Abdeldjalil Belkendil

In the semi-arid Batna Belezma region of northeastern Algeria, groundwater is a vital resource for agriculture and drinking water. However, the climate leads to intense evaporation, which affects its quality. This study aims to identify the key hydrogeochemical processes that control groundwater composition in the Merouana Basin and to evaluate the predictive performance of machine learning (ML) models. A total of 30 groundwater samples were analyzed using multivariate statistical techniques, including Principal Component Analysis (PCA), and were modeled using PHREEQC to assess mineral saturation states. Additionally, ML-based regression models, including K-Nearest Neighbors (KNN), Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGB),were employed to predict groundwater chemistry. The results indicate that the dominant ion distribution follows the following trend: Ca²⁺ > Mg²⁺ > Na⁺ and HCO₃⁻ > SO₄²⁻ > Cl⁻. Alkaline earth metals (Ca²⁺ and Mg²⁺) constitute the major fraction of total dissolved cations, reflecting carbonate equilibrium and dolomite dissolution processes. In contrast, Na⁺ represents a smaller proportion of the cationic load; however, its hydro-agronomic significance is substantial due to its influence on sodium adsorption ratio (SAR) and soil permeability. The PHREEQC modeling showed that calcite and dolomite precipitation promote evaporite dissolution, while most samples remain undersaturated with respect to gypsum. The PCA results reveal high positive loadings of Mg²⁺, Cl⁻, SO₄²⁻, HCO₃⁻, and EC, suggesting that ion exchange and seawater mixing are the primary controlling processes, with carbonate weathering playing a secondary role. To enhance predictive assessment, several supervised machine learning models were tested. Among them, the Random Forest model achieved the highest predictive performance (R² = 0.96) with low RMSE and MAE values, confirming its robustness and reliability. The results indicate that silicate weathering and mineral dissolution are the primary mechanisms governing groundwater chemistry. The integration of multivariate statistics and machine learning provides a comprehensive understanding of groundwater evolution and offers a reliable predictive framework for sustainable water resource management in semi-arid environments. Geochemical model performance showed a high global accuracy (GPI = 0.91), confirming a strong agreement between observed and simulated chemical data. However, the HH value (0.81) indicates some discrepancies, particularly for specific ions or extreme conditions.

This research is considered the first of its kind in this sector of the river for more than three decades and aims to evaluate the diversity, abundance, richness and spatiotemporal variations of Cladocera within Samarra Impoundment water. The samples of these crustaceans were collected from three sites in the impoundment every two months between February 2023 and December 2024. We identified 19 taxa belonging to five Cladocerian families. The most abundant genera were Alona sp., Bosmina sp., Chydorus sp., Ceriodaphnia sp., Diaphanosoma sp., Daphnia sp. and Moina sp. The minimum and maximum densities were observed in spring and winter, respectively. The average values for evenness, richness and diversity indices were 0. 9, 0.82 and 0.88; 2.10, 1.98 and 1.71; 1.62, 1.55, and 1.43 bits/ind. at sites 1, 2 and 3, respectively. Seasonally, the lowest and highest values of richness and evenness indices were observed in summer and spring, respectively. The diversity index was observed in the summer and winter seasons. Furthermore, the analysis of the Jaccard similarity index indicated the highest value between the species at sites 1 and 3, reaching 39.98%.

Sustainable land-use planning and catastrophe risk reduction depend critically on landslide susceptibility mapping. The complex, nonlinear interconnections of environmental and human elements cause terrain instability and challenge conventional prediction methods. In this work, we offer a DeepLabV3+-based deep learning framework coupled with Geographic Information Systems (GIS) and Multi-Criteria Decision Making (MCDM) methods for spatial prediction of landslide risk, over the Dubai coastal and urban region (covering approximately 4,000 km²). The approach uses an annotated dataset for semantic segmentation and high-resolution satellite images from the Mohammed Bin Rashid Space Center (MBRSC). On Google Colab with GPU acceleration, the model is trained and verified and then further improved for computational efficiency on a Mac M1 machine. Our results show an Overall Accuracy (OA) of 91.3%, a Mean Intersection over Union (IoU) of 82.5%, and an F1-score of 88.4%, demonstrating strong classification performance throughout a range of land cover types. The Confusion Matrix analysis highlights strong segmentation accuracy for water bodies (94.2%) and structures (92.4%). Considerable misclassification between roadways and unpaved terrain results from spectral similarities. Furthermore, the perclass Dice Coefficient analysis confirms that the model can efficiently discriminate intricate topographical patterns. Especially in fast-expanding areas like Dubai, UAE, it provides a scalable solution for landslide susceptibility mapping, catastrophe risk management, and sustainable urban design. Future work will explore multi-sensor data fusion, real-time inference, and applying explainable artificial intelligence (XAI) techniques to enhance model interpretability in dynamic terrain settings.

This study focuses on assessing the hydrogeochemical characteristics and irrigation suitability of groundwater in the Ras El Aioun and Merouana districts, using an integrated approach that combines physicochemical analysis, machine learning (ML), and Geographic Information Systems (GISs). Thirty groundwater samples were collected in June 2023 and subjected to extensive analyses, including major ions (Ca²⁺, Mg²⁺, Na⁺, K⁺, HCO₃⁻, Cl⁻, SO₄²⁻), pH, TDS, alkalinity, and hardness. Hydrochemical facies analysis revealed that the Ca-HCO₃ type was dominant (93.33%), with some samples exceeding FAO limits, particularly for Na⁺, K⁺, SO₄²⁻, Cl⁻, Mg²⁺, and HCO₃⁻. Assessment of groundwater irrigation suitability revealed generally favorable conditions based on three key parameters: all samples (100%) were classified as excellent based on the Sodium Adsorption Ratio (SAR < 10), 70% showed good-to-permissible status by Sodium Percentage (Na% < 60), and 83.3% were within safe limits for Residual Sodium Carbonate (RSC < 1.25 meq/L). However, the Permeability Index (PI > 75%) categorized 96.7% of samples as unsuitable for long-term irrigation due to potential soil permeability reduction. Additionally, Total Hardness (TH < 75 mg/L) indicated predominantly soft water characteristics (90% of samples), particularly in the central study area, suggesting possible limitations for certain agricultural applications that require mineral-rich water. GIS-based spatial analysis showed that irrigation suitability was higher in the eastern and western regions than in the central zone. Advanced machine learning algorithms provide superior predictive capability for water quality parameters by effectively modeling complex, non-linear feature interactions that conventional statistical approaches frequently fail to capture. Three ML models—Support Vector Regression (SVR), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were used to predict the Irrigation Water Quality Index (IWQI). XGBoost outperformed the others (RMSE = 2.83, R² = 0.957), followed by RF (RMSE = 3.12, R² = 0.93) and SVR (RMSE = 3.45, R² = 0.92). Integrating ML and GIS improved groundwater quality assessment and provided a robust framework for sustainable irrigation management. These findings provide critical insights for optimizing agricultural water use in water-scarce regions.

Evaluating soil erosion is vital due to its significant environmental and societal impact. This research addresses the scarcity of measured data on soil erosion in North Africa by introducing a methodology using the Revised Universal Soil Loss Equation (RUSLE) and the sediment delivery ratio (SDR) to estimate soil erosion and sediment yield. Serving as an illustrative example and case study, this study contributes to the broader context of erosion research in subhumid regions. Key factors including rainfall erosivity (R-factor), soil erodibility (K-factor), slope length-steepness factor (LS-factor), and vegetation coverage factor (C-factor) were computed and mapped using GIS tools. Validation of the generated soil erosion map was performed using Receiver Operating Characteristic (ROC) analysis. Results showed mean values of rainfall erosivity at 148.02 MJ.mm.ha^-1.h^-1.yr^-1 and soil erodibility at 0.034 t.ha.h.ha⁻¹.Mj⁻¹.mm⁻¹. Steeper slopes exhibited higher LS-values exceeding 20, with a notable positive impact of vegetation coverage factor contributing approximately 16% to mitigating soil erosion. The mean annual soil loss was 6.81 t∙ha⁻¹∙yr⁻¹ with an SDR of about 45%, resulting in a sediment yield of 3.07 t∙ha⁻¹∙yr⁻¹. The Williams and Berndt model emerged as the most suitable for estimating SDR, with an AUC value of 0.736, indicating good accuracy. This study underscores the importance of using modeling frameworks to better understand erosion and sediment processes and guide sustainable conservation practices.

La vallée de la Saoura, espace géographique célèbre, se situe dans le Sud-Ouest d'Algérie. Il compte 14 oasis, exploitant des eaux souterraines, agencées en un système hydrogéologique, scindé par l'oued Saoura en deux compartiments : oriental interconnecté, dit actif (nappe phréatique du grand erg occidental, nappes des terrasses et inféroflux de l'oued Saoura), et occidental passif, non connecté (nappe de Hamada de Guir et celle du Cambro-Ordovicien). C'est ainsi qu'il s'agit de système vulnérable. Ces eaux se caractérisent d'une température de 16.2°C à 31.4°C. Le résidu sec « RS » est contrasté, variant de 280 à 7000 mg/l. Le pH varie de 7.1 à 7,85. Les chlorures sont comprises entre 33 et 2800 mg/l. De même, les sulfates s'échelonnent de 12 et 1800 mg/l. Les bicarbonates varient de 281 à 470 mg/l, et le calcium entre 34 et 568 mg/l. Le magnésium est faible, de 13 à 105 mg/l, et le Sodium atteint 2235 mg/l. Ces eaux se rangent en "chlorurée et sulfatée calcique et magnésienne", "chlorurée sodique et potassique ou sulfatée sodique" et "hyper chlorurées sodiques". Les nitrates (NO3--) s'échelonnent entre 0 mg/l à >160mg/l dont 22% d'échantillons dépasse la norme de 50mg/l. La conjugaison de facteurs naturels et actions anthropiques, affecte, aujourd'hui le chimisme de ce système, notamment inféroflux et les terrasses, dessinant un zonage : inféroflux hyper salé, terrasses 1, 2, 3 salées et nappe phréatique eau douce, qui ne cessent de se diffuser d'avantage et c'est ainsi que les oasis de la Saoura sont en péril.

In this study, we evaluate the soil erosion and solid transport in the oued Mekerra watershed in north-west Algeria. The study area is subject to a semi-arid climate characterized by irregular rainfall and showers, which are often accompanied by significant floods. These floods of large volumes transport large amounts of solid input to the Sarno dam, which is in the outlet of oued Mekerra. Therefore, the water storage capacity of this dam is gradually decreasing, and it might reach the volume of dead water. For this study, we utilized the hydrometric database provided by the National Agency of Water Resources (ANRH). The operating period was 24 years, from 1988 to 2012. This period was extended by classic regression to 65 years, which allowed extracting a series of annual maximum instantaneous flow rates (Q_IXA) and subsequently quantified the sediment yield during floods. The specific degradation mean created by the 11 floods was quite high, in the order of 20 t km² year⁻¹. The highest value of solid contribution was observed during the floods of October 2000 (250,000 t), and the value of liquid contribution was 7,151,608 m³. The extracted results from the analysis of the graphs of concentration as a function of the liquid flow (C = f′(Q_l)) showed four types of hysteresis curves: clockwise loop, counterclockwise loop, shape of eight, and straight line curve. Class II (clockwise loop) was the dominant class in the four events, namely the floods that occurred on 09/22/1992, 09/21/1998, 09/27/1999, and the 08/24/2002. From these results, the water resource sector managers could formulate various methods for protection from floods and against the risk of sedimentation in storage structures.