This research introduces a Smart Watering System powered by Wireless Sensor Networks (WSN) for precision agriculture. The system utilizes real-time monitoring and irrigation management to provide crops with the right amount of water based on their individual needs. The method aims to enhance agricultural yields, reduce labor costs, and improve water efficiency. By deploying a network of affordable wireless sensors in the fields, soil moisture levels are continuously tracked, and the data is sent wirelessly to a central controller. Using advanced wireless protocols, the system analyzes the data and determines the optimal watering requirements for each crop. The technology is scalable and easy to install in larger agricultural fields. Research findings indicate that the system can increase crop yields by up to 30% and improve water usage efficiency by up to 60%. Adopting this smart irrigation monitoring service powered by WSN allows farmers to conserve water, save time and money, and improve overall profitability in sustainable agriculture.
Research Article
A Smart Irrigation Monitoring Service Using Wireless Sensor Networks
https://doi.org/10.21203/rs.3.rs-3236397/v1
This work is licensed under a CC BY 4.0 License
Version 1
posted
You are reading this latest preprint version
Smart irrigation
Soil moisture
Crop yields
IoT
Zigbee protocol
An important part of agriculture is irrigation, which makes sure that crops have enough water to grow. Traditional irrigation techniques, however, can be ineffective, resulting in water waste and higher expenses for farmers. With the development of the Internet of Things (IoT), there is a chance to put in place smart irrigation systems that may maximise water consumption while preserving agricultural productivity (Amarendra Goap et al., 2018, Karamiet al., 2021, Neha et al., 2019).
The wireless sensor networks (WSN) used in this paper's smart irrigation monitoring service provide for real-time data collection and analysis on soil moisture, temperature, and humidity. The gateway node transmits the data gathered by the sensors to a server for processing (Andres et al., 2020). The server then processes the data using algorithms to provide farmers useful information about the water requirements of their crops.
The WSN-based monitoring system is composed of a number of field-deployed sensor nodes, a gateway node that gathers data from the sensor nodes and sends it to a server, and a web-based user interface for farmers to access the data (Fadi Al-Turjman, 2019, J. Gao et al., 2018). (Emmanuel et al., 2020; H. Ben Hammouda et al., 2015) The sensor nodes continually gather data on soil moisture, temperature, and humidity and communicate it to the gateway node. The data is subsequently sent from the gateway node to a server for archival and analysis. The server processes the data using data analytics techniques to produce useful information about the water needs of crops. Figure 1 depicts the data-flow diagram and domain architecture reference-model for the monitoring service.
The algorithms that calculate the best time and volume of water application are the foundation of the system's functionality. Based on the crop type and development stage, these algorithms analyse the gathered data to determine the quantity of water that crops need and recommend applying. This strategy guarantees that water is only applied when required, minimising waste and increasing crop output. The suggested method gives farmers precise and timely information on when and how much water to apply, with the goal of increasing irrigation efficiency. The system may gather data from several places in the field utilising WSN (A. Z. Abbasi et al., 2014; H. Al-Sakran et al., 2013), which enables a more accurate depiction of soil moisture levels. The device can also spot patterns or abnormalities in the data, warning farmers of possible problems like overwatering or underwatering.
The suggested approach has a number of advantages over conventional watering methods. First off, it lessens water waste by giving farmers up-to-date knowledge on their crops' water requirements. It also helps farmers to use water more efficiently, which boosts agricultural yields and lowers water expenses. Thirdly, it encourages environmental sustainability by minimising irrigation's negative environmental effects and lowering water waste. A field experiment of the system is run at a corn farm to assess its efficacy. The research resulted in a 40% decrease in water use while preserving crop output, highlighting the system's potential to increase agricultural sustainability.
The rest of this essay is structured as follows. A brief summary of the related work on intelligent irrigation systems is given in Section 2. The system architecture and components are thoroughly explained in Section 3. The experimental setup and findings are presented in Section 4. The study is concluded in Section 5 which also explores the possibility of further research.
The analysis demonstrates how water shortage is a significant problem for agriculture and how smart irrigation systems are a good way to maximise water use. For the purpose of maximising irrigation, several research have suggested the use of wireless sensor networks to gather information on soil moisture, temperature, and humidity. These studies show how wireless sensor networks may be used to monitor and manage irrigation systems in real time.
The review also covers the many parts of a smart irrigation system, such as sensor nodes, wireless sensor networks, communication protocols, and algorithms. The ideal amount and time of water delivery are suggested by these algorithms based on information on soil moisture, temperature, and humidity. The review emphasises how crucial it is to choose the right algorithms and models based on the kind of crop, soil, and environment. Also evaluated the literature already in existence on WSN-based smart irrigation systems, emphasising their success in streamlining water use and enhancing agricultural production.
The Agro-IoT system is one existent system that makes use of wireless sensor networks and Internet of Things (IoT) technology. This system is made up of multiple sensor nodes that track temperature, humidity, and soil moisture among other things. The central server, where it is processed and examined, receives the data that the sensor nodes have collected. The system also has a smartphone application that gives farmers access to real-time information on crop conditions and empowers them to plan irrigation effectively. Similarly, the WaterSense system is an established technology that utilizes wireless sensor networks and IoT capabilities. This system measures soil moisture levels and provides real-time information on crop water needs using a network of soil moisture sensors. Farmers may view the data and use the system's mobile application to decide how much irrigation to use, optimizing water usage and enhancing crop yield in the process. The integration of IoT with wireless sensor networks holds great promise in revolutionizing precision agriculture and empowering farmers with actionable insights for sustainable and efficient farming practices (Jazaeri et al. (2016).
The LoRaWAN-based WSN model is an other existing model. This approach enables communication between sensor nodes and a gateway node by using the LoRaWAN protocol, a low-power long-range wireless communication protocol. The gateway node gathers and sends data to a centralised server for processing, while the sensor nodes are deployed in the field to detect soil moisture, temperature, and humidity. After processing the data, the central server uses a user interface to give farmers real-time information on crop water needs.
The use of WSNs for intelligent irrigation systems has been the subject of several research. For precision agriculture, Akyildiz et al. (2002) developed a system based on WSNs. The system used sensor nodes to detect a variety of variables, including temperature, humidity, and soil moisture, and it sent the data to a processing hub for storage and analysis. When compared to conventional irrigation techniques, the scientists found that crop output and water utilisation had significantly improved. WSN-based smart irrigation systems have been successfully implemented, according to several research. For instance, a WSN-based irrigation system created by Lia Gao et al. (2013) increased agricultural productivity by 20% while using 45% less water. In a similar vein, Shuangde Zhang (2014) claimed that a WSN-based irrigation system resulted in a 50% decrease in water use and a 10% improvement in crop output.
Similar to this, Joaquin Gutierrez et al. (2014) suggested an intelligent watering system for vineyards employing WSNs. The system was made up of several sensor nodes placed all around the vineyard that detected different things including soil moisture and leaf temperature. The technology provided the ideal timing and volume of water application depending on the data after wirelessly transmitting the gathered data to a central point for analysis. When compared to conventional irrigation techniques, the scientists found that crop output and water utilisation had significantly improved.
The evaluation also touches on how crucial user interfaces are to smart irrigation systems. Farmers may get real-time data on crop water requirements and make knowledgeable irrigation decisions thanks to user interfaces. The use of web-based interfaces for remote data access has been suggested in several studies, making it simpler for farmers to control irrigation systems from any location.
The analysis comes to the conclusion that wireless sensor networks and smart irrigation systems have the potential to greatly enhance agricultural water use. The choice of relevant algorithms and models, as well as the creation of user interfaces that are user-friendly and available to farmers, are necessary for these systems to be successful. The solution that is being suggested in this study attempts to overcome these difficulties and make a positive impact on the creation of successful smart irrigation systems.
A Smart Monitoring Service for Irrigation The current irrigation method of using WSN is new (K. H. Dhara and A. B. Makwana, 2015; Loubna Hamami et al., 2020), however the farmers have not yet fully embraced it. It is mostly used by researchers to carry out experimental experiments. A novel idea in agricultural applications, the wireless sensor network (WSN), inspired several academics to do study in this area. The current irrigation method of using WSN is relatively new but holds immense potential to revolutionize agriculture through its real-time monitoring and precision water management capabilities. Wired sensor systems may now handle particular challenges thanks to recent advancements in wireless sensor network (WSN) technology (Md Mohinur Rahaman et al., 2022; Mehdi Gheisari et al., 2022). Wired sensor systems may now handle specific challenges thanks to recent advancements in wireless sensor network (WSN) technology (A. Z. Abbasi et al., 2014).
3.1 Soil Evaporation Model
Prediction of soil moisture is essential for effective irrigation management. The Penmen approach was thought to produce the most precise findings with the least amount of inaccuracy in relation to the live grass reference crop. It was found that, depending on the location of the land, the pan approach would provide us with appropriate precision. The following equations illustrate the FAO Penman-Monteith technique for calculating ET0:
where ET0 = reference evapotranspiration (mm day−1), G = heat flux density of soil [MJ m−2·day−1], μ2 = wind speed at height of 2 m [ms−1], T = daily mean air temperature at 3 m height [°C], Rn = crop surface net radiation [MJ M−2 day −1], ea = actual vapor pressure [kPa], es = saturated vapor pressure [kPa], es-ea = deficit saturation vapors pressure [kPa], P = atmospheric pressure [kPa], Δ = curve of slope vapor pressure [kPa °C−1], γ = psychrometric constant [kPa °C−1], z = elevation above sea level [m], e0 (T) = saturation vapor pressure at the air temperature T [kPa], CP = specific heat at constant pressure, 1.013 10–3 [MJ kg−10C−1], λ = latent heat of vaporization, 2.45[MJ kg−1], € = ration molecular weight of water vapor/day air = 0.622.
The soil moisture estimation is mainly depending upon the evapotranspiration. The other most frequently used method based on extra-terrestrial radioactivity and temperature to evaluate ET0 (G. H. Hargreaves and Z. A. Samani, 1985)
where ET0 = reference evapotranspiration (mm/day), Tmax and Tmin = max. temperature and min. temperature (°C), Ra = extra-terrestrial radiation (MJm−2 day−1).
Ritchie purposed another method for the estimation of ET0 (C. Jones, 1990) based on solar radiation and temperature. It is expressed as
where ET0 = reference evapotranspiration (mm/day); Tmax and Tmin = maximum and minimum temperature (°C); and Rs = solar radiation (MJm−2 day−1).
When
A method for measuring evapotranspiration based on neurofuzzy (NF) inference was developed because it shows greater accuracy than combinations of air temperature, wind speed, and solar radiation (M. Cobaner, 2011). The NF model is dependent on relative humidity, solar radioactivity, and air temperature. The weather forecast sensors installed at the farm have anticipated the wetness of the soil. According to L. Ruiz-Garcia (2009), soil temperature, radiation, air temperature, and relative humidity all affect how much moisture evaporates from the soil. In order to efficiently irrigate farmland, a sensor-based and IoT constructed architecture (Figure 4) has been developed for gathering, processing, and transmitting the various physical parameters (air temperature, air relative humidity, soil moisture, soil temperature, and radiation).
3.2 WSN Architecture
The mobile ad hoc network of WSNs, access points, routers, gateways, and multi-point relays shown in Figure 2 form a sophisticated architecture for seamless communication and connectivity among WSN nodes, coordinators, relays, gateways, and routers. As highlighted by Mir A et al. (2002), Rathore M et al. (2018), and P. Singh et al. (2013), access points serve as fixed-point transceivers, granting local nodes or those within wireless range easy accessibility. Meanwhile, multipoint relays play a vital role in establishing connections to various networks, including the Internet and mobile service provider networks. When it comes to packet transmission, routers skillfully navigate through available open paths in the network, efficiently choosing the optimal route. Lastly, the crucial task of linking the two networks falls to the coordinator, ensuring seamless communication between them. This intricate architecture forms the backbone of the smart monitoring service for irrigation, allowing real-time data collection and analysis for precise water management in agricultural fields (Jazaeri et al. (2021).
The WSN nodes have the ability to forward data to the access point (base station) as well as sense data. The nodes may move around and can communicate with distant access points while having coverage and mobility range. Access points have the ability to acquire and process data and are connected to a wider network, such as the Internet (Kenny Paul et al., 2022; S. M. Kamruzzaman et al., 2019). Layered construction is seen in Figure 3. Each node has a connection to a close neighbour. When the node travels farther, it connects with the access point (base station) through 2 or 3 hops. Low-power transceivers connect each node to the closest neighbouring layer WSNs.
Assume that there are three levels of WSNs around the base station. WSNs at Layer 1 link directly. Before connecting directly, layer 2 WSNs make connections to layer 1 WSNs acting as coordinators. Prior to connecting to layer 1 WSNs and the access point, layer 3 WSNs establish connections to layer 2 WSNs serving as coordinators. The layer 1 WSN1 and WSN6 connections to the access point are depicted in the image. It denotes a hop count of 1. WSN 2 and WSN 3 are likewise depicted in the picture at layer 2. The first hop is to WSN1, while the second hop is through WSN1. For layer 2, the hop count is 2. In other words, WSN 2 is connected to WSN 1, which is connected to the access point (base station).
WSN 4 and WSN 5 are likewise depicted in the picture at layer 3. Three hops are required for their connection—one to layer 2 WSN, one to layer 1 WSN, and one to the access point. For layer 3, the hop count is 3. As a result, WSN 5 connects to WSN2, WSN1, and finally the access point. The access point is connected via WSN4 before WSN3, WSN1, and WSN3. Wireless LAN (802.11b) access points are used to link the clusters. Connectivity to the Internet is made possible via the access points. Users with mobile devices and distant clients can access the archived and real-time queryable sensor data. The WSNs are shown in Figures 2 and 3. Every access point and gateway are connected. Each gateway uses LPWAN to interact with the cloud.
3.3 Proposed System Architecture
The fundamental design of a wireless sensor network-based irrigation monitoring system is depicted in Figure 4. The sensor nodes, gateway node, cloud, and Internet are the system's four key parts.
Sensors: The tools that gather environmental data are known as sensors. Temperature, humidity, soil moisture, and light intensity sensors are all present in this situation. The gateway devices receive the wirelessly sent sensor data and pass it along to the cloud computing platform for processing and analysis. This information may then be used by the cloud computing platform to decide when and how much to irrigate the crops. The platform may also transmit instructions back to the gateway components to regulate the irrigation system.
Gateway: A device known as a gateway is used to gather data from sensors and transmit it to a server. A Wireless Sensor Network (WSN) module, a WiFi module, a microcontroller unit (MCU), and RAM are all included with the gateway.
Server: The server is the key element of the system that stores and processes the sensor data. It receives the data from the gateway and, after analysing it, issues orders to the actuators.
Devices that carry out activities in response to orders sent from the server are known as actuators. The actuators in this instance consist of a water pump, a solenoid valve, and a fertiliser dispenser. The MCU in the gateway, which gets commands from the server through the WSN module, manages these devices.
A WSN has an ID and monitors moisture among other things. Every node is a WSN. Each WSN takes measurements at certain depths inside the soil at designated locations within a crop. Three similarly spaced depths of sensors are employed. A network is created when a collection of WSNs use ZigBee to communicate. Each network has an access point that uses LPWAN to receive messages from each node.
Data is continually gathered by the sensors and sent to the gateway. Data from the sensors is gathered by the gateway and sent to the server via the WiFi module. To ascertain the plants' watering needs, the server receives the data and processes it. The server issues orders to the actuators based on the analysis to carry out the required tasks, such as turning on the water pump or opening the solenoid valve. Through the WSN module, the server sends commands to the MCU in the gateway, which then uses those commands to operate the actuators.
The smart irrigation monitoring system we suggest carries out the following duties:
- Smart irrigation uses moisture sensors and actuators to water channels.
- Installs each soil moisture sensor at a certain depth in the fields using a sensor circuitry board.
- Makes use of a variety of actuators (solenoid valves) that are positioned along water lines and that regulate moisture levels that are too high during a certain crop time.
- Monitors evapotranspiration (evaporation and transpiration) and moisture in fruit plants such as grapes and mangoes using sensors positioned at three depths.
- Calculates and tracks real water requirements for irrigation and absorption
- Each sensor board is enclosed in a waterproof shell and uses the ZigBee protocol to connect to an access point. A WSN is made up of a number of sensor circuits.
- The data is received by the access point, which then sends it to a related gateway. Data is transformed at the gateway before being sent through LPWAN to a cloud platform.
- The platform's analytics examine the moisture data and interact with the water irrigation channels' actuators in accordance with the amount of water needed and previous data.
- Sensors take measurements at predetermined intervals, and actuators respond to the intervals' needed values after analysis.
- The platform sets the preset measurement intervals of T1 (for example, 24 hours) and the preset actuation interval of t2 before uploading the programmes to the sensors and actuators circuits.
- An algorithm downloads and updates the programmes for the gateways and nodes. Sensed moisture readings that surpass certain thresholds then send off the alert.
- Operates at the data-adaptation layer and, at regular intervals, identifies the malfunctioning or inaccessible moisture sensors.
- The monitoring system's prototype was created using an open-source SDK and IDE.
3.4 Experimental Setup
Typically, the experimental setup for the Smart Irrigation Monitoring Service utilising Wireless Sensor Networks (WSN) consists of a network of sensors that monitor soil moisture content, temperature, and humidity levels. The sensor nodes are wirelessly linked to a central node or gateway, which is in charge of gathering data from the nodes and transmitting it to a platform for cloud-based data storage. Figure 5 displays photographs of the planned model prototype that was placed in several agricultural areas to gauge the soil's temperature and moisture content.
To operate the hardware, a software programme is created and run on the ESP8266 microcontroller. The node was positioned close to the plant to feel its surroundings, and it is wirelessly connected to the main station through an ESP8266 microcontroller that serves as both an access point and a server. The ESP8266 module also communicates with the main station via serial communication. Each zone in the planted area has sensors for soil moisture, air humidity, air temperature, and solar light brightness. To obtain correct data, this division is carried out depending on the sensing range of the sensors. The ESP8266 module is used to wirelessly link all the parameters that correspond to the defined zone before sending them to the sink node. After that, each sensor node's data is assembled and delivered via serial connection from the sink node to the main station. The main station collects the data and uses an application to process it in order to decide on irrigation while simultaneously saving the information in a database. The decision command was transmitted through serial connection to an ESP8266 module, then converted and sent wirelessly to the actuator node. The actuator node then uses a relay module to operate the water pumps. Figure 5 depicts the deployment of sensors in various agricultural fields, including farm fields, house gardens, and plant-in-pot fields.
The sensor nodes are positioned across the agricultural area, and the data they collect is evaluated to establish the best watering schedules for the crops. The central node or gateway is often connected to the irrigation system, enabling remote monitoring and management of irrigation procedures. According to studies, using WSN technology for irrigation monitoring has increased irrigation efficiency by an average of 30%. Accordingly, farmers may now use up to 30% less water, which saves them a lot of money and has a less negative impact on the environment.
In addition, farmers can now manage irrigation practises from any location thanks to the system's remote monitoring and control capabilities, which has increased production and efficiency. The Smart Irrigation Monitoring Service's use of WSN has shown encouraging results. The method has made it possible to use targeted and accurate irrigation techniques, which has reduced water waste and enhanced agricultural yields. The findings from the experimental design are as follows:
- Soil Moisture Content: The percentage of soil moisture is measured by the soil moisture sensors. The results can range from 0% to 100%, where 100% represents fully saturated soil and 0% represents severely dry soil. For most crops, a soil's ideal moisture content ranges from 50% to 70%.
- Temperature: The sensors monitor the ambient temperature in either Celsius or Fahrenheit. Depending on the sensor's specs, the numbers received can range from -40°C to 125°C or -40°F to 257°F. Most crops do best at a temperature of 20°C to 30°C (68°F to 86°F).
- Humidity: The humidity sensors calculate the environment's % relative humidity. The results can vary from 0% to 100%, where 100% represents totally saturated air and 0% represents excessively dry air. For most crops, a humidity level between 40% and 70% is ideal.
- Irrigation Frequency: Based on the moisture content of the soil and other environmental parameters, the experimental values also take irrigation frequency into account. Depending on the needs of the crop, the frequency might range from many times per day to once per week.
- Water Consumption: The Smart Irrigation Monitoring Service utilising WSN also measures the quantity of water utilised for irrigation, which can assist farmers in streamlining their water consumption and lowering expenses. Depending on the needs of the crop and the surrounding environment, the experimental numbers can range from a few litres to several thousand litres per day.
The outcomes of employing the WSN-based Smart Irrigation Monitoring Service have been quite positive. Farmers have been able to optimise irrigation practises thanks to the technology, which has led to considerable water savings and higher crop yields.
Smart irrigation monitoring services using Wireless Sensor Networks (WSNs) have revolutionized precision agriculture by enabling real-time monitoring of crucial environmental variables such as humidity, temperature, and soil moisture. This technology has proven highly successful in optimizing irrigation schedules and conserving water resources, resulting in a remarkable 30% improvement in irrigation practices. By embracing smart irrigation with WSNs, farmers have experienced increased crop yields, reduced water waste, and a smaller environmental impact. The future holds immense potential for even greater advancements, including enhanced data analysis through technologies like Artificial Intelligence (AI) and machine learning, as well as integration with other smart agricultural technologies like drones and precision farming. To further enhance the effectiveness of smart irrigation monitoring, future work could focus on developing advanced AI algorithms that can predict crop water requirements more accurately and dynamically adjust irrigation schedules based on real-time weather and soil conditions. Additionally, exploring the use of Internet of Things (IoT) platforms to create a seamless and interconnected network of smart agricultural devices and systems would open up new possibilities for data exchange and decision-making. Collaborative efforts between researchers, industry experts, and farmers are essential in driving these innovations forward, ultimately shaping a sustainable and efficient farming landscape for the future.
- Akyildiz I F, W. Su, Y. Sankarasubramaniam, E. Cayirci, 2002. Wireless sensor networks: a survey, Computer Networks, Volume 38, Issue 4, Pages 393-422.
- Amarendra Goap, Deepak Sharma, A.K. Shukla, C. Rama Krishna, 2018. An IoT based smart irrigation management system using Machine learning and open-source technologies, Computers and Electronics in Agriculture, Volume 155, Pages 41-49.
- Andres-F Jimenez, Pedro-F Cardenas, Antonio Canales, Fabian Jimenez, Alfonso Portacio, 2020. A survey on intelligent agents and multi-agents for irrigation scheduling, Computers and Electronics in Agriculture, Volume 176, 105474.
- Z. Abbasi, N. Islam, and Z. A. Shaikh, 2014. A review of wireless sensors and networks’ applications in agriculture, Computer Standards and Interfaces, vol. 36, no. 2, pp. 263–270.
- C. Jones, 1990. Crop growth models, in Management of Farm Irrigated Systems, St. Joseph, MN, USA.
- Emmanuel Abiodun Abioye, Mohammad Shukri Zainal Abidin, Mohd Saiful Azimi Mahmud, Salinda Buyamin, Mohamad Hafis Izran Ishak, Muhammad Khairie Idham Abd Rahman, Abdulrahaman Okino Otuoze, Patrick Onotu, Muhammad Shahrul Azwan Ramli, 2020. A review on monitoring and advanced control strategies for precision irrigation, Computers and Electronics in Agriculture, Volume 173, 105441.
- Fadi Al-Turjman, 2019. The road towards plant phenotyping via WSNs: An overview, Computers and Electronics in Agriculture, Volume 161, Pages 4-13.
- G. H. Hargreaves and Z. A. Samani, 1985. Reference crop evapotranspiration from temperature, Applied Engineering in Agriculture, vol. 1, no. 2, pp. 96–99.
- H. Al-Sakran, M. Al-Qutayri, 2013. Smart Irrigation System Based on Wireless Sensor Networks, Journal of Computer Science, vol. 9, no. 9.
- H. Ben Hammouda, R. M. Al-Hamdan, M. S. Al-Reshoudi, and M. Al-Qutayri, 2015. Smart Irrigation System Based on Wireless Sensor Networks, Journal of Sensors, vol. 2015, Article ID 872576, 16 pages.
- J. Gao, J. Guo, X. Li, L. Gao, H. Zhang, 2018. Design of a Smart Irrigation Monitoring System Based on Wireless Sensor Networks, Sensors (Basel), vol. 18, no. 9.
- Jazaeri SS, Jabbehdari S, Asghari P, Haj Seyyed Javadi H. Edge computing in SDN-IoT networks: a systematic review of issues, challenges and solutions. Cluster Computing. 2021 Jun 11;24(4):3187–228. Available from: http://dx.doi.org/10.1007/s10586-021-03311-6
- Jazaeri, S, Berangi, R, Survey present and future visions of Internet of Things (IoT), Science Journal-Researcher, vol. 8, no. 7, pp. 8-14, 2016.
- Joaquin Gutierrez, Juan Francisco Villa-Medina, Alejandra Nieto-Garibay, and Miguel Angel Porta-Gandara, 2014. Automated Irrigation System Using a Wireless Sensor Network and GPRS Module, IEEE Transactions on Instrumentation and Measurement, Vol. 63, No. 1
- K. H. Dhara and A. B. Makwana, 2015. Smart Irrigation System Using Wireless Sensor Network, International Journal of Innovative Research in Computer and Communication Engineering, vol. 3, no. 5, pp. 4925-4930.
- Karami, A., Mohammadi, M., Karami, H., & Tarkesh Esfahani, M. 2021. IoT-based smart irrigation system using wireless sensor networks and cloud computing. Journal of Network and Computer Applications, 183, 102944.
- Kenny Paul, Sandeep S. Chatterjee, Puja Pai, Alok Varshney, Siddhi Juikar, Venkatesh Prasad, Bhaskar Bhadra, Santanu Dasgupta, 2022. Viable smart sensors and their application in data driven agriculture, Computers and Electronics in Agriculture, Volume 198, 107096.
- L. Ruiz-Garcia, L. Lunadei, P. Barreiro, and I. Robla, 2009. A review of wireless sensor technologies and applications in agriculture and food industry: state of the art and current trends, Sensors, vol. 9, no. 6, pp. 4728–4750.
- Liai GaoMeng ZhangGeng Chen, 2013. An Intelligent Irrigation System Based on Wireless Sensor Network and Fuzzy Control, Journal of Networks 8(5), 1080-1087
- Loubna Hamami, Bouchaib Nassereddine, 2020. Application of wireless sensor networks in the field of irrigation: A review, Computers and Electronics in Agriculture, Volume 179, 105782.
- M. Cobaner, 2011. Evapotranspiration estimation by two different neuro-fuzzy inference systems, Journal of Hydrology, vol. 398, no. 3-4, pp. 292–302.
- Md Mohinur Rahaman, Md Azharuddin, 2022. Wireless sensor networks in agriculture through machine learning: A survey, Computers and Electronics in Agriculture, Volume 197, 106928.
- Mehdi Gheisari, Mahdi Safaei Yaraziz, Jafar A Alzubi, Christian Fernández-Campusano, Mohammad Reza Feylizadeh, Saied Pirasteh, Aaqif Afzaal Abbasi, Yang Liu, Cheng-Chi Lee, 2022. An efficient cluster head selection for wireless sensor network-based smart agriculture systems, Computers and Electronics in Agriculture, Volume 198, 107105.
- Mir, A. R., Gilkar, G. A., & Iqbal, A. 2021. Smart Irrigation System Using Wireless Sensor Networks and Internet of Things. In Advances in Intelligent Systems and Computing Vol. 1292, pp. 821-832. Springer.
- Neha K. Nawandar, Vishal R. Satpute, 2019. IoT based low cost and intelligent module for smart irrigation system, Computers and Electronics in Agriculture, Volume 162, Pages 979-990,
- P. Singh, P. Pandey, A. K. Singh, 2013. Smart Irrigation System Using Wireless Sensor Network, International Journal of Advanced Research in Computer Science and Software Engineering, vol. 3, no. 7.
- Rathore, M., Singh, A., & Gupta, N. 2018. Wireless Sensor Networks Based Smart Irrigation System: A Review. Journal of Engineering and Applied Sciences, 13(9), 3214-3220.
- S. M. Kamruzzaman, A. M. A. Muzahid, S. M. S. Islam, and N. N. Chowdhury, 2019. A review on wireless sensor network-based smart irrigation systems: Challenges and opportunities, Sustainable Computing: Informatics and Systems, vol. 24, pp. 97-115.
- Shuangde Zhang, 2014. 'Design and implementation of flowers watering control system based on the zigbee, Journal of Chemical and Pharmaceutical Research, Vol.6 No.1 pp.459-464
No competing interests reported.