This study integrates deep learning and geospatial analysis to enhance soil loss estimation in the Moulouya Watershed, a region prone to erosion due to diverse topography and climatic conditions. Traditional models like the Universal Soil Loss Equation (USLE) and its revised version (RUSLE) often fall short in capturing complex environmental interactions, leading to inaccurate soil loss predictions. This research introduces a novel approach using Convolutional Neural Networks (CNNs) combined with Geographic Information Systems (GISs) to improve the precision and spatial resolution of soil loss risk assessments. High-resolution satellite imagery, soil maps, and climatic data were processed to extract critical factors, such as slope, land cover, and rainfall erosivity, which were then fed into the CNN model. The findings revealed that the CNN model outperformed traditional methods, achieving a low Root Mean Square Error (RMSE) of 2.3 and an R-squared value of 0.92, significantly surpassing the USLE and RUSLE models. The resulting high-resolution soil loss maps identified high-risk erosion areas, particularly in the central and eastern regions of the watershed, with soil loss rates exceeding 40 tons/ha/year. These findings demonstrate the superior predictive capabilities of deep learning, offering valuable insights for targeted soil conservation strategies and highlighting the potential of advanced computational techniques to revolutionize environmental modeling.

By combining geomatics techniques and remote sensing data, this paper gives a thorough investigation of the forest fires that occurred close to Berkane, Morocco, from July 16 to July 18, 2023. The goals of the study included spatiotemporally tracking the propagation of active forest fires during...

This study concerns a Saharan wetland of southern Morocco, the Imlili Sebkha, located south of the Dakhla city. Considered among the rare permanent saharan sebkhas, it is recharged by episodic surface water supplies from an endorheic hydrographic network and by the unconfined aquifer, which...

Located in the central northwest of Morocco, the Sidi Mohamed Ben Abdellah dam watershed is particularly exposed to soil degradation risk due to a combination of factors such as wide exposure, lithological heterogeneity, and varying climatic conditions. Therefore, the purpose of the conducted...

Managing school transportation involves major challenges in efficiency, maintenance, cost, and student safety due to outdated manual systems. This paper presents an integrated School Transport Information System (STIS), a comprehensive SaaS platform built to solve these problems. The STIS integrates IoT for real-time vehicle diagnostics (CAN bus), GPS for tracking, GIS for route optimization, and QR codes for student attendance verification. A core innovation is its predictive maintenance module, which uses CAN bus data to forecast vehicle failures, reducing costs and downtime. A case study in a Moroccan province, demonstrated significant improvements: a 17% reduction in fuel consumption, a 25% decrease in unscheduled maintenance, and a 99.8% accuracy rate in student tracking. These findings validate the STIS as a scalable and effective solution for modernizing school transport, contributing a novel, holistic framework to Intelligent Transportation Systems (ITS), Smart Mobility, and Smart Education.