Soil erosion has been severely affecting soil and water resources in semi-arid areas like the Mediterranean. In Morocco, this natural process is accelerated by anthropogenic activities, such as unsustainable soil management, overgrazing, and deforestation. With a drainage area of 395,600 ha, the Bouregreg River Watershed extends from the Middle Atlas Range (Jebel Mtourzgane) to the Sidi Mohamed Ben Abdellah (SMBA) dam reservoir south-east of Rabat. Its contrasted eco-geomorphological landscapes make it susceptible to unprecedented soil erosion due to climate change. Resulting changes in erosive dynamics led to huge amounts of solid loads transported to the catchment outlet and, thus, jeopardised the SMBA dam lifespan due to siltation.
The research aims to quantify the average annual soil losses in this watershed using the Revised Universal Equation of Soil Losses (RUSLE) within a GIS environment. To highlight shifts in land use/land cover patterns and their effects on erosional severity, we have resorted to remote sensing through two Landsat 8 satellite images captured in 2004 and 2019. The C factor was combined with readily available local data regarding major erosion factors, e.g. rainfall aggressiveness ( R), soil erodibility ( K), topography ( LS), and conservation practices ( P). The helped to map the erosion hazard and determine erosion prone areas within the watershed where appropriate water and conservation measures are to be considered. Accordingly, from 2004 to 2019, average annual soil losses increased from 11.78 to 18.38 t∙ha ^–1∙y ^–1, as the watershed area affected by strong erosion (>30 t∙ha ^–1∙y ^–1) evolved from 13.57 to 39.39%.

The purpose of this study is to develop mathematical models based on artificial intelligence: Models based on the support vectors regression (SVR) for drought forecast in the Ansegmir watershed (Upper Moulouya, Morocco). This study focuses on the prediction of the temporal aspect of the two drought indices (standardized precipitation index – SPI and standardized precipitation-evapotranspiration index – SPEI) using six hydro-climatic variables relating to the period 1979–2013. The model SVR3-SPI: RBF, ε = 0.004, C = 20 and γ = 1.7 for the index SPI, and the model SVR3-SPEI: RBF ε = 0.004, C = 40 and γ = 0.167 for the SPEI index are significantly better in comparison to other models SVR1, SVR2 and SVR4. The SVR model for the SPI index gave a correlation coefficient of R = 0.92, MSE = 0.17 and MAE = 0.329 for the learning phase and R = 0.90, MSE = 0.18 and MAE = 0.313 for the testing phase. As for the SPEI index, the overlay is slightly poorer only in the case of the SPI index between the observed values and the predicted ones by the SVR model. It shows a very small gap between the observed and predicted values. The correlation coefficients R = 0.88 for the learning, R = 0.86 for testing remain higher and corresponding to a quadratic error average MSE = 0.21 and MAE = 0.351 for the learning and MSE = 0.21 and MAE = 0.350 for the testing phase. The prediction of drought by SVR model remain useful and would be extremely important for drought risk management.