Soil organic carbon (SOC) is an essential component, which soil quality depends on. Thus, understanding the spatial distribution and controlling factors of SOC is paramount to achieving sustainable soil management. In this study, SOC prediction for the Ourika watershed in Morocco was done using four machine learning (ML) algorithms: Cubist, random forest (RF), support vector machine (SVM), and gradient boosting machine (GBM). A total of 420 soil samples were collected at three different depths (0–10 cm, 10–20 cm, and 20–30 cm) from which SOC concentration and bulk density (BD) were measured, and consequently SOC stock (SOCS) was determined. Modeling data included 88 variables incorporating environmental covariates, including soil properties, climate, topography, and remote sensing variables used as predictors. The results showed that RF (R² = 0.79, RMSE = 1.2%) and Cubist (R² = 0.77, RMSE = 1.2%) were the most accurate models for predicting SOC, while none of the models were satisfactory in predicting BD across the watershed. As with SOC, Cubist (R² = 0.86, RMSE = 11.62 t/ha) and RF (R² = 0.79, RMSE = 13.26 t/ha) exhibited the highest predictive power for SOCS. Land use/land cover (LU/LC) was the most critical factor in predicting SOC and SOCS, followed by soil properties and bioclimatic variables. Both combinations of bioclimatic–topographic variables and soil properties–remote sensing variables were shown to improve prediction performance. Our findings show that ML algorithms can be a viable tool for spatial modeling of SOC in mountainous Mediterranean regions, such as the study area.

Terraced farming play several roles, from improving ecosystem services to enhancing associated population livelihoods. In this study, we were interested in evaluating the roles of mountain terraces in controlling floods and erosion risks, in particular in the Ourika watershed, located in the High Atlas mountains of Morocco. Rainfall simulation tests were conducted to measure infiltration, runoff and initial abstraction, while the Cesium-137 isotope technique was used to quantify soil loss. The results highlighted high infiltration for dense forests (78.00 ± 2.65 mm/h) and low for rangelands (27.12 ± 2.82 mm/h). For terraces, infiltration was found to be about 70.36 ± 0.56 mm/h, confirming the role of terraces in promoting infiltration. The runoff coefficient obtained was lowest for dense forests, followed by cultivated terraces, and highest for rangelands (62.71 ± 3.51). Thus, outside dense forests, infiltration and runoff were significantly very high and low, respectively, for agricultural terraces compared to other land use. The assessment of soil erosion rates showed a significant soil loss for rangelands compared to the agricultural terraces, further underlining the role of terraces in soil conservation. Terraces in the Ourika watershed, by increasing water infiltration, reduce the rate of surface runoff, and consequently, flood risks and soil degradation.

Several studies on the assessment of soil organic carbon (SOC) stocks have been carried out at the global level. However, reliable information on SOC stocks is not readily available at the regional level. In addition, very few studies have assessed the factors responsible for the variation of SOC...