Traditional irrigation systems for agricultural lands are expensive, time-consuming, and labor-intensive. Utilizing cutting-edge technology like machine learning, the internet of things, and wireless sensor networks, smart farming addresses current issues with agricultural sustainability while boosting the quantity and quality of crop production from the fields to fulfill the rising food demand. Soil moisture and temperature sensors are used to create a low-cost, real-time IoT-based automatic irrigation system. Two groups have been formed with the sensor information such as “require water” and “not require water” and saved on the server. The device intelligently determines whether the field needs water and automatically turns “ON” or “OFF” the motor. Machine learning based models such as k-nearest neighbor, support vector machines, decision tree, and naive bayes are applied to decide irrigation requirements. Performance metrics show that the KNN classifier performs better than the other two models. The suggested framework allows for better field monitoring and visualization.
TopIntroduction
Food needs have expanded due to the planet's rapidly increasing population of humans. Given the planet's finite resources, it is challenging to meet the world's food needs (Vootla et al., 2018). Technological innovations are applied in agriculture to boost productivity and overcome this problem. Precision agriculture (PA) uses IoT devices and near- and remote-sensing methods to keep track of crop conditions at various growing phases. PA entails collecting and processing a sizable volume of agricultural health data. Many factors, including water content and temperature, influence crops' health. With the help of PA, a farmer may accurately determine the conditions for a healthy crop and when, where, and in what quantity these conditions must exist. This necessitates gathering a considerable amount of data from various sources and areas of the farm, including soil nutrients, the existence of weeds and pests, plants' chlorophyll levels, and several environmental factors. To generate agronomic advice, all gathered data must be analyzed. For example, plants' chlorophyll content (amount of greenness) indicates the nutrients required depending on their development phase. These data are integrated with information about the soil characteristics where the crop will be grown, including climate prediction. The amount of a specific fertilizer that should be administered to that crop the following day is calculated using all the data that has been gathered. Farmers must receive agronomic advice properly and follow its suggestions to increase yields. WSN (wireless sensor network) consists of several nodes coupled to track and record the physical state of the environment, which is the primary driver of the PA. Figure 1 shows the various application of WSN-based IoT in agriculture monitoring.
Figure 1. Application of IoT-based WSN in agriculture monitoring
Every wireless node comprises a microcontroller, sensors, a radio transceiver, and additional circuitry that allows it to connect to a gateway and transmit data that the sensor has acquired (Kumar et al., 2022). Sensors gather data by measuring the physical parameters and sending it to the controller, who then sends it to a portable device or the cloud. The agriculture industry has a variety of needs, including those related to soil characteristics, crop varieties, climate, fertilizer classes, and water necessities. The requirements of crops vary based on the crops grown in the same area and the same plant grown on other lands with various climatic conditions. Sensors keep track of how these crop factors change over time. The size and expenditure of sensors have decreased due to the rapid development of WSN technologies, making it possible to use them in various fields, including agriculture. Sensors keep track of how these crop factors change over time. The size and expenditure of sensors have decreased due to the rapid development of WSN technologies, making it possible to use them in various fields, including agriculture.