Machine Learning and Explainable AI for Thai Basil Growth Prediction in Hydroponics

Hydroponic farming has emerged as a sustainable solution to modern agricultural challenges, offering enhanced resource efficiency, reduced environmental impacts, and optimized crop growth. Deep-Water Culture (DWC) is a hydroponic technique that provides continuous nutrients and oxygenated water to plants to enhance plant growth compared to traditional hydroponic systems. Thai basil is a medicinal plant chosen for this study. The growth of the plant is affected due to temperature, humidity, solar radiation, pH and total dissolved solids (TDS). This study emphasizes the impact of DWC on cultivation of Thai Basil over a month monitoring environmental and physiological parameters. The green area and plant height are recorded as growth parameters. The six machine learning (ML) models are employed to estimate the growth of Thai Basil. The best model is selected based on the ensemble VotingRegressor method. The predictions of the best model are explained with Shapley Additive Explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) Explainable AI models. Explainable AI provides clear and understandable justifications for predictions. Using Explainable AI, the proposed research predicts Thai Basil growth while providing reasoning for its prediction.