Floods and landslides are two distinct natural phenomena influenced by different conditioning factors, though some environmental triggers may overlap. This study applied eXtreme Gradient Boosting (XGBoost) to develop susceptibility maps for both phenomena, using a unified approach based on the same geospatial predictors. The approach integrated topographical, geological, and remote sensing datasets. Flood event data were collected from institutional sources using multi-source and high-resolution remotely sensed data. The landslide inventory was compiled based on historical records and geomorphological analysis. Key conditioning factors such as elevation, slope, lithology, and land cover were analyzed to identify areas prone to floods and landslides. The methodology was applied to the Basento River basin in Southern Italy, a region frequently impacted by both hazards, to assess its vulnerability and inform risk management strategies. While flood susceptibility is primarily associated with low-lying areas near river networks, landslides are more influenced by steep slopes and geological instability. The XGBoost model achieved a classification accuracy close to 1 for flood-prone areas and 0.92 for landslide-prone areas. Results showed that flood susceptibility was primarily associated with low Elevation and Relative Elevation, and high Drainage Density, whereas landslide susceptibility was more influenced by a broader and balanced set of factors, including Elevation, Drainage Density, Relative Elevation, Distance and Lithology. The resulting susceptibility maps offered critical approaches for land use planning, emergency management, and risk mitigation. Overall, the results demonstrated the effectiveness of XGBoost in multi-hazard assessments, offering a scalable and transferable approach for similar at-risk regions worldwide.

Climate change is globally recognised as a key driver of geomorphological transformation increasingly impacting natural systems, particularly through the intensification of erosion processes and modifications to landforms in vulnerable landscapes. This study focuses on landforms, processes, measurement approaches, quantitative methods, and a suitable sampling area from southern Italy, specifically in the middle valleys of Bradano and Basento rivers in Basilicata. The study is undertaken as part of one of the most significant research projects of the Italian National Recovery and Resilience Plan (NRRP), called “Technologies for Climate Change Adaptation and Quality of Life Improvement (Tech4You)”. This project aims to study – among many topics also related to cultural heritage protection and climate change adaptation – the specific framework of natural risks, with particular emphasis on the impact of global climate change in Mediterranean semi-arid areas and soil erosion rates in socio-economically “inner” areas. In this work, we focused on the multiproxy approach needed to discriminate the components of erosion processes at different temporal and spatial scales. Such a goal was approached through the construction of a complex relational database associated with thematic maps produced in a GIS environment. The framework enables the identification of priority areas affected by accelerated erosion and provides a methodological base for replicable climate-change monitoring, including in other Mediterranean semi-arid contexts. Further, it aims to offer a strategic tool for early-warning systems and long-term adaptation planning.