PSO algorithm. The performance was compared with that of the conventional Ziegler-Nichols (ZN) methods, where the PSO tuned with different performance indices had a better response, efficiency, reduced overshoot, and robust stability. PSO has also successfully been used for optimal irrigation scheduling by Liu et al. (2018), Moubarak et al. (2018), Pawda et al. (2013), Afshar and Rpour (2007). It also offers the potential of been used for tuning irrigation controllers for optimal performances. The tuning of optimal controllers using PSO could help reduce the computational burden, as it speeds up the convergence of error to global minima and searches efficiently under numerous constraints. 5.2.2.6. Hybrid intelligent systems. Hybrid intelligent systems are the combination of at least two artificial intelligence (AI) algorithms such as neural networks and fuzzy logic referred to as neuro-fuzzy; others are GAPSO and fuzzy PID. Çam et al. (2015) proposed a hybrid optimization approach to Multi-Layer Perceptron using the combination of an artificial bee colony, GA and PSO to help the critical parameters of backpropagation algorithm such as learning rate and momentum coefficient to speed up learning and deviation ratio from the global minimum and improved the robustness and stability of the system. Also, Allawi et al. (2018) developed an artificial intelligence model called Shark Machine Learning Algorithm (SMLA) to provide optimal operational rules. This algorithm outperformed GA and PSO when compared. In Tseng et al. (2018), aerial agricultural images of soil moisture condition was used to support automatic irrigation; the study proposed the used of seven different machine learning algorithms to learn local soil moisture conditions using images of the soil. The simulation result of the controller shows that water consumption was reduced by 52% and robust to errors in irrigation level, location, and timing. Related work was carried out by Wen and Shang (2019), where two machine learning algorithm (support vector machine and random forest) were combined to analyse remote sensing data for crop identification. In the work of Perea et al. (2018), the combination of dynamic Artificial Neural Networks (ANN) architecture, the Bayesian framework and Genetic Algorithms (GA) were used for forecasting the short term daily irrigation water demand when data availability is limited. When compared to previous work, the model developed enhanced the forecast precision by 3% to 11%. Similarly, in Ma et al. (2019), the combination of farmer's 5.2.2.4. Genetic algorithm based irrigation controller. Genetic Algorithm (GA) is influenced by how living organisms can adapt to the harsh realities of life in a hostile environment, i.e., by evolution and inheritance. GA is a stochastic global search technique that mimics natural evolution. This evolutional algorithm is population-based, which imitates the process of selection of fittest individuals for reproduction. It operates with a fixed-size population of feasible alternatives to problem called individuals, which are changing over time. Three critical components of genetic algorithm operators are selection, crossover, and mutation. GA has been utilized in the optimization of the water system (Sadati et al., 2014), and irrigation networks (Fernando et al., 2014) and also operational scheduling of irrigation canal by Mathur et al. (2009). According to Chen et al. (2011), GA is best suitable for getting a globally optimal solution when compared to other nonlinear methods of programming. GA has been successfully used in tuning controllers such as PID and other optimal controllers. According to Mantri and Kulkarni, (2013), the parameters of PID controller such as Kp , Ki , and K d are difficult to tune. However, the controller design parameters were tuned by a genetic algorithm which provides faster response time, better stability, and robustness than the Zeigler-Nichols (Z-N) classical method and other tuning methods. An improved GA (IGA) based multilevel parameter optimized feature selection algorithm for extreme machine learning (ELM) classifier (IGA-ELM), which was integrated with an IoTbased DSS, was proposed by Kale and Sonavane (2019). The computation complexity of most advance controllers can be adequately 13 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. be achieved using either the first principle approach when the physics of the process is understood or by using data-driven or soft computing approaches such as system identification and other artificial intelligence approaches (neural networks, LSTM). An example of the data-driven modelling approach was carried out by Ławrýnczuk (2013), who also observed that the development and validation of the first principle-based model are complicated and proposed a soft computing approach using a neural network as a better alternative. MPC provides control actions by repeatedly solving a constrained optimization problem, with predictions obtained using the model of the plant. The control action is provided by minimizing a cost function subject to constraints over a finite prediction horizon. This can be applied to multi-input, multi-output (MIMO) systems (Bordons, 2003). Another approach that was adopted by Delgoda et al. (2014) applied grey box modelling using linear time series data obtained from a water balance model. The system identification was carried out considering under saturated circumstances and noise on the soil moisture readings. The model fits of 84 and 63 percent for the two-field information set observed and satisfaction in all residual tests while the model fit above 99% using AQUACROP model data. Furthermore, a grey box system identification method was also compared with a white box, otherwise known as the first principle approach used to develop a model for a model predictive controller used for a multi-zone office building (Picard et al., 2016). Another modelling approach in many kinds of literature is by using the system identification method, which is an essential tool for technical areas that provides a mathematical and physical representation of a dynamic system through different models that can be used for controller design, but they require operational data (Mathworks, 2015). In order to combine the best features of the two approaches, dynamic modelling based on the combination of system identification and physical modelling was proposed by (Adeyemi et al., 2018b; Ooi and Weyer, 2008). This method was also adopted by Adeyemi et al. (2018a), where system identification was used to develop a data-driven model for prediction of plant transpiration dynamics. The results obtained stated that a second-order discrete-time transfer function model adequately explained the dynamics with an average determination coefficient of ± R 0.93 0.04 with incoming radiation, vapour pressure, and leaf area index as inputs. While first principle-based models or grey boxes are desirable, obtaining models that are effective and fit for purpose may not always be practical, and precision irrigation agriculture has often depended on data-driven modelling for system identification instead. A research work carried out by Winkler et al. (2016), was able to overcome the physical constraint of the traditional irrigation system with the emergence of a sprinkler node capable of sensing the local soil moisture, communicating it wirelessly, and actuate its sprinkler based on a centrally computed timetable. The author suggested that future work may be directed to data-driven system identification, where soil moisture and weather variables measurements leveraging on the IoT and knowledge of fluid movement can be used to build the predictive model over time to address the changing dynamics of the environment. Although few of researchers have adopted the use of a predictive model for control as seen in (Delgoda et al., 2016a,b; Lozoya et al., 2016; Saleem et al., 2013; Puig et al., 2012) for irrigation control as summarized in Table 4, there is still need for its enhancement to help achieve water saving, minimize the energy needed for irrigation and to ensure better yield by developing better predictive models, optimization algorithm and by integrating IoT for enhancement of the monitoring and real-time adaptive control. According to Koech and Langat (2018), real-time optimal based control of the irrigation system is still is rapidly attracting more research effort for surface irrigation because of its ability to improve water use efficiency, as illustrated in Fig. 10. Therefore, MPC has been an optimal based control, which offers a very promising method for improving water use efficiency, as 40% of the water consumed by irrigation can be saved using a predictive model knowledge and the IoT was used for deficit irrigation control. Images of the soil were captured, and feature extraction was carried out using a convolutional neural network for soil moisture prediction and further fed into the fuzzy controller. The combination of the IoT was used to get information from the field, artificial intelligence and image processing was used to provide more precise and comprehensive control to enhance the irrigation process and hydroponics system, as seen in Mehra et al. (2018) where the integration of ANN and Bayesian network algorithm with IoT for intelligent interaction and control of hydroponics system input parameters. Likewise, the combination of AI algorithms, greenhouse climate, irrigation, and crop growth control challenge embarked upon by Hemming et al. (2019), was aimed at combining horticultural expertise with AI offers a breakthrough in fresh food production with limited resources. Integrating a hybrid intelligent algorithm for control of irrigation can help achieve robust precision irrigation and can be used to enhance the performance and smartness of existing irrigation controllers. 5.2.3. Model predictive based irrigation controller Model Predictive Control (MPC) is a multivariable computer control algorithm that became popular in the power plants, chemicals, and petroleum industries (Qin and Badgwell, 2003). It has also been applied in a wide variety of industrial applications such as pharmaceuticals (Wong et al., 2018; Lee et al., 2016), wastewater treatment plants (Rahmat et al., 2011), building (Bosschaerts et al., 2017), food processing, automotive, and aerospace (Yakub and Mori, 2013). According to Ding et al. (2018), although MPC is an industry born process control method, it is incredibly applicable in agricultural activities such as irrigation control, given that it can deal efficiently with multivariable, nonlinear, and large time-delay systems such as irrigation. MPC has the advantages of dealing with constraints; its capability of utilizing simple models, closed-loop stability, and its robustness against parametric uncertainties make it one of the most popular multivariable control algorithms (Mohamed et al., 2015). Also, MPC is an industrial control technique employed in decision support for large scale multivariable problems with multiple constraints (Ocampo-Martinez, 2010). It requires a heavy computational burden to optimize the future control inputs and future process responses that are predicted using a mathematical model and optimized according to a cost function. In order to obtain a future value of the performance criterion, this control technique uses a plant model and an optimizer for calculating plant input. The performance of the system is predicted over a finite horizon subject to constraints on both the inputs and outputs of the plant (Lozoya et al., 2014). All systems experience one form of constraint to another, ranging from physical, environmental to economic constraints, which limits the operation of a process. By adopting advanced process control techniques such as MPC for irrigation control, excellent performance, better efficiency and optimality can be achieved when compared to the use of classical control methods (Balbis et al., 2006). Because of the robustness of MPC, the concept of shifting the prediction and control horizon based on the next sampling step is always applied, wherein the prediction horizons define the optimal future control signal. However, it suffers the challenge of very high computational complexity due to the fact that it solves online optimization at every time step, which needs to be addressed. Proper system identification of a plant is required to be carried out to identify model parameters to help reduce the design effort and computational load of the predictive model controller (Wahab et al., 2008). This advanced process control method requires an accurate process model that tries to summarize and describe the behaviour of the system. Better satisfactory control performances can be achieved based on the accuracy of the process model. Perhaps, the most important use of the system model arises in predictive control applications, in which the model is used to predict the process output behaviour when facing changes in set point or inputs. Developing the mathematical model can 14 E.A. Abioye, et al. Table 4 Application of MPC for irrigation control. 15 References Method Parameters Considered Modelling Approach Control Objectives Improvement/Limitation Lozoya et al. (2016) MPC Water flow, soil moisture System Identification Integrated WSN with the controller in an open field condition. Parameter estimation was done offline. Puig et al. (2012) Non-linear MPC Water flow and pressure Delgoda et al. (2016a,b) Robust MPC Soil moisture and irrigation amount First-principles modelling First-principles modelling Saleem et al. (2013) Linear MPC Soil moisture, Reference evapotranspiration State space-based The irrigation control aimed at minimizing the effective control signals (irrigation) while keeping the soil moisture below a certain threshold and taking into consideration environmental disturbances. combined irrigation and water supply system, generate flow control strategies from sources to consumers and for irrigation Irrigation control to minimize both root zone soil moisture deficit and irrigation amount with certainty equivalence control and disturbance affine feedback control Control framework for real-time irrigation scheduling without constraints handling. Mao et al. (2018) Zone MPC Javalera et al. (2010) Distributed MPC Soil Moisture, the volume of water for irrigation The trajectory of tank level linear parameter varying (LPV) model Model-free Delgoda et al. (2013) Adaptive Multi MPC Data Driven MPC MPC Flow, the water level Discrete-time Linear Model Data-Driven Shang et al. (2019) Park et al. (2009) RHC Soil moisture, weather variables First principle model Weather data and soil moisture, salinity Predictive model MPC calculates the irrigation demand of the individual fields PSO optimizes the distribution of irrigation volume and timing based on neighbouring fields requirements Receding Horizon Control (RHC) to enable successful autonomous control of soil salinization. Simulation-based and theoretical framework, validated using AQUACROP model Inaccurate simulation model, other weather variables not considered in estimating ET. No operational constraints were considered on the control variable. Simulation-based with a good prediction model. The implementation of the test crop was not carried out. Integration of reinforcement learning and computationally efficient. Does not consider nonlinear dynamics It does not incorporate economic and environmental indices into control objectives and constraints. Computationally efficient through the use of PSO optimizer and was useful only for large open field irrigation. Integrated wireless data transfer and genetic algorithm for optimal control Computers and Electronics in Agriculture 173 (2020) 105441 Dilini Delgoda et al. (2014) Precipitation, soil moisture, reference evapotranspiration Asymmetric zone tracking penalties to reduce irrigation under weather uncertainties Distributed implementation combining learning techniques to perform the negotiation of variables in a cooperative multi-agent environment to provide speed, scalability and computational effort reduction. Real-time automatic flood control using multiple models to manage river network To optimize the trajectory of future soil moisture level to minimize water usage with the prediction of evapotranspiration Simulation-based, not implemented on a specific plant. Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Fig. 10. Advances in irrigation Technologies (Koech and Langat, 2018). when compared with the conventional system or open-loop automatic irrigation system (Lefkowitz, 2019). However, not much work has been reported in the tuning of the model predictive controllers using evolutional algorithms such as GA and PSO, towards the realization of smart irrigation systems (with optimization and real-time control) for improving water use efficiency (WUE). Future work should focus on adaptive model predictive control to be able to track the changing dynamics and uncertainties effectively. Also, due to the computation complexity of predictive and optimization algorithms, which makes it challenging for its implementation on target embedded systems, future work should focus on leveraging on industrial IoT servers for real-time control of the irrigation process. sensor network-based DSS was optimized to adapt changes of crop type, irrigation pattern, and field location for instructions on individual sprinkler heads on how much water to apply and where it is needed. Similarly, Patel et al. (2017) successfully applied a DSS for an onfarm sensor-based irrigation water management to determine the timing and volume of irrigation using a border, sprinkler, and drip irrigation systems for wheat, maize, potato, and chili crops. However, the usage and adoption of the various types of site-specific variable rate (SS-VRI) precision irrigation technologies have generally been limited by farmers and researchers. Thus, a potential barrier is that full implementation of advanced SS-VRI generally has the most demanding requirements and the most complicated and costly control systems of all precision irrigation technologies (Evans and King, 2012). Simulation models can be used to simulate crop reactions to irrigation and plant management based on the physical modelling of the crop phenology by first principles (Mccarthy et al., 2014). These simulation models offer the opportunity to enhance precision irrigation strategies as the need for time-consuming field experiments is eliminated (Cong et al., 2017). A simulation framework called VARIwise, which was used for precision irrigation and capable of performing real-time decision support, was proposed by Mccarthy et al. (2014). The framework was able to integrate input information from real-time sensors for irrigation adaptive decisions. However, simulation models are necessary to assist irrigation decisions making in order to achieve model precision; most often, the information is limited to a particular plant that the platform is accessible for that purpose. The limitation in data available for this endeavour often limits the use of the platforms to specific crops. Similarly, a crop water model newly developed by FAO, called Aqua Crop, simulates the response of water to crop yield. It was calibrated using ten years of daily weather data to grow winter wheat and subsequently used to simulate yield under different sowing dates, irrigation frequencies, and irrigation sequences (Ali and Abustan, 2013). The simulation result shows that under the prevailing climatic and soil conditions, irrigation frequency is the most water-efficient schedule for wheat. The results further indicate a lower yield trend under late sowing. An optimization framework based on simulation for the ideal fertigation schedule was developed by Cong et al. (2017). The problem is represented in the form of decision tree graphs, and ant colony optimization (ACO) is used as the optimization engine and a process-based crop growth model to evaluate the objective function. The results show that ACO was able to identify irrigation and fertilizer schedules that result in better net returns while using less irrigation water and fertilizer. Also available in the literature is a crop process-based model called 5.2.4. Adaptive decision support system and other precision irrigation control method The characteristics of soil, plant, and weather variables that affect the cropping system are dynamic and nonlinear; hence, they are timevarying parameters. In farming, the properties that typically vary within and between seasons which include crop coefficient, plant growth, soil properties, and environmental factors. Therefore, those factors have a direct effect on the timing and irrigation quantity needed for ideal plant growth (Evans and King, 2012). The heart of an adaptive decision support system includes the real-time monitoring of the various parameters using different types of sensors as well as the modification and adjustment of the adaptive rules in the decision support system. Adaptive Decision Support System makes use of sensor feedback readings of soil, plant, and weather parameters stored on cloud platforms to regularly re-adjust the scheduling algorithm to maintain the required irrigation system efficiency. The adaptive performance of the system is measured on how well the changing dynamics of the plant in terms of infield temporal and spatial variability is captured. The adaptability to parameter uncertainties, spatial variabilities and the environmental disturbances on irrigation systems have been extensively investigated by using optimal control with the adaptive feature as well as variable rate water application systems proposed by numerous researchers (Pereira et al., 2018; Raine and Mccarthy, 2014; Smith et al., 2009; Evans and Sadler, 2008). Also, several works on the adaptive control of machines based on continuous move systems such as low energy precision application (LEPA), centre pivot, a linear and lateral move for spatially variable irrigation has been carried out (Debauche et al., 2018; Peters, 2014; Smith et al., 2009). Due to their present automation stage and the big coverage area using a single lateral pipe, these systems are particularly suited for variable rate implementation (Adeyemi et al., 2017). A sprinkler controlled with a modulated pulse on a self-moving linear sprinkler system was applied by Evans et al. (2012b), where wireless 16 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Table 5 Commercial irrigation system. Company Product Description References Baseline Decagon Device Soil moisture sensor for smart irrigation The sensor senses soil water for smart Irrigation https://baselinesystems.com/ https://www.metergroup.com IoT- based controller for scheduling of Irrigation https://www.rainbird.com/ Toro Water Sense Baseline’s Smart Watering Solution Irrigation Monitoring System, MPS-2 matric potential sensor ST8I-Wifi Smart Irrigation indoor Wifi Controller Automatic Irrigation Weather-based Irrigation Controllers Rachio Rachio 3 Smart Sprinkler Controller+ https://www.toro.com/en/irrigation https://www.epa.gov/watersense/ irrigation-controllers https://www.rachio.com/rachio-3/ Edaphic Scientific Jains Irritec Environmental Research & Monitoring Equipment Smart Irrigation Systems Sprinkler Systems Web-Based, Wireless (Wifi) Irrigation Controller Sprinkler and drip irrigation system Fertigation Automation Huisong Irrigation FlyBird Innovations Center pivot irrigation system Sensor-based irrigation controller Remotely control and manage the irrigation system Use real-time weather data to adapt irrigation schedules properly Shared remote access allows irrigation pros to monitor and adjust schedules anytime, anywhere. WSN monitors soil moisture, hydrology, weather, nutrient, EC, water quality. Use to grow lawns and landscapes for efficient water savings. Residential and commercial Irrigation system Supports weather forecast, user-friendly, automatic delay after. Make use of rain sensor, flow sensor, door sensor Smart irrigation network using sprinkler and drip network. Automated fertigation for management of pH and EC with radio system Smart farming irrigation machines for water sprinkling Ensures smart irrigation and fertigation of crops based on weather, soil parameters sensed. Rain Bird Morin's ECO Hunter Irrigation Blue Spray DSS for Agro-technology Transfer (DSSAT). This software consists of 16 different crop models with software to evaluate and apply the crop models for various purposes. However, it is increasingly difficult to maintain the DSSAT crop models, because different sets of computer code were written for different crops with little attention to software design at the level of crop models themselves (Jones et al., 2003). Levidow et al. (2014) suggested that for farmers and researchers to be able to use a DSS efficiently, it should not be too complicated but userfriendly, affordable, and informative systems helpful to achieve precision irrigation. https://www.edaphic.com.au/ https://morinslandscaping.com/ https://www.hunterindustries.com/ https://www.bluespray.net/ https://www.jains.com/ https://irritec.ie/ https://huisongirrigation.en/ https://csrbox.org/ index (NDVI), lea area index (LEA) as well as other technical indexes in deciding and planning irrigation scheduling for large irrigation farm area. Also, accurate model-based predictions can guide farmers to prepare for the activities and guide against unusual changes that can affect agricultural practices. Furthermore, different control algorithms in the context of irrigation systems have been discussed; researchers should focus on enhancing any of the model-based and adaptive controllers with real time monitoring for precision irrigation. The integration of evolutional algorithms such as Genetic Algorithm, Ant Colony and Particle Swarm Optimization for parameters tuning of adaptive irrigation controllers, is important for the adaptation of nonlinear and changing dynamics of soil, plant and weather variables while ensuring optimal precision irrigation for enhancement of irrigation technology. In addition, the development of the digital and complex irrigation technology is really important to be explored, so that developed technology will provide a stable, suitable, and affordable system for ordinary farmers in improving the water use efficiency while minimizing water scarcity for agricultural activities. Though, the various types of monitoring and advanced control strategies for precision irrigation have been discussed in this review, and they might not have covered all the approaches in kinds of literature. Interested readers can refer to the cited references in the paper, from which more related articles could be accessed. 6. Commercial irrigation system for farmers and researchers As precision irrigation control is crucial to increase productivity and ensuring food security, so many companies have developed a smart watering system that may help achieve high water-saving and precise irrigation; few are highlighted in Table 5. Most of the products aim to achieve precision irrigation and reducing the stress involved in manual irrigation. However, the high cost of acquiring these state-of-the-art devices poses a significant challenge to farmers and researchers. Also, most of these commercial irrigation systems available in the market are custombuilt, therefore, making them difficult to be appropriately tuned and adaptively controlled. Furthermore, most of the commercial irrigation systems do not consider soil, plant, weather parameters conditions in making irrigation decisions for optimal water saving. Also, the effect of disturbances to plants such as evapotranspiration, signifying water loss from plants and the surface of the soil, the changing and nonlinear dynamics of plants cannot be correctly manage by most of the commercial products. 8. Conclusion The global awareness on the effect of global warming and climate change on water scarcity and food security is on the increase, which has challenged researchers to brace up more efforts developing cutting edge strategies on real-time monitoring and control for precision agriculture that can mitigate the effect of this inevitable phenomenon. This review on the monitoring and control strategies for precision irrigation systems is based on the previous and relevant research work that has been done to help achieve water saving in agriculture. This review article has been able to give a clear picture of research trends in developing advanced control strategies for precision irrigation and to assess research opportunities in studies that can ensure water saving, improve crop yield and optimize the energy needed for irrigation. It is expected to generate new ideas and inspire readers on how current monitoring and advance control approaches can be enhanced towards achieving improved precision irrigation for food security and help achieve water saving on forestalling imminent water crises. 7. Future research directions The essence of this review work is to explore the various efforts and progress that have been made to improve water use efficiency, watersaving, and above all, to achieve food security using the IoT- based monitoring and applied control systems. From the review, researchers and farmers can leverage on recent developmental evolution on the IoT for real-time monitoring and data collection for data-driven control, machine, and deep learning for intelligent prediction of agricultural processes such as yield, water consumption, and weather. Further investigation is needed on the use of normalized dimension vegetation 17 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Declaration of Competing Interest Bajpai, A., Kaushal, A., 2020. Soil moisture distribution under trickle irrigation: a review. In Press. Water Sci. Technol. Water Supply 1–12. https://doi.org/10.2166/ws.2020. 005. Balbis, L., Kateb, R., Ordys, A.W., 2006. Model predictive control design for industrial applications. In: UKACC International Conference on Control. University of Strathclyde, Glasgow.Uk, pp. 1–6 https://doi.org/http://ukacc.group.shef.ac.uk/ Control_Conferences/... Bauer, J., Aschenbruck, N., 2018. Design and implementation of an agricultural monitoring system for smart farming. In: 2018 IoT Vertical and Topical Summit on Agriculture - Tuscany, IOT Tuscany 2018, IEEE, pp. 1–6. https://doi.org/10.1109/ IOT-TUSCANY.2018.8373022. Bemani, A., Araghinejad, S., Nejadhashemi, A.P., Sarai, M., 2013. Optimal water allocation in irrigation networks based on real time climatic data. Agric. Water Manag. 117, 1–8. Bhalage, Pradeep, Jadia, B.B., Sangale, S.T., 2015. Case studies of innovative irrigation management techniques. Aquat. Procedia 4, 1197–1202. https://doi.org/10.1016/j. aqpro.2015.02.152. Bi, P., Zheng, J., 2014. Study on application of grey prediction fuzzy PID control in water and fertilizer precision irrigation. In: 2014 IEEE International Conference on Computer and Information Technology. IEEE, pp. 789–791 https://doi.org/10.1109/ CIT.2014.43. Bitella, G., Rossi, R., Bochicchio, R., Perniola, M., Amato, M., 2014. A novel low-cost open-hardware platform for monitoring soil water content and multiple soil-air-vegetation parameters. Mdpi Sensors J. 14, 19639–19659. https://doi.org/10.3390/ s141019639. Bogue, R., 2017. Sensors key to advances in precision agriculture. Sensor Review, Emerald Publishing Limited 37 (1), 1–6. https://doi.org/10.1108/SR-10-2016-0215. Boman, B., Smith, S., Tullos, B., 2015. Control and automation in citrus microirrigation systems. Agricultural and Biological Engineering Department, UF/IFAS Extension, pp. 1–15. Bordons, E.F.C. and C., 2003. Model Predictive Control (Second). London: Springer. Bosschaerts, W., Van Renterghem, T., Hasan, O.A., Limam, K., 2017. Development of a model based predictive control system for heating buildings. Energy Procedia 112 (October 2016), 519–528. https://doi.org/10.1016/j.egypro.2017.03.1110. Bralts, V., Edwards, D., 1987. Drip Irrigation Design and Evaluation based on the Statistical Uniformity Concept. ACADEMIC PRESS, INC. https://doi.org/10.1016/ B978-0-12-024304-4.50005-5. Brouwer, C., Prins, K., Kay, M., Heibloem, M., 1990a. Drip Irrigation. Retrieved June 17, 2019, from http://www.fao.org/3/S8684E/s8684e07.htm. Brouwer, Prins, Kay, Heibloem, 1990b. Surface irrigation systems. Retrieved June 17, 2019, from http://www.fao.org/3/T0231E/t0231e04.htm. Cai, P.W., L, Z., 2017. Simulation of soil water movement under subsurface irrigation with porous ceramic emitter. Agric. Water Manage. 192, 244–256. https://doi.org/ 10.1016/j.agwat.2017.07.004. Çam, Z.G., Çimen, S., Yildirim, T., 2015. Learning parameter optimization of multi-layer perceptron using artificial bee colony, genetic algorithm and particle swarm optimization. In: SAMI 2015 - IEEE 13th International Symposium on Applied Machine Intelligence and Informatics, Proceedings, vol. 1, pp. 329–332. https://doi.org/10. 1109/SAMI.2015.7061899. Cambra, C., Sendra, S., Lloret, J., Lacuesta, R., 2018. Smart system for bicarbonate control in irrigation for hydroponic precision farming. Sensors-MDPI 1333, 1–16. https://doi. org/10.3390/s18051333. Capraro, F., Patifio, D., Tosetti, S., 2008. Neural network-based irrigation control for precision agriculture. In: 008 IEEE International Conference on Networking, Sensing and Control, pp. 357–362. Capraro, F., Tosetti, S., Rossomando, F., Mut, V., 2018. Web-based system for the remote monitoring and management of precision irrigation: a case study in. Sensors MDPI. https://doi.org/10.3390/s18113847. Chami, D. El, Knox, J.W., Daccache, A., Weatherhead, E.K., 2019. Assessing the financial and environmental impacts of precision irrigation in a humid climate. Horticultural Science (Prague) 46 (1), 43–52. https://doi.org/10.17221/116/2017-HORTSCI. Chate, B.K., Rana, P.J.G., 2016. Smart irrigation system using raspberry pi. Retrieved from. Int. Res. J. Eng. Technol. (IRJET) 3 (5), 247–249. https://www.irjet.net/ archives/V3/i5/IRJET-V3I553.pdf. Chen, W., Zheng, T., Chen, M., Li, X., 2011. Improved nonlinear model predictive control based on genetic algorithm. In: Advanced Model Predictive Control. InTech, pp. 1–19 https://doi.org/10.5772/18778. Chieochan, Oran, Saokaew, Anukit, Boonchieng, Ekkarat, 2017. Internet of things (IOT) for smart solar energy: A case study of the smart farm at Maejo University. International Conference on Control, Automation and Information Sciences, ICCAIS 2017 262–267. https://doi.org/10.1109/ICCAIS.2017.8217588. Cong, D., Nguyen, H., Ascough, J.C., Maier, H.R., Dandy, G.C., Andales, A.A., 2017. Optimization of irrigation scheduling using ant colony algorithms and an advanced cropping system model. Environ. Modell. Software 97, 32–45. https://doi.org/10. 1016/j.envsoft.2017.07.002. Daccache, A., Knox, J.W., Weatherhead, E.K., Daneshkhah, A., Hess, T.M., 2015. Implementing precision irrigation in a humid climate – Recent experiences and ongoing challenges. Elsevier -Agricultural Water Manage. 147, 135–143. https://doi. org/10.1016/j.agwat.2014.05.018. De Baerdemaeker, J., 2000. Process monitoring and control for precision agriculture. IFAC Proceedings Volumes 33 (29), 23–30. https://doi.org/10.1016/S14746670(17)36746-0. Debauche, O., Moulat, M. El, Mahmoudi, S., 2018. Irrigation pivot-center connected at low cost for the reduction of crop water requirements. In: 2018 International Conference on Advanced Communication Technologies and Networking (CommNet). doi.org/10.1109/COMMNET.2018.8360259. There is no conflict of interest in the submission of this manuscript. The manuscript is approved by all authors for publication. Acknowledgment The authors are grateful to the Universiti Teknologi Malaysia and the Ministry of Higher Education Malaysia, for their partial financial support through their research funds, Vote No. R.J130000.7851.4L710, R.J130000.7351.4B428 and Q.J130000.2651.17J53. Appendix A. Supplementary material Supplementary data to this article can be found online at https:// doi.org/10.1016/j.compag.2020.105441. References Adamala, S., Raghuwanshi, N.S., Mishra, A., 2014. Development of surface irrigation systems design and evaluation software (SIDES). Comput. Electron. Agric. 100, 100–109. https://doi.org/10.1016/j.compag.2013.11.004. Adeyemi, O., Grove, I., Peets, S., Domun, Y., Norton, T., 2018a. Dynamic modelling of lettuce transpiration for water status monitoring. Comput. Electron. Agric. 155 (September), 50–57. https://doi.org/10.1016/j.compag.2018.10.008. Adeyemi, O., Grove, I., Peets, S., Domun, Y., Norton, T., 2018b. Dynamic modelling of the baseline temperatures for computation of the crop water stress index (CWSI) of a greenhouse cultivated lettuce crop. Comput. Electron. Agric. 153 (January), 102–114. https://doi.org/10.1016/j.compag.2018.08.009. Adeyemi, Olutobi, Ivan, Grove, Peets, Sven, Domun, Yuvraj, Norton, Tomas, 2018c. Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling. MDPI-Sensors 18, 1–22. https://doi.org/10.3390/s18103408. Adeyemi, O., Grove, I., Peets, S., Norton, T., 2017. Advanced monitoring and management systems for improving sustainability in precision irrigation. SustainabilityMDPI 9 (353), 1–29. https://doi.org/10.3390/su9030353. Afshar, M.H., Rajabpour, R., 2007. Optimal design and operation of irrigation pumping systems using particle swarm optimization algorithm. Retrieved from. Int. J. Civil Eng. 5 (4), 302–311. http://ijce.iust.ac.ir/article-1-332-en.html. Agale, R.R., Gaikwad, D.P., 2017. Automated irrigation and crop security system in agriculture using internet of things. In: 2017 International Conference on Computing, Communication, Control and Automation (ICCUBEA). IEEE, pp. 1–5. https://doi.org/ 10.1109/ICCUBEA.2017.8463726. Agency, U. S. E. P. (2017). Soil Moisture-Based Irrigation Control Technologies : WaterSense ® Specification Update. EPA WaterSense. Akbari, M., Gheysari, M., Mostafazadeh-Fard, B., Shayannejad, M., 2018. Surface irrigation simulation-optimization model based on meta-heuristic algorithms. Agric. Water Manag. 201, 46–57. https://doi.org/10.1016/J.AGWAT.2018.01.015. Al-Ali, A.R., Qasaimeh, M., Al-Mardinia, M., Radder, S., Zualkernan, I.A., 2015. ZigBeebased irrigation system for home gardens. In: 2015 International Conference on Communications, Signal Processing, and Their Applications, ICCSPA 2015, 0–4. https://doi.org/10.1109/ICCSPA.2015.7081305. Aleotti, J., Amoretti, M., Nicoli, A., Caselli, S., 2018. A smart precision-agriculture platform for linear irrigation systems. In: 26th International Conference on Software, Telecommunications and Computer Networks (SoftCOM). University of Split, FESB, pp. 1–6. Ali, M.H., Abustan, I., 2013. Irrigation management strategies for winter wheat using AquaCrop model. J. Natl. Resour. Dev. 3, 106–113. https://doi.org/10.5027/jnrd. v3i0.09. Aliyev, R.A.E.Z.H., 2018. Review of the methods of optimization of irrigation. Global J. Otolaryngology (GJO) 12 (4). https://doi.org/10.19080/GJO.2018.12.555845. Allawi, Mohammed Falah, Jaafar, Othman, Ehteram, Mohammad, Mohamad Hamzah, Firdaus, El-Shafie, Ahmed, 2018. Synchronizing artificial intelligence models for operating the dam and reservoir system. Water Resour. Manage. 32 (10), 3373–3389. https://doi.org/10.1007/s11269-018-1996-3. Alomar, B., 2018. A smart irrigation system using IoT and fuzzy logic controller. Fifth HCT Information Technology Trends (ITT) 2018, 175–179. https://doi.org/10.1109/ CTIT.2018.8649531. Andrew, R.C., Malekian, R., Bogatinoska, D.C., 2018. IoT solutions for precision agriculture. In: 41st International Convention on Information and Communication Technology, Electronics and Microelectronics, MIPRO 2018 – Proceedings, Croatian Society MIPRO, pp. 345–349. https://doi.org/10.23919/MIPRO.2018.8400066. Anusha, K.Surendra, A.Mohan, H.K, M.V.Kirthika, N. Internet of things based smart irrigation using regression algorithm. https://doi.org/10.1109/ICICICT1.2017. 8342819. Azaza, M., Tanougast, C., Fabrizio, E., Mami, A., 2016. Smart greenhouse fuzzy logic based control system enhanced with wireless data monitoring. Elsevier-ISA Transactions 61, 297–307. https://doi.org/10.1016/j.isatra.2015.12.006. Bah, A., Balasundram, S.K., Husni, M.H.A., 2012. Sensor technologies for precision soil nutrient management and monitoring. Am. J. Agricultural Biol. Sci. 7 (1), 43–49. https://doi.org/10.3844/ajabssp.2012.43.49. 18 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Dela Cruz, J.R., Magsumbol, J.A.V., Dadios, E.P., Baldovino, R.G., Culibrina, F.B., Lim, L.A.G., 2017. Design of a fuzzy-based automated organic irrigation system for smart farm. In: HNICEM 2017–9th International Conference on Humanoid, Nanotechnology, Information Technology, Communication and Control, Environment and Management, https://doi.org/10.1109/HNICEM.2017.8269500. Delgoda, D.K., Saleem, S.K., Halgamuge, M.N., Malano, H., 2013. Multiple model predictive flood control in regulated river systems with uncertain inflows. Water Resour. Manage. 27 (3), 765–790. https://doi.org/10.1007/s11269-012-0214-y. Delgoda, D., Malano, H., Saleem, S.K., Halgamuge, M.N., 2016a. Irrigation control based on model predictive control (MPC): Formulation of theory and validation using weather forecast data and AQUACROP model. Environ. Modell. Software 78, 40–53. https://doi.org/10.1016/j.envsoft.2015.12.012. Delgoda, D., Saleem, S.K., Malano, H., Halgamuge, M.N., 2016b. Root zone soil moisture prediction models based on system identification: Formulation of the theory and validation using field and AQUACROP data. Agric. Water Manag. 163 (November 2017), 344–353. https://doi.org/10.1016/j.agwat.2015.08.011. Deng, Xiaolong, Dou, Yingtong, Hu, Dawei, 2018. Robust closed-loop control of vegetable production in plant factory. Comput. Electron. Agric. 155, 244–250. https://doi.org/ 10.1016/j.compag.2018.09.028. Difallah, W., Bounnama, F., Draoui, B., Benahmed, K., 2018. Intelligent irrigation management system. (IJACSA). Int. J. Adv. Comput. Sci. Appl. 9 (9), 429–433 https:// doi.org/Intelligent Irrigation Management System. Dilini Delgoda, K., Saleem, S.K., Malano, H., Halgamuge, M.N., 2014. A fair irrigation scheduling method prioritizing on the individual needs of the crops and infrastructure limitations. In: 21st Century Watershed Technology Conference and Workshop Improving Water Quality and the Environment, pp. 1–14. https://doi.org/ 10.13031/wtcw.2014-010. Dimitriadis, S., Goumopoulos, C., 2008. Applying machine learning to extract new knowledge in precision agriculture applications. In: Proceedings - 12th Pan-Hellenic Conference on Informatics, PCI, pp. 100–104. https://doi.org/10.1109/PCI.2008.30. Ding, Ying, Wang, Liang, Li, Yongwei, Li, Daoliang, 2018. Model predictive control and its application in agriculture: A review. Comput. Electron. Agric. 151, 104–117. https:// doi.org/10.1016/j.compag.2018.06.004. Divya, Y., 2019. Smart water monitoring system using cloud service. Int. J. Trend Sci. Res. Dev. (IJTSRD) 3 (2), 406–408. https://doi.org/10.31142/ijtsrd21379. Dlodlo, N., Josephat, K., 2015. The internet of things in agriculture for sustainable rural development. In: International Conference on Emerging Trends in Networks and Computer Communications (ETNCC). IEEE, pp. 13–18 https://doi.org/10.1109/ ETNCC.2015.7184801. Dubravko Ćulibrk, Minic, D.V.V., Osuna, M.A.F.J.A., Crnojevic, V., 2014. Sensing Technologies For Precision Irrigation. Springer New York Heidelberg Dordrecht London Library https://doi.org/DOI 10.1007/978-1-4614-8329-8. Eid, S., Abdrabbo, M., 2018. Developments of an expert system for on-farm irrigation water management under arid conditions. J. Soil Sci. Agric. Eng. 9 (1), 69–76. https://doi.org/10.21608/jssae.2018.35544. Elasbah, R., Selim, T., Mirdan, A., Berndtsson, R., Elasbah, R., Selim, T., Berndtsson, R., 2019. Modeling of fertilizer transport for various fertigation scenarios under drip irrigation. MDPI-Water 11 (5), 878–893. https://doi.org/10.3390/w11050893. Elijah, O., Orikumhi, I., Rahman, T.A., Babale, S.A., Orakwue, S.I., 2018. Enabling smart agriculture in Nigeria: Application of IoT and data analytics. In: 2017 IEEE 3rd International Conference on Electro-Technology for National Development, NIGERCON 2017, 2018-Janua, pp. 762–766. https://doi.org/10.1109/NIGERCON. 2017.8281944. Elijah, O., Rahman, T.A., Orikumhi, I., Leow, C.Y., Hindia, M.N., 2018b. An overview of internet of things (IoT) and data analytics in agriculture: benefits and challenges. IEEE Internet Things J. 4662 (c), 1–17. https://doi.org/10.1109/JIOT.2018. 2844296. Elshaikh, A.E., Jiao, X., Yang, S., 2018. Performance evaluation of irrigation projects: Theories, methods, and techniques. Agric. Water Manag. 203 (February), 87–96. https://doi.org/10.1016/j.agwat.2018.02.034. Evans, R.G., Iversen, W.M., Kim, Y., 2012. Integrated decision support, sensor networks, and adaptive control for wireless site-specific sprinkler irrigation. Appl. Eng. Agriculture, Am. Soc. Agricultural Biol. Eng. 28 (3), 377–387. Evans, R.G., Iversen, W.M., Kim, Y., 2012b. Integrated decision support, sensor networks, and adaptive control for wireless site-specific sprinkler irrigation. In: Applied Engineering in Agriculture 2012 American Society of Agricultural and Biological Engineers ISSN 0883-854, vol. 28, pp. 377–387. Evans, R.G., King, B.A., 2012. Site-specific sprinkler irrigation in a water-limited future. Transactions of the ASABE 2012 American Society of Agricultural and Biological Engineers ISSN 2151-0032, 55(2), 493–504. https://doi.org/10.13031/2013.35829. Evans, Robert G., Sadler, E.J., 2008. Methods and technologies to improve efficiency of water use. Water Rources Res. 44 (July), 1–15. https://doi.org/10.1029/ 2007WR006200. Evett, S., Shaughnessy, S.A.O., Colaizzi, P., 2009. Advanced irrigation engineering : Precision and precise. Dahlia Greidinger International Symposium January, 338–353. Fandika, I.R., Stirzaker, R., Chipula, G., 2019. Promoting social learning in soil water and nutrients management using farmer — friendly. In: MDPI-Proceedings at the third International Tropical Agriculture Conference (TROPAG 2019), Brisbane, Australia, vol. 36, p. 3390. https://doi.org/10.3390/proceedings2019036019. Fengshen, Sun, Ma, Weishun, Li, Heju, Wang, Songhong, 2018. Research on WaterFertilizer Integrated Technology Based on Neural Network Prediction and Fuzzy Control. IOP Conference Series: Earth and Environmental Science 170 (3), 1–7. https://doi.org/10.1088/1755-1315/170/3/032168. Fernández, J., 2017. Plant-based methods for irrigation scheduling of woody crops. Horticulturae 3 (2), 35. https://doi.org/10.3390/horticulturae3020035. Fernando, F., Marcuzzo, N., Wendland, E.C., 2014. The optimization of irrigation networks using genetic algorithms. J. Water Resour. Prot. 6 (September), 1124–1138. https://doi.org/10.4236/jwarp.2014.612105. Ferrández-Pastor, F.J., García-Chamizo, J.M., Nieto-Hidalgo, M., Mora-Martínez, J., 2018. Precision agriculture design method using a distributed computing architecture on internet of things context. MDPI, Sensors (Switzerland) 18 (6), 1710–1731. https://doi.org/10.3390/s18061731. Ferrarezi, R.S., T.R., 2016. Performance of wick irrigation system using self- compensating troughs with substrates for lettuce production. J. Plant Nutr., 39(1), 147–161. https://doi.org/10.1080/01904167.2014.983127. Fuentes, B.S., Tongson, E., 2018. Advances and requirements for machine learning and artificial intelligence applications in viticulture. Wine & Viticulture J. 47–51. Fujimaki, H., Inoue, M., Mamedov, A., Ikeguchi, N., Nakai, R., 2018. Salinity management under a capillary-driven automatic irrigation system. J. Arid Land Stud. 118, 115–118. Ghodake, M.R.G., Mulani, M.A.O., 2016. Sensor based automatic drip irrigation system. J. Res. 02 (02), 53–56. Gillies, M., 2017. Modernisation of furrow irrigation in the sugar industry: final report 2014/079. Sugar Research Australia Ltd. Retrieved from http://elibrary.sugarresearch.com.au/. Goap, A., Sharma, D., Shukla, A.K., Rama Krishna, C., 2018. An IoT based smart irrigation management system using Machine learning and open source technologies. Comput. Electron. Agric. 155 (May), 41–49. https://doi.org/10.1016/j.compag.2018.09.040. Goldstein, A., Fink, L., Meitin, A., Bohadana, S., Lutenberg, O., Ravid, G., 2018. Applying machine learning on sensor data for irrigation recommendations: revealing the agronomist’s tacit knowledge. Precis. Agric. 19 (3), 421–444. https://doi.org/10. 1007/s11119-017-9527-4. Goodchild, M.S., Kühn, K.D., Jenkins, M.D., Burek, K.J., Dutton, J.A., 2015. A method for precision closed-loop irrigation using a modified PID control algorithm. Sensors & Transducers 188 (5), 61–68. https://doi.org/10.1097/ALN.0b013e318223b78b. Gu, J., Yin, G., Huang, P., Guo, J., Chen, L., 2017. An improved back propagation neural network prediction model for subsurface drip irrigation system. Comput. Electr. Eng. 60, 58–65. https://doi.org/10.1016/j.compeleceng.2017.02.016. Hamouda, Y.E.M., 2017. Smart irrigation decision support based on fuzzy logic using wireless sensor network. In: International Conference on Promising Electronic Technologies, pp. 109–113. https://doi.org/10.1109/ICPET.2017.26. Harper, S., 2017. Real-time control of soil moisture for efficient irrigation. https://doi. org/10.1111/icad.12044. Harun, A.N., Mohamed, N., Ahmad, R., Rahim, A.R.A., Ani, N.N., 2019. Improved Internet of Things (IoT)monitoring system for growth optimization of Brassica chinensis. Comput. Electron. Agric. 1–11. https://doi.org/10.1016/j.compag.2019.05. 045. Harun, A.N., Rawidean, M., Kassim, M., Mat, I., Ramli, S.S., 2015. Precision irrigation using wireless sensor network. In: International Conference on Smart Sensors and Application (ICSSA). IEEE, pp. 71–75. https://doi.org/10.1109/ICSSA.2015. 7322513. Hasan, F., Haque, M.M., Khan, M.R., Ruhi, R.I., Charkabarty, A., 2018. Implementation of fuzzy logic in autonomous irrigation system for efficient use of water. In: Joint 7th International Conference on Informatics, Electronics & Vision (ICIEV) and 2nd International Conference on Imaging, Vision & Pattern Recognition (IcIVPR), 234–238. https://doi.org/10.1109/ICIEV.2018.8641017. Hebbar, S., Golla, V.P., 2017. Automatic water supply system for plants by using wireless sensor network. In: International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC 2017) Automatic, pp. 742–745. Hemming, S., Zwart, F. De, Elings, A., Righini, I., Petropoulou, A., 2019. Remote control of greenhouse vegetable production irrigation, and crop production. MDPI-Sensors Article 19, 1785–1807. https://doi.org/10.3390/s19081807. Hou, L., Shang, J., Liu, J., Lu, H., Qi, Z., 2015. Soil water movement under a drip irrigation double-point source. Water Sci. Technol. Water Supply 15 (5), 924–932. https://doi.org/10.2166/ws.2015.045. Hussain, M.H., Min, T.W., Siraj, S.F., Rahim, S.R.A., Hashim, N., Sulaiman, M.H., 2011. Fuzzy logic controller for automation of greenhouse irrigation system. In: 3rd CUTSE International Conference (CUTSE 2011). Hussan, E., Hamouda, A., 2014. Implementation fuzzy irrigation controller (mamdani and sugeno performance comparison). Int. J. Adv. Res. Electr., Electron. Instrum. Eng. 03 (11), 12819–12824. https://doi.org/10.15662/ijareeie.2014.0311004. Huuskonen, J., Oksanen, T., 2018. Soil sampling with drones and augmented reality in precision agriculture. Comput. Electron. Agric. 154 (September), 25–35. https://doi. org/10.1016/j.compag.2018.08.039. Isık, M.F., Sönmez, Y., Yılmaz, C., Özdemir, V., Yılmaz, E.N., 2017. Precision irrigation system (PIS) using sensor network technology integrated with IOS/android application. MDPI-Appl. Sci. 7 (9), 1–14. https://doi.org/10.3390/app7090891. Izzuddin, T.A., Johari, M.A., Rashid, M.Z.A., Jali, M.H., 2018. Smart irrigation using fuzzy logic method. ARPN J. Eng. Appl. Sci. 13 (2), 517–522. Javalera, V., Morcego, B., Puig, V., 2010. Distributed MPC for large scale systems using agent-based reinforcement learning. IFAC Proceedings Volumes (IFACPapersOnline), 9(PART 1), 597–602. https://doi.org/10.3182/20100712-3-FR-2020. 00097. Jawad, H.M., Nordin, R., Gharghan, S.K., 2017. Energy-efficient wireless sensor networks for precision agriculture: a review. Sensors-MDP I, 17. https://doi.org/10.3390/ s17081781. Jayaraman, P., Yavari, A., Georgakopoulos, D., Morshed, A., Zaslavsky, A., 2016. Internet of things platform for smart farming: experiences and lessons learnt. Sensors MDPI 1–17. https://doi.org/10.3390/s16111884. Jha, R.K., Kumar, S., Joshi, K., Pandey, R., 2017. Field monitoring using IoT in agriculture. In: 2017 International Conference on Intelligent Computing, Instrumentation and Control Technologies (ICICICT, pp. 1417–1420. 19 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Jia, X., Huang, Y., Wang, Y., Sun, D., 2019. Research on water and fertilizer irrigation system of tea plantation. Int. J. Distrib. Sens. Netw. 15 (3). https://doi.org/10.1177/ 1550147719840182. Jianfeng, Z., Zhu, Y., Zhang, X., Ye, M., Yang, J., 2018. Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas. J. Hydrol. 561 (April), 918–929. https://doi.org/10.1016/j.jhydrol.2018.04.065. Joly, M., Mazenq, L., Marlet, M., Temple-Boyer, P., Durieu, C., Launay, J., 2017. Multimodal probe based on ISFET electrochemical microsensors for in-situ monitoring of soil nutrients in agriculture. Proceedings, 1(10), 420. https://doi.org/10. 3390/proceedings1040420. Jones, J.W., Hoogenboom, G., Porter, C.H., Boote, K.J., Batchelor, W.D., Hunt, L.A., ... Ritchie, J.T., 2003. The DSSAT cropping system model. Elsevier Science, Europ. J. Agronomy 18. Kale, A.P., Sonavane, S.P., 2019. IoT based Smart Farming : Feature subset selection for optimized high- dimensional data using improved GA based approach for ELM. Comput. Electron. Agric., 161(November 2018), 225–232. https://doi.org/10.1016/ j.compag.2018.04.027. Kamal, R., Muhammed, H.H., Mojid, M.A., 2019. Two-dimensional modeling of water distribution under capillary wick irrigation system. Science & Technology, Pertanika J. Sci. & Technol. 27 (1): 205–223 (2019) Science, 27(1), 205–223. Retrieved from http://www.pertanika.upm.edu.my/%0A. Kamilaris, A., Kartakoullis, A., Prenafeta-boldú, F.X., 2017. A review on the practice of big data analysis in agriculture. Comput. Electron. Agric. 143 (September), 23–37. https://doi.org/10.1016/j.compag.2017.09.037. Karim, F., Karim, F., Ali, F., 2017. Monitoring system using web of things in precision agriculture. In: The 12th International Conference on Future Networks and Communications (FNC 2017). Elsevier B.V., pp. 402–409 https://doi.org/10.1016/ j.procs.2017.06.083. Kelley, J., Pardyjak, E.R., 2019. Using neural networks to estimate site-specific crop evapotranspiration with low-cost sensors. MDPI Agronomy Article 9 (108), 1–17. https://doi.org/10.3390/agronomy9020108. Keswani, B., Mohapatra, A.G., Mohanty, A., Khanna, A., Rodrigues, J.J.P.C., Gupta, D., de Albuquerque, V.H.C., 2018. Adapting weather conditions based IoT enabled smart irrigation technique in precision agriculture mechanisms. Neural Comput. Appl. 1, 1–16. https://doi.org/10.1007/s00521-018-3737-1. Khamkar, M.N.U., 2014. Design and Implementation of Expert System in Irrigation of Sugarcane: Conceptual Study. Sinhgad Institute. Khanna Abhishek, S.K., 2019. Evolution of internet of things (IoT) and its significant impact in the field of precision agriculture. Comput. Electron. Agric. 157, 218–231. https://doi.org/10.1016/j.compag.2018.12.039. Kinoshita, T., Masuda, M., Watanabe, S., Nakano, Y., 2010. Application of controlledrelease fertilizer to forcing culture of tomato using root-proof capillary wick. Hortic Resour. 9 (1), 39–46. https://doi.org/10.2503/hrj.9.39. Klein, L.J., Hamann, H.F., Hinds, N., Guha, S., Sanchez, L., Sams, B., Dokoozlian, N., 2018. Closed loop controlled precision irrigation sensor network. IEEE Internet Things J. 5 (6), 4580–4588. https://doi.org/10.1109/JIOT.2018.2865527. Koech, R., Langat, P., 2018. Improving irrigation water use efficiency: A review of advances, challenges and opportunities in the Australian context. MDPI J.-Water (Switzerland) 10 (12), 1754–1771. https://doi.org/10.3390/w10121771. Koech, R., Smith, R., Gillies, M., 2010. Automation and control in surface irrigation systems: Current status and expected future trends. In: Southern Region Engineering Conference, SREC 2010, pp. 11–17. Kothawade, S.N., Furkhan, S.M., Raoof, A., Mhaske, K.S., 2016. Efficient water management for greenland using soil moisture sensor. In: 1st IEEE International Conference on Power Electronics, Intelligent Control and Energy Systems (ICPEICES2016), pp. 1–4. https://doi.org/10.1109/ICPEICES.2016.7853281. Krishna, K.L., 2017. Internet of things application for implementation of smart agriculture system. International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC 2017) Fig., 54–59. Kumar, V. Vinoth, Ramasamy, R., Janarthanan, S., VasimBabu, M., 2017. Implementation of IoT in smart irrigation system using arduino processor. Int. J. Civil Eng. Technol. (IJCIET) 8 (10), 1304–1314. http://http://www.iaeme.com/ijciet/issues.asp? JType=IJCIET&VType=8&IType=10. Kushwaha, D.S., Taram, M., Taram, A., 2015. A framework for technologically advanced smart agriculture scenario in India based on internet of things model. Int. J. Eng. Trends Technol. (IJETT) 27 (4), 182–185. Lakhiar, I.A., Jianmin, G., Syed, T.N., Chandio, F.A., Buttar, N.A., Qureshi, W.A., 2018. Monitoring and control systems in agriculture using intelligent sensor techniques: a review of the aeroponic system. Hindawi J. Sens. 2018, 1–18. https://doi.org/10. 1155/2018/8672769. Ławrýnczuk, M., 2013. Computationally Efficient Model Predictive Control Algorithms A Neural Network Approach. Springer International Publishing Switzerland https:// doi.org/10.1007/978-3-319-04229-9, third ed. Lee, J.B., Gondhalekar, R., Dassau, E., Doyle, F.J., 2016. Shaping the MPC cost function for superior automated glucose control. Int. Federa. Automat. Control 49 (7), 779–784. https://doi.org/10.1016/j.ifacol.2016.07.283. Lefkowitz, M., 2019. Smart irrigation model predicts rainfall to conserve water. Retrieved July 26, 2019, from https://phys.org/news/2019-07-smart-irrigation-rainfall.htm. Levidow, L., Zaccaria, D., Maia, R., Vivas, E., Todorovic, M., Scardigno, A., 2014. Improving water-efficient irrigation: Prospects and difficulties of innovative practices. Agric. Water Manag. 146, 84–94. https://doi.org/10.1016/j.agwat.2014.07. 012. Li, Q., Sugihara, T., Kodaira, M., Shibusawa, S., 2018. Water use efficiency of precision irrigation system under critical water-saving condition. In: 14th International Conference on Precision Agriculture June, pp. 1–7. Montreal, Quebec, Canada. Li, Z., Wang, J., Higgs, R., Zhou, L., Yuan, W., 2017. Design of an intelligent management system for agricultural greenhouses based on the internet of things. In: IEEE International Conference on Computational Science and Engineering and IEEE/IFIP International Conference on Embedded and Ubiquitous Computing, CSE and EUC, vol. 2, pp. 154–160. https://doi.org/10.1109/CSE-EUC.2017.212. Liakos, K.G., Busato, P., Moshou, D., Pearson, S., Bochtis, D., 2018. Machine learning in agriculture: A review. Sensors (Switzerland) 18 (8), 1–29. https://doi.org/10.3390/ s18082674. Lijia, Sun, Yanxiang, Yang, Jiang, Hu, Dana, Porter, Thomas, Marek, Charles, Hillyer, 2018. Reinforcement learning control for water-efficient agricultural irrigation. Proceedings - 15th IEEE International Symposium on Parallel and Distributed Processing with Applications and 16th IEEE International Conference on Ubiquitous Computing and Communications, ISPA/IUCC 2017 1334–1341. https://doi.org/10. 1109/ISPA/IUCC.2017.00203 1334. Lin, H., Cai, K., Chen, H., Zeng, Z., 2015. The construction of a precise agricultural information system based on internet of things. Int. J. Online Biomed. Eng. (IJOE) 11 (6), 10–15. https://doi.org/10.3991/ijoe.v11i6.4847. Liu, Y., Yang, T., Zhao, R.-H., Li, Y.-B., Zhao, W.-J., Ma, X.-Y., 2018. Irrigation canal system delivery scheduling based on a particle swarm optimization algorithm. MDPIWater 10 (9), 1268–1281. https://doi.org/10.3390/w10091281. Lozoya, C., Eyzaguirre, E., Espinoza, J., Montes-fonseca, S.L., Rosas-perez, G., 2019. Spectral vegetation index sensor evaluation for greenhouse precision agriculture. IEEE SENSORS 2019, 1–4. Lozoya, C., Mendoza, C., Aguilar, A., Román, A., Castelló, R., 2016. Sensor-based model driven control strategy for precision irrigation. J. Sens. 2016 (9784071), 1–12. https://doi.org/10.1155/2016/9784071. Lozoya, C., Mendoza, C., Mej, L., Mendoza, G., Bustillos, M., Arras, O., Sol, L., 2014. Model predictive control for closed-loop irrigation. In: Preprints of the 19th World Congress The International Federation of Automatic Control, Cape Town, South Africa, pp. 4429–4434. Ma, Y., Shi, J., Chen, J., Hsu, C., Chuang, C., 2019. Integration agricultural knowledge and internet of things for multi-agent deficit irrigation control. In: 21st International Conference on Advanced Communication Technology (ICACT). Global IT Research Institute (GIRI). https://doi.org/10.23919/ICACT.2019.8702012, pp. 299–304. Mantri, G., Kulkarni, N.R., 2013. Design and optimization of pid controller using genetic algorithm. Int. J. Res. Eng. Technol. (IJRET) 2 (6), 926–930. https://doi.org/10. 15623/ijret.2013.0206002. Mao, Y., Liu, S., Nahar, J., Liu, J., Ding, F., 2018. Soil moisture regulation of agro-hydrological systems using zone model predictive control. Comput. Electron. Agric. 154 (March), 239–247. https://doi.org/10.1016/j.compag.2018.09.011. Marinescu, T., Arghira, N., Hossu, D., Fagarasan, I., 2017. Advanced control strategies for irrigation systems. In: The 9th IEEE International Conference on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications 21-23 September, 2017, Bucharest, Romania, pp. 843–848. Martín, J., Eduardo, L., Alejandro, J., Alejandra, M., Manuel, J., Teresa, D., Ernesto, L., 2017. Review of IoT applications in agro-industrial and environmental fields. Comput. Electron. Agric. 142 (118), 283–297. https://doi.org/10.1016/j.compag. 2017.09.015. Masuda, M.F.S., 2008. Potential for tomato cultivation using capillary wick-watering method. Bull Fac Agric Okayama Univ., vol. 6. Mathur, Y.P., Sharma, G., Pawde, A.W., 2009. Optimal operation scheduling of irrigation canals using genetic algorithm. Int. J. Recent Trends Eng. 1 (6), 1–6 https://doi.org/ ijrte0106011015. Mathworks, T., 2015. System identification toolbox TM getting reference R 2015 a how to contact MathWorks. Mccarthy, A.C., Hancock, N.H., Raine, S.R., 2014. Simulation of irrigation control strategies for cotton using model predictive control within the VARIwise simulation framework. Comput. Electron. Agric. 101, 135–147. https://doi.org/10.1016/j. compag.2013.12.004. Mehra, M., Saxena, S., Sankaranarayanan, S., Tom, R.J., Veeramanikandan, M., 2018. IoT based hydroponics system using deep neural networks. Comput. Electron. Agriculture 155 (October), 473–486 https://doi.org/S0168169918311839. Mishra, S., Deep, V., Akankasha, 2014. Expert systems in agriculture: an overview. Int. J. Sci. Technol. Eng. 1 (5), 45–49. Mohamed, K., Mahdy, A. El, Refai, M., 2015. Model predictive control using FPGA. Int. J. Control Theory Comput. Model. (IJCTCM) 5 (2), 1–4. https://doi.org/10.5121/ ijctcm.2015.5201. Mohanraj, I., Ashokumar, K., Naren, J., 2016. Field monitoring and automation using IOT in agriculture domain. Procedia Comput. Sci., ScienceDirect 93 (September), 931–939. https://doi.org/10.1016/j.procs.2016.07.275. Mohanraj, I., Gokul, V., Ezhilarasie, R., Umamakeswari, A., 2017. Intelligent drip irrigation and fertigation using wireless sensor networks. In: IEEE technological innovations in ICT for agriculture and rural development, TIAR, vol. 2018-Janua, pp. 36–41. https://doi.org/10.1109/TIAR.2017.8273682. Montesano, F.F., Van Iersel, M.W., Parente, A., 2016. Timer versus moisture sensor-based irrigation control of soilless lettuce: Effects on yield, quality and water use efficiency. Horticultural Sci. 43 (2), 67–75. https://doi.org/10.17221/312/2014-HORTSCI. Moubarak, A., El-Saady, G., Ibrahim, E.N.A., 2018. Optimal operation of renewable energy irrigation system using particle swarm optimization. ARPN J. Eng. Appl. Sci. 13 (24), 9318–9327. https://doi.org/10.31224/osf.io/hbj6d. Mousa A, K, Crook M, S, Abdullah M, N, 2014. Fuzzy based decision support model for irrigation system management. International Journal Computer Application 104 (9). https://doi.org/10.5120/18230-9177. Munoth, P., Goyal, R., Tiwari, K., 2016. Sensor based irrigation system: A review. Int. J. Engg. Res. Tech. 4 (23), 86–90 https://doi.org/IJERTCONV4IS23026. Nada, A., Nasr, M., Hazman, M., 2014. Irrigation expert system for trees. Int. J. Eng. Innovative Technol. (IJEIT) 3 (8), 170–175 Retrieved from http://ijeit.com/Vol 3/ 20 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. Issue 8/IJEIT1412201402_31.pdf. Nalliah, V., Sri Ranjan, R., 2010. Evaluation of a capillary-irrigation system for better yield and quality of hot pepper (capsicum annuum). Appl. Eng. Agric. 26 (5), 807–816. https://doi.org/10.13031/2013.34941. Nath, S., Nath, J. Kumar, Sarma, P.K.C., 2018. IoT based system for continuous measurement and monitoring of temperature, soil moisture and relative humidity. Int. J. Electr. Eng. Technol. (IJEET) 9 (3), 106–113. Niu, Q., Fratta, D., Wang, Y.-H., 2015. Precision agriculture * a worldwide overview. J. Hydrol. 522 (20150806), 475–487 Retrieved from http://linkinghub.elsevier.com/ retrieve/pii/S002216941401066X. Norhaliza, A.W., Katebi, R., Jonas, B., 2011. Multivariable PID control of an activated sludge wastewater treatment process. In: Mansour, T., (Ed.), PID Control Implementation and Tuning, Vol. 1. https://doi.org/10.5772/652. Nutini, F., Stroppiana, D., Busetto, L., Bellingeri, D., Corbari, C., Mancini, M., Boschetti, M., 2017. A weekly indicator of surface moisture status from satellite data for operational monitoring of crop conditions. Sensors (Switzerland) 17 (6). https://doi. org/10.3390/s17061338. O’Grady, M.J., O’Hare, G.M.P., 2017. Modelling the smart farm. Information Process. Agriculture 4 (3), 179–187. https://doi.org/10.1016/j.inpa.2017.05.001. Obiechefu, G.C., 2017. Evaluation of evapotranspiration models for waterleaf crop using data from lysimeter. In: ASABE Annual International Meeting Sponsored by ASABE, pp. 1–13. https://doi.org/10.13031/aim.201700025. Oborkhale, Lawrence I., Abioye, A.E., Egonwa, B.O., Olalekan, T.A., 2015. Design and Implementation of Automatic Irrigation Control System. IOSR J. Comput. Eng. (IOSRJCE) 17 (4), 99–111. https://doi.org/10.9790/0661-174299111. Ocampo-Martinez, C., 2010. Model Predictive Control of Wastewater Systems. SpringerVerlag London Limited, London https://doi.org/10.1007/978-1-84996-353-4. Ohaba, Shukri, Qichen, Shibusawa, Kodaira, Osato, 2015. Adaptive control of capillary water flow under modified subsurface irrigation based on a SPAC model. In: Proceedings of the 7th International Conference on Precision Agriculture (ICPA 2015). Ooi, S.K., Weyer, E., 2008. Control design for an irrigation channel from physical data. Elsevier-Science Direct 16, 1132–1150. https://doi.org/10.1016/j.conengprac.2008. 01.004. Panawong, N., Namahoot, C.S., 2017. Cultivation of plants harnessing an ontologybased expert system and a wireless sensor network. J. Telecommun., Electron. Comput. Eng. 9 (2–3), 109–113. Park, Y., Shamma, J.S., Harmon, T.C., 2009. A receding horizon control algorithm for adaptive management of soil moisture and chemical levels during irrigation. Environ. Modell. Software 24 (9), 1112–1121. https://doi.org/10.1016/j.envsoft.2009.02. 008. Patel, A., Sharda, R., Siag, M., 2017. Development of decision support system for on-farm irrigation water management. Int. J. Pure Appl. Biosci. 5 (3), 749–763. https://doi. org/10.18782/2320-7051.2561. Patil, P., Kulkarni, U., Desai, B.L., Benagi, V.I., Naragund, V.B., 2012. Fuzzy logic based irrigation control system using wireless sensor network for precision agriculture. Proceeding of the 3rd national conference on agro-informatics and precision agriculture (AIPA 2012), 1-3 August 2012, Hyderabad, India, 262–269. Patil, P., Desai, L.B., 2013. Intelligent irrigation control system by employing wireless sensor networks. Int. J. Comput. Appl. 79 (11), 33–40. https://doi.org/10.5120/ 13788-1882. Pawde, Anil W., Mathur, Yogesh P., Kumar, Rajesh, 2013. Optimal Water Scheduling in Irrigation Canal Network using Particle Swarm Optimization. Wiley Online (Irrigation and Drainage) 62, 135–144. https://doi.org/10.1002/ird.1707. Perea, R.G., Camacho, E., Montesinos, P., Gonz, R., Rodrı, J.A., 2018. Optimisation of water demand forecasting by artificial intelligence with short data sets. ScienceDirect-Biosyst. Eng. 7, 3–10. https://doi.org/10.1016/j.biosystemseng.2018. 03.011. Pereira, R.M.S., Lopes, S., Caldeira, A., Fonte, V., 2018. Optimized planning of different crops in a field using optimal control in Portugal. Sustainability Article, MDPI 1–16. https://doi.org/10.3390/su10124648. Peters, R.T., 2014. Low Energy Precision Application (LEPA) Low Energy Spray Application (LESA) on Center Pivots in the PNW. WSU Irrigated Agriculture Research and Extension Center, Prosser, WA Howard. Pham, X., Stack, M., 2018. How data analytics is transforming agriculture. Business Horizons, ScienceDirect Www. Elsevier. Com 61 (1). https://doi.org/10.1016/j. bushor.2017.09.011. Picard, D., Sourbron, M., Jorissen, F., 2016. Comparison of model predictive control performance using grey-box and white-box controller models of a multi-zone office building. International High Performance Buildings Conference 4. Pierpaoli, E., Carli, G., Pignatti, E., Canavari, M., 2013. Drivers of precision agriculture technologies adoption. A literature review. Procedia Technol. 8 (Haicta), 61–69. https://doi.org/10.1016/j.protcy.2013.11.010. Pongnumkul, S., Chaovalit, P., Surasvadi, N., 2015. Applications of smartphone-based sensors in agriculture: a systematic review of research. Hindawi Publishing Corporation, J. Sens. 2015. Pramanik, Lai, Ray, Patra, 2016. Effect of drip fertigation on yield, water use efficiency, and nutrients availability in banana in West Bengal, India. Commun Soil Sci Plant Anal., 47, 13–14. https://doi.org/10.1080/00103624.2016.1206560 55. Prasad, A.N., Mamun, K.A., Islam, F.R., Haqva, H., 2016. Smart water quality monitoring system. In: 2nd Asia-Pacific World Congress on Computer Science and Engineering, APWC on CSE 2015, pp. 1–6. IEEE. https://doi.org/10.1109/APWCCSE.2015. 7476234. Puig, V., Ocampo-Martinez, C., Romera, J., Quevedo, J., Negenborn, R., Rodriguez, P., de Campos, S., 2012. Model predictive control of combined irrigation and water supply systems: Application to the Guadiana river. In: Proceedings of 2012 9th IEEE International Conference on Networking, Sensing and Control. IEEE, pp. 85–90 https://doi.org/10.1109/ICNSC.2012.6204896. Qin, S.J., Badgwell, T.A., 2003. An overview of industrial model predictive control technology. Control Eng. Practice 11 (7), 733–764 https://doi.org/10.1.1.52.8909. Rad, C., Hancu, O., Takacs, I., 2015. Smart monitoring of potato crop: a cyber-physical system architecture model in the field of precision agriculture. ST26733”. International Conference “Agriculture for Life, Life for Agriculture 6, 73–79. https:// doi.org/10.1016/j.aaspro.2015.08.041. Ragab, S., El-Gindy, A., Arafa, Y., Gaballah, M., 2018. An expert system for selecting the technical specifications of drip irrigation control unit. Arab Universities J. Agricultural Sci. 26 (2), 601–609. https://doi.org/10.21608/ajs.2018.15965. Rahman, M.K.I.A., Abidin, M.S.Z., Azimi, M.S., Mahmud, S.B., Ishak, M.H.I., Emmanuel, A.A., 2019. Advancement of a smart fibrous capillary irrigation management system with an internet of things intgration. Bull. Electr. Eng. Inf. 8 (4), 1402–1410. https:// doi.org/10.11591/EEI.V8I4.1606. Rahman, M.K.I.A., Abidin, M.S.Z., Buyamin, S., Mahmud, M.S.A., 2018. Enhanced fertigation control system towards higher water saving irrigation. Indonesian J. Electr. Eng. Comput. Sci. 10 (3), 859–866. https://doi.org/10.11591/ijeecs.v10.i3.pp859866. Rahmat, M.F., Samsudin, S.I., Wahab, N.A., Najib, S., Salim, S., 2011. Control strategies of wastewater treatment plants control strategies of wastewater treatment plants. Aust. J. Basic & Appl. Sci. 5 (8), 2011 (May 2014). Raine, S.R., Mccarthy, A.C., 2014. Advances in intelligent and autonomous systems to improve irrigation and fertiliser efficiency. In: 27th Annual FLRC Workshop held at Massey University, Palmerston North, New Zealand, New Zealand. Retrieved from http://eprints.usq.edu.au/id/eprint/24973. Rajalakshmi, P., Devi, M., 2016. IOT based crop-field monitoring and irrigation automation. In: Proceedings of the 10th International Conference on Intelligent Systems and Control, ISCO 2016, pp. 1–6. https://doi.org/10.1109/ISCO.2016.7726900. Rajeswari, S., Suthendran, K., Rajakumar, K., 2017. A smart agricultural model by integrating IoT, mobile and cloud-based big data analytics. In: International Conference on Intelligent Computing and Control (I2C2). https://doi.org/10.1109/I2C2.2017. 8321902. Rajkumar, M.N., Abinaya, S., Kumar, V.V., 2017. Intelligent irrigation system - An IOT based approach. In: IEEE International Conference on Innovations in Green Energy and Healthcare Technologies – IGEHT, pp. 1–5. https://doi.org/10.1109/IGEHT. 2017.8094057. Ramesh, M.V., Rangan, V.P., 2017. High yield groundnut agronomy: an IoT based precision farming framework. IEEE Global Humanitarian Technology Conference (GHTC). https://doi.org/10.1109/GHTC.2017.8239287. Ramli, L., Mohamed, Z., Abdullahi, A.M., Jaafar, H.I., Lazim, I.M., 2017. Control strategies for crane systems : A comprehensive review. Mech. Syst. Sig. Process. 95, 1–23. https://doi.org/10.1016/j.ymssp.2017.03.015. Rao, R. Nageswara, Sridhar, B., 2018. IOT Based Smart Crop-Field Monitoring And Irrigation Automation. Proceedings of the Second International Conference on Inventive Systems and Control (ICISC 2018)-IEEE Xplore Compliant 18, 478–483 978-1-5386-0807-4. Ravina, I., Paz, E., Sofer, Z., Marcu, A., Shisha, A., Sagi, G., 1992. Control of emitter clogging in drip irrigation with reclaimed wastewater. Irrig. Sci. 13 (3), 129–139. https://doi.org/10.1007/BF00191055. Rekha, H.J., Kombali, G., Kumara, G., 2015. Impact of drip fertigation on water use efficiency and economics of aerobic rice. Irrigation Drain Syst. Eng. 04 (S1), 1–3. https://doi.org/10.4172/2168-939768.S1-00156. Rodríguez, D., Reca, J., Martínez, J., López-Luque, R., Urrestarazu, M., 2015. Development of a new control algorithm for automatic irrigation scheduling in soilless culture. Appl. Math. Inf. Sci. 9 (1), 47–56. https://doi.org/10.12785/amis/ 090107. Saleem, S.K., Delgoda, D.K., Ooi, S.K., Dassanayake, K.B., Liu, L., Halgamuge, M.N., Malano, H., 2013. Model predictive control for real-time irrigation scheduling. In: Proceedings of the 4th IFAC Conference on Modelling and Control in Agriculture, Horticulture and Post Harvest Industry. https://doi.org/10.3182/20130828-2-SF3019.00062. Sadati, S.K., Ghahraman, B., Speelman, S., Sabouhi, M., Gitizadeh, M., 2014. Optimal irrigation water allocation using a genetic algorithm under various weather conditions. MDPI-Water 6, 3068–3084. https://doi.org/10.3390/w6103068. Saiful, M., Mahmud, A., Shukri, M., Abidin, Z., Emmanuel, A.A., Hasan, H.S., 2020. Robotics and automation in agriculture: present and future applications. Appl.Model. Simul. 4, 130–140. http://arqiipubl.com/ojs/index.php/AMS_Journal/article/view/ 130. Salvi, S., A, P.J.S., Sanjay, H.A., Harshita, T.K., Farhana, M., Jain, N., Suhas, M.V., 2017. Cloud based data analysis and monitoring of smart multi-level irrigation system using IoT. In: International conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud) (I-SMAC 2017), pp. 752–757. Saraf, S.B., Gawali, D.H., 2017. IoT based smart irrigation monitoring and controlling system. In: IEEE International Conference On Recent Trends in Electronics Information & Communication Technology (RTEICT), pp. 1–5. Say, S.M., Keskin, M., Sehri, M., Sekerli, Y.E., Engineering, T., 2018. Adoption of precision agriculture technologies in developed and developing countries. In: International Science and Technology Conference (ISTEC). Berlin, Germany, vol. 8, pp. 7–15. Semananda, N., Ward, J., Myers, B., 2018. A semi-systematic review of capillary irrigation: the benefits, limitations, and opportunities. Horticulturae 4 (3), 23. https://doi. org/10.3390/horticulturae4030023. Shahzadi, R., Ferzund, J., Tausif, M., Asif, M., 2016. Internet of things based expert system for smart agriculture. Int. J. Adv. Comput. Sci. Appl. 7 (9). https://doi.org/10. 14569/ijacsa.2016.070947. Sharma, S., Regulwar, D.G., 2016. Prediction of evapotranspiration by artificial neural 21 Computers and Electronics in Agriculture 173 (2020) 105441 E.A. Abioye, et al. network and conventional prediction of evapotranspiration by artificial neural network and conventional methods, (May), 1–5. https://doi.org/10.17950/ijer/v5i1/ 043. Shashi, S., Joe, C., Chandra, K., Francisco, M., 2017. Intelligent infrastructure for smart agriculture : an integrated food, energy and water system. Computing Community Consortium Catalyst. USA. Retrieved from http://cra.org/ccc/resources/ccc-ledwhitepapers/#infrastructure. Shang, C., Chen, W.-H., Stroock, A.D., You, F., 2019. Robust model predictive control of irrigation systems with active uncertainty learning and data analytics. IEEE Trans. Control Syst. Technol. 1–12. https://doi.org/10.1109/TCST.2019.2916753. Shekhar, Y., Dagur, E., Mishra, S., Tom, R.J., Veeramanikandan, M., 2017. Intelligent IoT based automated irrigation system. Int. J. Appl. Eng. Res. 12 (18), 7306–7320 https://doi.org/0000-0001-5145-510X. Shibusawa, S., 2001. Precision farming approaches to small-farm agriculture. Elsevier2nd IFAC-CIGR Workshop on Intelligent Control and Agricultural Applications [Preprints], Bali, Indonesia., 34(11), 1–10. https://doi.org/https://doi.org/10.1016/ S1474-6670(17)34099-5. Shigeta, R., Kawahara, Y., Goud, G.D., Naik, B.B., 2018. Capacitive-touch-based soil monitoring device with exchangeable sensor probe. In: 2018 IEEE SENSORS, IEEE, pp. 1–4. https://doi.org/DOI:10.1109/icsens.2018.8589698. Shukri Bin Zainal Abidin, Shibusawa, S., Ohaba, M., Qichen, L., Kodaira, M., 2012. Transient water flow model in a soil-plant system for subsurface precision irrigation. In: Proceedings of the 13th International Conference on Precision Agriculture (ICPA 2012), pp. 1–8. Singh, S.N., Jha, R., 2012. Optimal design of solar powered fuzzy control irrigation system for cultivation of green vegetable plants in rural India. In: 1st Int’l Conf. on Recent Advances in Information Technology | RAIT-2012 |. https://doi.org/10.1109/ RAIT.2012.6194541. Smith, & Baillie, 2009. Defining precision irrigation : A new approach to irrigation management. In: Irrigation and Drainage Conference 2009, Irrigation Australia Ltd, Swan Hill, Vic, Australia, pp. 18–21. Smith, R.J., Baillie, J.N., Mccarthy, A.C., Raine, S.R., Baillie, C.P., 2010. Review of Precision Irrigation Technologies and their Application. National Centre for Engineering in Agriculture University of Southern Queensland Toowoomba. Shukri, Bin Zainal Abidin, Shibusawa, S, Ohaba, M, Li, Q, Kalid, M. Bin, 2014. Capillary flow responses in a soil – plant system for modified subsurface precision irrigation. Precision Agric Open Access at Springerlink.Com 15, 17–30. https://doi.org/10. 1007/s11119-013-9309-6. Shukri, Bin Zainal Abidin, Shibusawa, S, Ohaba, M, Li, Q, Marzuki K, B, 2014. Water uptake response of plant in subsurface precision irrigation system. Sci. Direct-Eng. Agriculture, Environ. Food 6 (3), 128–134. https://doi.org/10.1016/s1881-8366(13) 80022-5. Smith, R.J., Raine, S.R., McCarthy, A.C., Hancock, N.H., 2009. Managing spatial and temporal variability in irrigated agriculture through adaptive control. Aust. J. MultiDisciplinary Eng. 7 (1), 79–90. https://doi.org/10.1080/14488388.2009.11464801. Su, C., Ma, J., 2012. Nonlinear predictive control using fuzzy hammerstein model and its application to CSTR process. AASRI Procedia 3, 8–13. https://doi.org/10.1016/j. aasri.2012.11.003. Sudarmaji, A., Sahirman, S., Saparso, Ramadhani, Y., 2019. Time based automatic system of drip and sprinkler irrigation for horticulture cultivation on coastal area. IOP Conference Series: Earth and Environmental Science, 250(1). https://doi.org/10. 1088/1755-1315/250/1/012074. Susilo, Adi Widyanto, Achmad, Widodo, Achmad, Hidayatno, Suwoko, S., 2014. Error analysis of ON-OFF and ANN controllers based on evapotranspiration. TELKOMNIKA Indonesian J. Electr. Eng. 12 (9), 6771–6779. https://doi.org/10.11591/telkomnika. v12i9.5090. Touati, F., Al-Hitmi, M., Benhmed, K., Tabish, R., 2013. A fuzzy logic based irrigation system enhanced with wireless data logging applied to the state of Qatar. Comput. Electron. Agric. 98, 233–241. https://doi.org/10.1016/j.compag.2013.08.018. Tropea, F., 2014. Precision agriculture: an opportunity for Eu farmers- potential support with the cap 2014–2020. Europian Union 56. https://doi.org/10.2861/74.58758. Tsang, S.W., Jim, C.Y., 2016. Applying artificial intelligence modeling to optimize green roof irrigation. Scence Direct, Energy Build. 127, 360–369. https://doi.org/10.1016/ j.enbuild.2016.06.005. Tseng, D., Wang, D., Chen, C., Miller, L., Song, W., Viers, J., … Goldberg, K., 2018. Towards automating precision irrigation : deep learning to infer local soil moisture conditions from synthetic aerial agricultural images. In: 2018 IEEE 14th International Conference on Automation Science and Engineering (CASE), pp. 284–291. Tzounis, A., Katsoulas, N., Bartzanas, T., Kittas, C., 2017. Internet of Things in agriculture, recent advances and future challenges. Elsevier –Biosyst. Eng. 164, 31–48. https:// doi.org/10.1016/j.biosystemseng.2017.09.007. Uddin, M.A., Mansour, A., Le Jeune, D., Aggoune, E.H.M., 2017. Agriculture internet of things: AG-IoT. In: 2017 27th International Telecommunication Networks and Applications Conference, ITNAC 2017, vol. 2017-Janua, pp. 1–6. https://doi.org/10. 1109/ATNAC.2017.8215399. Umair, S., Muhammad, R.U., 2015. Automation of irrigation system using ANN based controller. Int. J. Electr. Comput. Sci. IJECS-IJENS, vol:10 No:(January 2010). Vegetronix, 2016. VH400 Soil Moisture Sensor Probes. Retrieved August 14, 2019, from https://vegetronix.com/Products/VH400/. Viani, F., Bertolli, M., Salucci, M., Polo, A., 2017. Low-cost wireless monitoring and decision support for water saving in agriculture. IEEE Sens. J. 17 (13), 4299–4309. https://doi.org/10.1109/jsen.2017.2705043. Villarrubia, G., De Paz, J.F., De La Iglesia, D.H., Bajo, J., 2017. Combining multi-agent systems and wireless sensor networks for monitoring crop irrigation. Sensors (Switzerland) 17 (8). https://doi.org/10.3390/s17081775. Wahab, N.A., Balderud, J., Katebi, R., 2008. Data driven adaptive model predictive control with constraints. In: Emss 2008 20Th European Modeling and Simulation Symposium, pp. 231–236. Wang, D., Tan, D., Liu, L., 2018. Particle swarm optimization algorithm: an overview. Soft. Comput. 22 (2), 387–408. https://doi.org/10.1007/s00500-016-2474-6. Wang, L., Zhang, H., 2018. An adaptive fuzzy hierarchical control for maintaining solar greenhouse temperature. Comput. Electron. Agric. 155 (October), 251–256. https:// doi.org/10.1016/j.compag.2018.10.023. Wasson, T., Choudhury, T., Sharma, S., Kumar, P., 2017. Integration of Rfid and sensor in agriculture using Iot. In: International Conference On Smart Technology for Smart Nation, pp. 217–222. Wen, Y., Shang, S., 2019. Pre-constrained machine learning method for multi-year mapping of three major crops in a large irrigation district. Remote Sensing Article, MDPI. https://doi.org/10.3390/rs11030242. Wesonga, J.M., Wainaina, C., Francis, O., W., M.P., Home, P.G., 2014. Wick material and media for capillary wick based. Irrigation System in Kenya. Int. J. Sci. Res., 3(4), 613–617. Winkler, D.A., Wang, R., Blanchette, F., Carreira-Perpinan, M., Cerpa, A.E., 2016. MAGIC: Model-based actuation for ground irrigation control. In: 2016 15th ACM/IEEE International Conference on Information Processing in Sensor Networks (IPSN). IEEE, pp. 1–12. https://doi.org/10.1109/IPSN.2016.7460680. Wolfert, S., Ge, L., Verdouw, C., Bogaardt, M., 2017. Big data in smart farming – A review. Agric. Syst. 153, 69–80. https://doi.org/10.1016/j.agsy.2017.01.023. Wong, W.C., Chee, E., Li, J., Wang, X., 2018. Recurrent neural network-based model predictive control for continuous pharmaceutical manufacturing. https://doi.org/10. 3390/math6110242. Xingye, Zhu, Prince, Chikangaise, Weidong, Shi, Wen-Hua, Chen, Shouqi, Yuan, 2018. Review of intelligent sprinkler irrigation technologies for remote autonomous system. International journal of agricultural and biological engineering 11, 23–30. https:// doi.org/10.25165/j.ijabe.20181101.3557. Yakub, F., Mori, Y., 2013. Model predictive control for car vehicle dynamics system – comparative study. In: Third International Conference on Information Science and Technology Yangzhou, Jiangsu, China, https://doi.org/10.1109/ICIST.2013. 6747530. Yashaswini, L.S., Vani, H.U., Sinchana, H.N., Kumar, N., 2017. Smart automated irrigation system with disease prediction. In: 2017 IEEE International Conference on Power, Control, Signals and Instrumentation Engineering (ICPCSI), pp. 422–427. Yesil, E., Guzelkaya, M., Eksin, I., 2014. Fuzzy PID controllers : An overview. In: The Third Triennial ETAI International Conference on Applied Automatic Systems, Skopje, Macedonia, pp. 1–8. Yonts, C.D., 1994. Surface irrigation. In: Encycl Agric Food Biol Eng., pp. 979–981. Yubin, Z., 2018. The control strategy and verification for precise water-fertilizer irrigation system. Chinese Automation Congress (CAC) 2018, 4288–4292. https://doi.org/10. 1109/CAC.2018.8623710. Yubin, Z., Zhengying, W., Xinguo, Z., Yang, U., Linzhang, L., 2017. Control strategy for precision water-fertilizer irrigation system and its verification. Retrieved from. J. Drainage Irrigation Machinery Eng. 35 (12). http://zzs.ujs.edu.cn/pgjx/EN/ abstract/abstract2356.shtml#. Yusuke, S., 2018, June. Is Asia facing a coming water crisis? https://doi.org/http://www. iiasa.ac.at/web/home/resources/publications/options/Is_Asia_facing_a_coming_ water_crisis_.html. Zacepins, A., Stalidzans, E., Meitalovs, J., 2012. Application of information technologies in precision agriculture. In: Proceedings of the 13th International Conference on Precision Agriculture (ICPA 2012). Zamora-izquierdo, M.A., Martı, J.A., Skarmeta, A.F., 2018. Smart farming IoT platform based on edge and cloud computing. ScienceDirect –Biosyst. Eng. 7, 4–17. https:// doi.org/10.1016/j.biosystemseng.2018.10.014. Zazueta, F.S., Smajstrla, A.G., Clark, G.A., 2008. Irrigation system controllers. Agricultural and Biological Engineering Department, Institute of Food and Agriculture Science, University of Florida, SSAGE22, pp. 1–11. Zhang, N., Wang, M., Wang, N., 2002. Precision agriculture -a worldwide overview. Retrieved from. Comput. Electron. Agric. 522 (20150806), 475–487. http:// linkinghub.elsevier.com/retrieve/pii/S002216941401066X. Zhang, Xiaoping, Gu, Q., Bin, S., 2004. Water saving technology for paddy rice irrigation and its popularization in China. Irrigation Drain System 18 (4), 347–356. https://doi. org/10.1007/s10795-004-2750-y 50. Zhang, Xueyan, Zhang, J., Li, L., Zhang, Y., Yang, G., 2017. Monitoring citrus soil moisture and nutrients using an IoT based system. Sensors (Switzerland) 17 (3), 1–10. https://doi.org/10.3390/s17030447. Zhang, Y., Wei, Z., Lin, Q., Zhang, L., Xu, J., 2018. MBD of grey prediction fuzzy-PID irrigation control technology. Desalin. Water Treat. 110, 328–336. https://doi.org/ 10.5004/dwt.2018.22336. Zhao, J.G., J,H., W.Y., 2009. Study on precision water-saving irrigation automatic control system by plant physiology. In: 4th IEEE Conference on Industrial Electronics and Applications, pp. 1296–1300. https://doi.org/10.1109/ICIEA.2009.5138411 53. 22