The FORMATION project aims at fostering the implementation of new approaches for the description of geomorphological processes and representation of landforms, whose spatial distribution represents the most immediate tool to detect areas affected by geological risks. Despite the maturity of traditional cartographic… Leggi tutto approaches (mainly symbols-based), the operational readiness of geomorphological maps is quite low, as they are perceived as static tools, suffering from temporal and scale resolution. The FORMATION project aims to fill this gap, integrating emerging remote sensing techniques into the new Italian guidelines for the geomorphological mapping provided by ISPRA (Istituto Superiore per la Protezione e la Ricerca Ambientale, Italian Institute for the environmental protection and research) The main driver of the FORMATION project is the design of new paradigms for geomorphological mapping, where outcomes of traditional geomorphological survey and land degradation models, coupled with multi-band satellite analysis and multi-platform LiDAR and UAV data are convoyed within GIS (Geographic Information System) environment for the classification of landforms and the creation of a multi-scale, digital geomorphological map. The final aim of the FORMATION project is the production of a multi-scale digital cartography model, characterized by a full-coverage representation of landforms. Outputs of the FORMATION project, consisting of models with different hierarchical levels (from physiographic units to details on components of mapped landforms) will provide a complete and flexible representation of the complexity of the physical landscape evolution (including geology, landforms and active processes), finally suitable for every action and decision on the territory, from land planning to civil engineering applications. Databases, models, tools and methods will be presented and discussed with prototype implementations at pilot Italian cases in the Alps and Apennines, which share common pressing challenges on the environment, such as gravitational and running water-based processes causing several damages with a direct implication on human life and millions of euros spent in environmental remediation. Target basins have been selected to cover different geological, geomorphological and climatic settings and to demonstrate the effectiveness and replicability of the proposed methodology.

Slow deep-seated mass movements are widespread players of slope dynamics, with different mechanisms depending on involved materials, geomorphic settings and external forcing. Alpine settings, characterized by crystalline rocks and para/periglacial environments, are extensively affected by slow rock-slope deformations, deep-seated… Leggi tutto rockslides and periglacial features (e.g. rock glaciers). Mountains with fluvial-dominated topography in sedimentary rocks (i.e. Apennines) are typically affected by long-lived earthflows. These processes have different controls, show different spatio-temporal deformation patterns and rates, and threaten lives, activities, and infrastructures in different ways. Mitigating risks posed by deep-seated mass movements requires capabilities to: a) detect and classify different processes systematically and rapidly over wide areas; b) monitor their evolution towards possible destabilisation; c) predict interactions with elements at risk. Current regional scale analyses rely on geomorphological techniques supported by remote sensing to capture processes and their spatio-temporal evolution. These approaches are accurate but time consuming and difficult to update. Such gaps could be filled using artificial intelligence techniques, yet their applications to mass movements are still few, mostly limited to interpretation of optical images and missing robust process-oriented approaches. The MIRAGE project will provide methods and tools for the semi-automated detection, classification and kinematic characterization of deep-seated mass movements through the combination of multi-scale geomorphological data, spaceborne InSAR and deep learning techniques. The construction of libraries of expert-interpreted InSAR phase signal features, corresponding to different mass movements, will allow training and validating a Convolutional Neural Network (CNN).This will be tested with routinely generated SAR interferograms, to produce automated multi-temporal maps able to detect and classify mass movements, evaluate their displacement rates and temporal evolution. These results will provide policy making and engineering communities with new tools to quantify hazards related to specific processes, anticipate their critical evolution and support the prioritisation, planning and design of risk mitigation measures. MIRAGE addresses strategic research topics of the Italian “Piano Nazionale di Ripresa e Resilienza''(PNRR; Mission 4, Component 2, investments 1.3-1.4) as well as typical risk management missions of Civil Protection and regional authorities. Project goals will be achieved by exploiting the complementary expertise of three research units (UNIMIB, UNIBO, CNR), including the applied geomorphological and engineering characterization, monitoring and modelling of mass movements, InSAR processing and artificial intelligence. Activities will be deployed in six interrelated work packages and disseminated to scientific and technical communities.