Assessing Soil Water Content of Regenerative Cotton Crop with Extreme Gradient Boosting from Agrometeorological and Satellite Data

Sustainable irrigation in water-limited regions requires timely, field-scale estimates of soil water content (SWC). Yet, field-scale SWC studies leveraging near-daily satellite imagery of regenerative systems—particularly cotton under Mediterranean conditions—are lacking, and explainable integrations of Planet SuperDove with agrometeorological inputs remain underexplored. In this study, we evaluated a machine learning framework that integrates near-daily multispectral features from Planet SuperDove with agrometeorological variables to estimate the daily SWC of regenerative cotton under Mediterranean conditions across two seasons (2023–2024). Six regression models were compared; extreme gradient boosting achieved the highest accuracy (R2 = 0.73 ± 0.08; RMSE = 4.60 mm ± 0.81; nRMSE = 0.035 ± 0.01), with limited bias and stable performance across the years and moisture conditions. The model interpretability via SHAP indicated that agrometeorological drivers contributed over half of the predictive power, while the NDVI and NIR provided the most informative satellite inputs, followed by the NDRE and PSRI. The results show that combining high-frequency satellite data with meteorological inputs can deliver accurate and interpretable SWC estimates at the homogeneous plot level, supporting irrigation optimization of regenerative systems. This approach is practical, transferable, and suited for operational decision-making where frequent, high-resolution observations are available.