Spatial Bias Correction of ERA5_Ag Reanalysis Precipitation Using Machine Learning Models in Semi-Arid Region of Morocco

Abstract

Accurate precipitation data are essential for effective water resource management. This study aimed to correct precipitation values from the ERA5_Ag reanalysis dataset using observational data from 20 meteorological stations located in the Tensift basin, Morocco. Five machine learning models were evaluated: MLP, XGBoost, CatBoost, LightGBM, and Random Forest. Model performance was assessed using RMSE, MAE, R2, and bias metrics, enabling the selection of the best−performing model to apply the correction. The results showed significant improvements in the accuracy of precipitation estimates, with R2 ranging between 0.80 and 0.90 in most stations. The best model was subsequently used to correct and generate raster maps of corrected precipitation over 42 years, providing a spatially detailed tool of great value for water resource management. This study is particularly important in semi−arid regions such as the Tensift basin, where water scarcity demands more accurate and informed decision−making.