Advanced machine learning for predicting groundwater decline and drought in the Rabat–Salé–Kénitra region, Morocco DOI Creative Commons
Abdessamad Elmotawakkil, Nourddine Enneya

Journal of Hydroinformatics, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 24, 2024

ABSTRACT The Rabat–Salé–Kénitra region of Morocco faces critical groundwater challenges due to increasing demands from population growth, agricultural expansion, and the impacts prolonged droughts climate change. This study employs advanced machine learning models, including artificial neural networks (ANN), gradient boosting (GB), support vector regression (SVR), decision tree (DT), random forest (RF), predict storage variations. dataset encompasses hydrological, meteorological, geological factors. Among models evaluated, RF demonstrated superior performance, achieving a mean squared error (MSE) 484.800, root (RMSE) 22.018, absolute (MAE) 14.986, coefficient determination (R2) 0.981. Sensitivity analysis revealed significant insights into how different respond variations in key environmental factors such as evapotranspiration precipitation. Prophet was also integrated for its ability handle seasonality time-series data, further enhancing prediction reliability. findings emphasize urgent need integrate predictive management address depletion ensure sustainable water resources amid rising drought conditions. Policymakers can use these regulate extraction, promote water-saving technologies, enhance recharge efforts, ensuring sustainability vital future generations.

Language: Английский

Hydraulic modeling of Sebou tributaries for flood prevention in the el Gharb plain - Morocco DOI

Ikram Khadir,

Mohamed Saadi, Ikram El hamdouni

et al.

Data & Metadata, Journal Year: 2025, Volume and Issue: 4, P. 643 - 643

Published: Feb. 13, 2025

Flooding is one of the most unpredictable natural hazards. In Morocco, El Gharb plain affected. The Rharb basin receives between 500 and 600mm precipitation includes 30% Morocco's water resources. All factors that make a vulnerable area are: climatic factors, lithology, geomorphology, limited number outlets for drainage towards Atlantic Ocean. methodology adopted based on determination flood zones hydraulic modeling main tributaries Oued Sebou sanitation channels, in order to monitor evolution evaluate flow understand functioning hydrographic network overflow points. According hydrographs established by protection department, maximum at entrance city Kenitra was estimated 2,600 m3/s this level 1,600 m3/s, which explains overflows recorded left bank Sebou, dead arm Oued. results these studies as well analysis history floods show two major occur every 10 years reach upstream highway cover Merja-Fouarate such case flooding 2010.

Language: Английский

Citations

0
Advanced machine learning for predicting groundwater decline and drought in the Rabat–Salé–Kénitra region, Morocco DOI Creative Commons
Abdessamad Elmotawakkil, Nourddine Enneya

Journal of Hydroinformatics, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 24, 2024

ABSTRACT The Rabat–Salé–Kénitra region of Morocco faces critical groundwater challenges due to increasing demands from population growth, agricultural expansion, and the impacts prolonged droughts climate change. This study employs advanced machine learning models, including artificial neural networks (ANN), gradient boosting (GB), support vector regression (SVR), decision tree (DT), random forest (RF), predict storage variations. dataset encompasses hydrological, meteorological, geological factors. Among models evaluated, RF demonstrated superior performance, achieving a mean squared error (MSE) 484.800, root (RMSE) 22.018, absolute (MAE) 14.986, coefficient determination (R2) 0.981. Sensitivity analysis revealed significant insights into how different respond variations in key environmental factors such as evapotranspiration precipitation. Prophet was also integrated for its ability handle seasonality time-series data, further enhancing prediction reliability. findings emphasize urgent need integrate predictive management address depletion ensure sustainable water resources amid rising drought conditions. Policymakers can use these regulate extraction, promote water-saving technologies, enhance recharge efforts, ensuring sustainability vital future generations.

Language: Английский

Citations

1