Estimation of Reference Crop Evapotranspiration with Three Different Machine Learning Models and Limited Meteorological Variables

Precise reference crop evapotranspiration (ET0) estimation plays a key role in agricultural fields as it aids the proper operation and management of irrigation scheduling. However, reliable ET0 poses challenge when there is insufficient or incomplete long-term meteorological data at East Coast Economic Region (ECER), Malaysia, where economy highly dependent on production. This study evaluated performances different standalone machine learning (ML) models, namely, light gradient boosting (LGBM), decision forest regression (DFR), artificial neural network (ANN) models using four combinations variables. The incorporation solar radiation enhanced accuracy ML demonstrating energetic factors mechanism. Additionally, both ANN LGBM showed overall satisfactory performances, were thus recommended them alternate for estimation. was owing to their good capability capturing non-linearity interaction process among outcomes this will be advantageous farmers policymakers determining actual water demands maximize productivity data-scarce tropical regions.