IoT-Driven Model for Weather and Soil Conditions Based on Precision Irrigation Using Machine Learning

Abstract

To feed a growing population, sustainable agriculture practices are needed particularly for irrigation. Irrigation makes use of about 85% of the world’s freshwater resources. Thus, for efficient utilization of water in irrigation, conventional irrigation practices need to either be modified or be replaced with advanced and intelligent systems deploying Internet of Things, wireless sensor networks, and machine learning. This article proposes intelligent system for precision irrigation for monitoring and scheduling using Internet of Things, long range, low-power (LoRa)-based wireless sensor network, and machine learning. The proposed system makes use of soil and weather conditions for predicting the crop’s water requirement. The use of machine learning algorithms provides the proposed system capability of the prediction of irrigation need. Dataset of soil and weather conditions captured using sensors is used with six different machine learning algorithms, and the best one giving highest efficiency in predicting the irrigation scheduling is selected. Linear discriminant analysis algorithm gives the best efficiency of 91.25% with prediction efficiency.