Understanding the influence of the hydrological regime changes, encompassing both the duration and spatial extent of floods, is explored, through this paper, in the context of the complex interactions of the geological, geomorphological and climate change conditions. Integrating these parameters and their combined influence becomes paramount for effective flood risk management and disaster prevention, as highlighted in the broader context of the study’s conclusions. Over the past decade, despite prevailing drought conditions in North African countries, the Mejerda Valley in Tunisia has experienced several major flood events. The valley geomorphological history is presented, within the landscape evolution. This study explores the use of Sentinel-1 radar data for detecting and managing floods in the region, with a particular emphasis on the vulnerability of the Lower Mejerda Valley. Sentinel-1 radar data, owing to their continuous monitoring capabilities independent of weather conditions, prove highly effective in tracking the temporal evolution of floods and accurately mapping the extent of affected areas. The methodology utilized in this study has proven to be highly effective in accurately identifying areas susceptible to flooding, both spatially and temporally. In generating classified flood images, water objects are highlighted by applying a specific formula. The study delves into significant flood events in the Mejerda Valley, including occurrences in 2015, 2017, 2019, and 2020, examining their profound impacts on various regions. For instance, the floods of 2015 recorded precipitation levels reaching up to 141 mm, contributing to the overall understanding of flood evolution in the region. In conclusion, the Mejerda Delta’s relief is primarily due to tectonism, influencing both Mio-Pliocene and Quaternary processes, shaping the current delta configuration. The Valley’s topography results from extensive geomorphological evolution, with the eastward shoreline advance leading to the formation of sebkhas and lagoons, indicators of high flood risk, supported by detailed flood event analysis. Moreover, The climate change and anthropic activity are non-negligible parameters influencing flood occurrence and intensity.

The Kerkennah archipelago in Tunisia is one of the most vulnerable areas where the influence of climate change is undeniable. Soil salinization has emerged as a major consequence of climate variation on this island. In this study, remote sensing techniques were implemented to develop a model for predicting soil salinity from satellite images. Machine learning algorithms, Sentinel-1 and Sentinel-2 data, and ground truth measurements were used to estimate soil salinity. Several algorithms were considered to achieve accurate findings. These algorithms are categorized as polynomial regression, random forest regression, exponential regression, and linear regression. The results demonstrate that exponential regression is the pre-eminent algorithm for estimating soil salinity with high predictive accuracy of R² = 0.75 and RMSE = 0.47 ds/m. However, spatiotemporal soil salinity maps reveal distinct and clear distribution patterns, highlighting salty areas (i.e., sebkhas) and agricultural parcels. Thus, through the model, we explore areas of moderately high salinity within agricultural lands that could be affected by irrigation practices. The present work demonstrates a reliable model for soil salinity monitoring in the Kerkennah archipelago and inspires more successful technologies such as remote sensing and machine learning to improve the estimation of soil salinity in climate-affected vulnerable areas.