Optimizing Cherry Tomato Crop Irrigation: A Robust Daily Schedule Incorporating Weather, Soil, and Irrigation Data through Cascaded-Output ANN

Water scarcity and the lack of fertile agricultural land are pressing issues in many countries, including Jordan, one of the world's driest nations. This study aims to develop an AI-driven irrigation system to optimize the daily irrigation schedule and water quantity for cherry tomato plants. Utilizing data from the Autonomous Greenhouse Challenge, this research focuses on creating a reliable multi-output regressor to determine the ideal time, duration, and amount of irrigation needed. The data, collected every five minutes over 166 days, encompasses external weather, greenhouse climate, soil, and root zone conditions. The study introduces a Cascaded Output Artificial Neural Network (Cascaded-Out ANN), which sequentially processes each predicted output as an input for the subsequent layer, outperforming traditional multi-output regression models. Evaluations using metrics such as normalized RMSE, MSE, and R
²
scores demonstrate significant improvements in prediction accuracy. The Cascaded-Out ANN model's superior performance is further validated through RMSE confidence interval comparisons, confirming its efficacy in managing water resources for cherry tomato cultivation. This approach not only addresses water conservation but also enhances crop yield and quality, thereby supporting Jordanian farmers in increasing profitability and reducing costs.