It is undeniable reality the fact of increasing frequency and severity of natural hazards on a global scale. A trend that seems likely to continue in the future, as a consequence of increase in extreme weather events and climate change, constituting one of the most significant risks for the natural, technological and human environment. This session concerns the use of Geoinformatics technologies, specifically the use of Geographical Information Systems and Remote Sensing technologies as well as Artificial Intelligence methodologies, in order to understand the mechanisms of the manifestation and evolution of catastrophic phenomena, mostly related to floods, landslides, droughts and wildfires.
New data, remotely or in-situ acquired, advanced methodologies for their analysis and integration aimed at managing natural hazards are welcome in this session. Particular emphasis is placed on the application of explainable Artificial Intelligence methods, through techniques such as Shapley Additive explanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME), Permutation Importance, Partial Dependence Plot, Explainable Boosting Machine, etc., aimed at understanding the decision-making mechanism in problems related to the occurrence and evolution of natural hazards. Participants will be exposed to state-of-the-art technologies and practical applications to gain a full picture of the possibilities available for building applications of good disaster management practices. The intention of the session is to present successful cases that cover natural hazards in different environments and climate scenarios, leveraging cutting-edge technologies and contributing to the formation of a safer and more resilient society in the light of increased environmental challenges.