An Intelligent Irrigation Decision Support System for Optimizing Cotton Water Use

Irrigation plays a crucial role in increasing agricultural productivity. However, other factors, such as climate change, affect crop yields negatively. Furthermore, increasing competition for water by other sectors, such as industry and domestic use, increases the pressure on available water supplies. Under these circumstances, agricultural producers must be able to manage their available supplies efficiently to optimize irrigation water use. This research utilized the internet of things (IoT) and Deep Reinforcement Learning (DRL) to address the "when to irrigate and how much" questions through designing and developing a highly customized, intelligent, and robust end-to-end irrigation decision support system (DSS). Our approach uses multiple DRL algorithms that enable an intelligent agent to learn cotton irrigation needs in an interactive environment by trial and error using feedback from its past actions and experiences. Aquacrop is coupled with a DRL model to simulate and optimize crop yield for different actions taken by the agent. Our proposed software estimates the daily irrigation needs of a 7-acre crop field irrigated by a center pivot located at Clemson University's Edisto Research and Education Centre (REC), near Blackville, SC. This new system enables a closed-loop control scheme to adapt the DSS to local perturbations such as soil moisture and rainfall variabilities.