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.

Groundwater recharge is critical for sustainable water management in water-scarce regions like North Algeria, where climate change and urbanization exacerbate resource challenges, particularly in the populous Algiers watershed. This study evaluates groundwater recharge potential using the Analytical Hierarchy Process (AHP) and its fuzzy extension (FAHP), integrated with Geographic Information Systems (GIS), to map recharge zones. Employing open-source data, AHP and FAHP assessed factors such as lithology, slope, and rainfall, classifying the watershed into high, moderate, and low recharge potential zones. Results show AHP identifying 44.01% (528.95 km²) as high, 52.82% (634.93 km²) as moderate, and 3.18% (38.14 km²) as low potential, with FAHP yielding similar outcomes (44.35%, 52.47%, and 3.17%, respectively). Validation using borehole drawdown data confirmed a 73.3% accuracy and an AUC of 0.72, indicating moderate to good reliability. High recharge zones were concentrated in the central and northern areas with permeable soils and gentle slopes, moderate zones dominated the region, and low zones were minimal. This study concludes that both AHP and FAHP are effective for preliminary recharge assessments, with AHP favored for its simplicity, though FAHP excels with uncertain data. Limited high-resolution hydrogeological data highlight the need for further refinement, yet the approach offers a replicable framework for managing groundwater in arid, urbanized regions facing similar environmental pressures.

Steady uniform and non-uniform flows through an array of emergent and slightly submerged square cylinders are experimentally investigated with a specific focus on transverse seiche waves induced by vortex shedding. The study is first and foremost aimed at assessing the effect of streamwise flow non-uniformity on seiche waves. Its secondary purpose is to investigate the change in seiche magnitude, when initially emerged cylinders become slightly submerged. Thirdly and lastly, the effect of seiche waves on mean velocities and velocity fluctuations is quantified. The lock-in process between waves and vortex shedding is unaltered by flow non-uniformity and by a change from cylinder emergence to submergence. For non-uniform flows, this results in the co-existence of two differently oscillating transverse waves close to each other. Relative wave amplitude is found to be mainly influenced by relative submergence in the case of submerged cylinders, and by Froude number and oscillation mode in the case of emergent cylinders. Finally, seiche waves modify the streamwise mean velocity, when cylinders are emergent.