Early Forecasting Hydrological and Agricultural Droughts in the Bouregreg Basin Using a Machine Learning Approach

Water supply for drinking and agricultural purposes in semi-arid regions is confronted with severe drought risks, which impact socioeconomic development. However, early forecasting of indices crucial water resource management to implement mitigation measures against its consequences. In this study, we attempt develop an integrated approach forecast the hydrological a zone ensure sustainable agropastoral activities at watershed scale reservoir scale. To that end, used machine learning algorithms annual SPEI embedded it into by implementing correlation between reservoir’s inflow SPEI. The results showed starting from December can so NSE ranges 0.62 0.99 during validation process. proposed allows decision makers not only manage order pastoral “sustainability scale” but also