The evaluation and quantification of solids transport in Morocco often uses the Universal Soil Loss Model (USLE) and the revised version RUSLE, which presents a calibration difficulty. In this study, we apply the MUSLE model to predict solid transport, for the first time on a large river basin in the Kingdom, calibrated by two years of solid transport measurements on four main gauging stations at the entrance of the Sidi Mohamed Ben Abdellah dam. The application of the MUSLE on the basin demonstrated relatively small differences between the measured values and those expected for the calibrated version, these differences are, for the non-calibrated version, +5% and +102% for the years 2016/2017 and 2017/2018 respectively, and between −33% and +34% for the calibrated version. Besides, the measured and modeled volumes that do not exceed 1.78 × 106 m3/year remain well below the dam’s siltation rate of 9.49 × 106 m3/year, which means that only 18% of the dam’s sediment comes from upstream. This seems very low because it is calculated from only two years. The main hypothesis that we can formulate is that the sediments of the dam most probably comes from the erosion of its banks.
Sediment transport in basins disturbs the ecological systems of the water bodies and leads to reservoir siltation. Its evaluation is crucial for managing water resources. The practical application of the process-based model can confront some limitations noticed in the lower accuracy during the validation process due to the lack of reliable physical datasets. In this study, we attempt to apply machine-learning-based modeling (ML) to predict the suspended sediment load, using hydro-climatic data as input variables in the semi-arid Bouregreg basin, Morocco. To that end, data for the years 2016 to 2020 were used for the training process, and the validation was performed with 2021 data. The results showed that most ML models have good accuracy, with a Nash–Schiff efficiency (NSE) ranging from 0.47 to 0.80 during the validation phase, which indicates satisfactory performances in predicting the SSL. Furthermore, the models were ranked against their generalization ability (GA), which revealed that the developed models are good to excellent in terms of GA. Overall, the present study provides new insight into predicting the SSL in a semi-arid environment, such as the Bouregreg basin.