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.

This study presents an integrated approach for identifying groundwater potential zones in the Constantine region, northeastern Algeria, by combining the Analytical Hierarchical Process (AHP) with Geographic Information Systems (GIS). The methodology incorporates a multi-criteria analysis based on seven critical parameters: geomorphology, slope, drainage density, fault density, land use, lithology, and soil types. Each parameter was weighted using the AHP technique to quantify its relative influence on groundwater accumulation. Subsequently, areas were classified into zones of varying groundwater potential, ranging from ‘very poor’ to ‘excellent’. Field verification was conducted to validate the model’s results, demonstrating its effectiveness. Specifically, 80% of the 22 drilled wells in ‘good’ potential zones were found to exhibit reliable performance and sustainability. In contrast, wells located in areas classified as ‘poor’ potential zones were non-performing. These findings highlight the practical reliability of the AHP-GIS methodology in delineating groundwater-rich areas and its potential application in strategic water resource management. Moreover, the results reinforce the utility of this approach in addressing water scarcity challenges prevalent in arid and semi-arid regions. By accurately mapping groundwater concentration zones, this method offers a valuable tool for resource planners. The study also emphasizes its broader implications, including drought risk mitigation, particularly in regions where sustainable water management is critical for economic and environmental resilience.

In open-pit mining, optimizing blasting techniques is essential for enhancing both operational efficiency and achieving desired rock fragmentation, which directly impacts subsequent processes such as loading, hauling, and crushing. A well-designed drilling pattern and precise blasting plan are crucial for ensuring the effective distribution of block sizes. The technical and geometrical characterization of rock fragments plays a key role in improving blasting performance. This study focuses on enhancing fragmentation quality in the ENG Ain Touta limestone quarry, NE of Algeria, through the application of numerical modeling techniques. Current blasting outcomes were evaluated using WipFrag software to create particle size distribution curves, which revealed a significant proportion of oversized blocks, ranging between 21% and 25%. This highlights a critical need for modifications to the blasting plan. To address this, a revised plan was developed, incorporating an additional 20 kg of explosives per borehole. The predicted effects of this adjustment were modeled using the Kuz-Ram method, showing a 40% reduction in oversized blocks and a substantial improvement in rock fragmentation quality. The results underscore the effectiveness of integrating image analysis software and predictive modeling in refining blasting strategies. By mproving fragmentation, this approach can significantly boost mining operations’ efficiency, reduce the handling of oversized materials, and optimize the overall quarrying process. This study demonstrates the potential of numerical models and targeted adjustments in blasting plans to enhance productivity and cost-effectiveness in open-pit mining operations.

Interest in flood risk prevention has been growing steadily in recent years, with multi-criteria analysis frequently used to develop prevention plans. One of the common factors included in these analyses is annual rainfall. This study aims to assess the role of annual rainfall in identifying flood-prone areas, using Geographic Information Systems (GIS) to conduct the research in two stages. The first stage involved identifying at-risk areas using factors such as the Topographic Wetness Index, Height Above Nearest Drainage, proximity to watercourses, and drainage density. In the second stage, these results were integrated with annual rainfall maps, applying consistent weights across both stages. The findings suggest that while rainfall is a crucial factor in flood assessment, its inclusion in multi-criteria analysis may inadvertently distort results. This distortion occurs because rainfall distribution is influenced by topography, making it the only variable criterion among otherwise stable basin characteristics. As a result, rainfall data may shift the focus from lower basin areas, which are typically at greater risk but receive less rainfall, to higher basin areas with more rainfall. Furthermore, the study argues that annual rainfall is not a reliable basis for prevention planning, as it fails to accurately represent the characteristics of rain events – such as intensity, duration, and frequency – that are critical in flood studies. The research highlights the need for more appropriate criteria tailored to the specific study area and emphasizes the importance of developing new methods that focus on the impact of rainfall rather than just its distribution.