This study presents two machine learning models, namely, the light gradient boosting machine (LightGBM) and categorical boosting (CatBoost), for the first time for predicting flash flood susceptibility (FFS) in the Wadi System (Hurghada, Egypt). A flood inventory map with 445 flash flood sites was produced and randomly divided into two groups for training (70%) and testing (30%). Fourteen flood controlling factors were selected and evaluated for their relative importance in flood occurrence prediction. The performance of the two models was assessed using various indexes in comparison to the common random forest (RF) method. The results show areas under the receiver operating characteristic curves (AUROC) of above 97% for all models and that LightGBM outperforms other models in terms of classification metrics and processing time. The developed FFS maps demonstrate that highly populated areas are the most susceptible to flash floods. The present study proves that the employed algorithms (LightGBM and CatBoost) can be efficiently used for FFS mapping.

Flood-susceptibility mapping (FSM) is crucial for effective flood prediction and disaster prevention. Traditional methods of modeling flood vulnerability, such as the Analytical Hierarchy Process (AHP), require weights defined by experts, while machine-learning and deep-learning approaches require extensive datasets. Remote sensing is also limited by the availability of images and weather conditions. We propose a new hybrid strategy integrating deep learning with the HEC–HMS and HEC–RAS physical models to overcome these challenges. In this study, we introduce a Weighted Residual U-Net (W-Res-U-Net) model based on the target of the HEC–HMS and RAS physical simulation without disregarding ground truth points by using two loss functions simultaneously. The W-Res-U-Net was trained on eight sub-basins and tested on five others, demonstrating superior performance with a sensitivity of 71.16%, specificity of 91.14%, and area under the curve (AUC) of 92.95% when validated against physical simulations, as well as a sensitivity of 88.89%, specificity of 93.07%, and AUC of 95.87% when validated against ground truth points. Incorporating a “Sigmoid Focal Loss” function and a dual-loss function improved the realism and performance of the model, achieving higher sensitivity, specificity, and AUC than HEC–RAS alone. This hybrid approach significantly enhances the FSM model, especially with limited real-world data.

Medjerda is a key transboundary watershed in the Maghreb region, crossing from the Algerian mountains through northern Tunisia. Therefore, the analysis of the rainfall regime in this basin is of paramount importance for water resources management and regional economic development, notably concerning agriculture. This study examines the rainfall trends over the Medjerda watershed on multi-temporal scales (monthly, seasonally and annually) with a database of monthly rainfall observed in 60 stations evenly spread over the watershed. After filling gaps and homogenizing data, the Mann–Kendall test for trend detection was applied to rainfall series and the Sen’s slope method was adopted to estimate the trend’s magnitude, interpolated over the sub-catchments, to analyze the spatial distribution of rainfall changes within the watershed. Results showed the absence of significant trends at the annual scale for the entire catchment. However, rainfall redistribution was observed throughout the year, with a notable precipitation reduction during spring and increased winter precipitation, which could impact agriculture and ecosystem functioning. This modification of the rainfall regime implies an adaptation of the management of dams and reservoirs, with a reduced filling capacity during spring in anticipation of the summer dry season.

1. Rainfall data plays a pivotal role in hydrological modeling, influencing the accuracy and reliability of predictions essential for effective watershed management. While ground-based observations...