Desertification is a complex environmental phenomenon that affects many regions worldwide, including the Mediterranean area. Its effects, primarily resulting from climate variations and also influenced by human-induced changes, impact upon potential regional progress due to significant economic losses, social problems and ecological damage. The aim of this study was the identification of sensitive areas to desertification at watershed scale, in the Bradano River basin (Basilicata, southern Italy). The analysis was carried out by means of the model developed within the European project MEDALUS (MEditerranean Desertification And Land USe), which identifies prone areas to desertification through the Environmentally Sensitive Areas (ESAs) index. The model parameters were implemented and processed using a GIS-based approach to evaluate climate, soil, vegetation and management system quality factors, which represent the input for the ESAs assessment. The results indicate that 35% of the study area is highly sensitive to desertification, 49% of the study area has moderate sensitivity to desertification, 12% has low sensitivity and only 4% is non-sensitive to desertification.

Sinkhole susceptibility assessment was carried out in "Lesina Marina" evaporite karst area, located in the north-eastern part of the Apulia region (southern Italy), near the Adriatic coast. Land instability due to the widespread presence of sinkholes especially in a built-up area, constitutes a complex dynamic system, structured by a sets of interacting components, controlled by several natural and anthropogenic factors, forming an integrated whole, in which physical dynamic processes evolve. Heuristic method, multivariate statistical analysis and ANN procedure were performed in order to assess sinkhole susceptibility. In the study area, sinkhole phenomenon is strictly related to the structure and stratigraphy of the evaporite rocks, the groundwater regime conditioned by tide-induced surface water and groundwater interactions, and by the presence of the complex sea-channel-lagoon system. The analysis performed by different procedures explains the relationship between datasets and models capability to predict the behaviour of the phenomenon. The performances of prediction models have been evaluated using ROC curves. The results show that the multivariate statistical model produces a more reliable accuracy.