Hybrid Ensemble Learning for TWSA Prediction in Water-Stressed Regions: A Case Study from Casablanca–Settat Region, Morocco

Abstract

A hybrid machine learning framework has been developed in this study to estimate Terrestrial Water Storage Anomalies (TWSA) in Morocco’s Casablanca–Settat region, which faces serious groundwater stress due to rapid urbanization, intensive agriculture, and climate variability. In this study, TWSA is used as an integrated proxy for groundwater-related storage changes, while acknowledging that it also includes contributions from soil moisture and surface water. The approach combines satellite-based observations from the Gravity Recovery and Climate Experiment (GRACE) and GRACE Follow-On (GRACE-FO) with key environmental indicators such as rainfall, evapotranspiration, and land use data to track changes in groundwater availability with improved spatial detail. After preprocessing the data through feature selection, normalization, and outlier handling, the model applies six base learners, i.e., Huber regressor, automatic relevance determination regression, kernel ridge, long short-term memory, k-nearest neighbors, and gradient boosting. Their predictions are aggregated using a random forest meta-learner to improve accuracy and stability. The ensemble achieved strong results, with a root mean square error of 0.13, a mean absolute error of 0.108, and a determination coefficient of 0.97—far better than single-model baselines—based on a temporally independent train-test split. Spatial analysis highlighted clear patterns of groundwater depletion linked to land cover and usage. These results can guide targeted aquifer recharge efforts, drought response planning, and smarter irrigation management. The model also aligns with national goals under Morocco’s water sustainability initiatives and can be adapted for use in other regions with similar environmental challenges.