Soil erosion by water is a major problem that the Northern part of Algeria witnesses nowadays; it reduces: the productivity of agricultural areas due to the loss of lands, and leads to the loss of storage capacity in reservoirs, the deterioration of water quality etc. The aim of this study is to evaluate the soil losses due to water erosion, and to identify the sectors which are potentially sensitive to water erosion in the Bouhamdane watershed, that is located in the northeastern part of Algeria. To this end, the Revised Universal Soil Loss Equation (RUSLE) was used. The application of this equation takes into account five parameters, namely the rainfall erosivity, topography, soil erodibility, vegetative cover and erosion control practices. The product of these parameters under GIS using the RUSLE mathematical equation has enabled evaluating an annual average erosion rate for the Bouhamdane watershed of 11.18 t·ha^-1·y^-1. Based on the estimates of soil loss in each grid cell, a soil erosion risk map with five risk classes was elaborated. The spatial distribution of risk classes was 16% very low, 41% low, 28% moderate, 12% high and 3% very high. Most areas showing high and very high erosion risk occurred in the lower Bouhamdane watershed around Hammam Debagh dam. These areas require adequate erosion control practices to be implemented on a priority basis in order to conserve soil resources and reduce siltation in the reservoir.

The objective of the study presented herein is to provide an accurate climate classification on the basis of aridity in northern Algeria. The aridity indices used in this study were the De Martonne index (I _DM), the Emberger index (I _Emberger), and the United Nations Environment Program index (I _UNEP), generally admitted in the Mediterranean region. The data required for their calculation were taken from 37 meteorological stations, and processed in a Geographical Information System (GIS) environment to generate climate classification maps according to each index. Generally, the three indices revealed the prevalence of semi-arid conditions in the study area. Similar climate classifications were identified with the I _UNEP and the I _DM, while the I _Emberger has identified larger arid extent. The obtained maps were then validated against the long-term soil moisture data extracted from a gridded global data set. The validation results indicated that the three indices gave very satisfactory results since they showed strong correlation coefficients with the soil moisture data. However, the I _Emberger slightly outperformed the I _UNEP and the I _DM with coefficients of determination (R ²) of 0.80, 0.78, and 0.77, respectively. The seasonal investigation of aridity allowed to identify regions and seasons in which irrigation is needed for the main crops cultivated in the study area.

Erosion can have a negative impact on the agricultural sustainability and grazing lands in the Mediterranean area, especially in northern Algeria. It is useful to map the spatial occurrence of erosion and identify susceptible erodible areas on large scale. The main objective of this research was to compare the performance of four machine learning techniques: Categorical boosting, Adaptive boosting, Convolutional Neural Network, and stacking ensemble models to predict the occurrence of erosion in the Macta basin, northwestern Algeria. Several climatologic, morphologic, hydrological, and geological factors based on multi-sources data were elaborated in GIS environment to determine the erosion factors in the studied area. The conditioning factors encompassing rainfall erosivity, slope, aspect, elevation, LULC, topographic wetness index, distance from river, distance from roads, clay mineral ratio, lithology, and geology were derived via the integration of topographic attributes and remote sensing data including Landsat 8 and Sentinel 2 within a GIS framework. The inventory map of soil erosion was created by integrating data from the global positioning system to locate erosion sites, conducting extensive field surveys, and analyzing satellite images obtained from Google Earth through visual interpretation. The dataset was divided randomly into two sets with 60% for training and calibrating and 40% for testing the models. Statistical metrics including sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (ROC) were used to assess the validity of the proposed models. The results revealed that machine learning and deep learning, as well stacking ensemble techniques, showed outstanding performance with accuracy over 98% with sensitivity 0.98 and specificity 0.98. Policy makers and local authorities can utilize the predicted erosion susceptibility maps to promote sustainable use of water and soil conservation and safeguard agricultural activities against potential damage.

This study aims to estimating annual soil erosion rate and its spatial distribution in the Bou Namoussa water-shed located in the North-East of Algeria by applying the revised universal soil loss equation (RUSLE) within a Geographical Information System environment (GIS). The application of the RUSLE model in different natural environments and on every scale takes into account five key factors namely: the rainfall erosivity, the soil erodibility, the steepness and length of slopes, the vegetation cover and the conservation support practices. Each of these factors was generated in GIS as a raster layer, their combination, resulted in the development of a soil loss map indicating an average erosion rate of 7.8 t·ha⁻¹·y⁻¹. The obtained soil loss map was classified into four erosion severity classes; low, moderate, high and very high severity representing respectively 40, 30.48, 22.59 and 6.89% of the total surface. The areas, showing moderate, high and very high erosion rates which represent more than half of the basin area were found generally located in regions having high erodibility soils, steep slopes and low vegetation cover. These areas should be considered as priorities in future erosion control programs in order to decrease the siltation rate in the Cheffia reservoir.

Soil erodibility is one of the most crucial factors used to estimate soil erosion by applying modeling techniques. Soil data from soil maps are commonly used to create maps of soil erodibility for soil conservation planning. This study analyzed the spatial variability of soil erodibility by using a digital elevation model (DTM) and surface soil sample data at the Rhirane catchment (Algeria). A total of 132 soil samples were collected of up to 20 cm in depth. The spatial distributions of the K-value and soil physical properties (permeability, organic matter, and texture) were used to elaborate ordinary Kriging interpolation maps. Results showed that mean values of soil organic matter content were statistically different between Chromic Cambisols (M = 3.4%) vs. Calcic Cambisols (M = 2.2%). The analysis of variance of the organic matter provided a tool for identifying significant differences when comparing means between the soil types. The soil granulometry is mainly composed of silt and fine sand. The soil erodibility showed values varying between 0.012 and 0.077 with an average of 0.034, which was greater in soils with calcic horizons. Statistical evaluation by using Pearson’s correlation revealed positive correlations between erodibility and silt (0.63%), and negative correlations with sand (−0.16%), clay (−0.56%), organic matter (−0.32%), permeability (−0.41%), soil structure (−0.40%), and the soil stability index (−0.26%). The variability analysis of the K-factor showed moderate spatial dependency with the soil erodibility map indicating moderate to highly erodible risk in cropland and sparse grassland land uses. Overall, the study provides scientific support for soil conservation management and appropriate agricultural food practices for food supply.