Internet of Things and Artificial Intelligence for Sustainable Agriculture: A Use Case in Citrus Orchards

Abstract

With climate changes, the agricultural sector will soon face significant challenges due to increasing water scarcity, extreme weather conditions, and shrinking arable land. Accurate estimations of crop water requirements are thus essential to improve water usage in agriculture. This paper provides a successful application of Internet of Things (IoT) and Artificial Intelligence (AI) technologies for developing a Smart and Sustainable Agriculture. In particular, the paper presents an example of an IoT system to monitor and predict soil water contents, actual evapotranspiration and other environmental variables, with the objective to use AI for precise irrigation scheduling in Mediterranean tree crops. The data collected during the monitoring period is used for training Machine Learning (ML) models and predict daily actual evapotranspiration (ETa) in a citrus orchard with a regulated deficit irrigation (RDI) strategy, using different feature combinations. Results show that the accuracy of the proposed ML models remains acceptable even when the number of input features is reduced from 10 to 4, making the cost of such IoT systems more affordable in sustainable.