DESIGN AND RESULTS OF AN AI-BASED FORECASTING OF AIR POLLUTANTS FOR SMART CITIES

For Bavaria, Germany, we developed the first region-wide data-driven landslide susceptibility map, training a neural network on over 11,000 landslide events using terrain, geological, and land cover data. The model shows strong predictive performance, with geology and soil properties as the most influential features. Validation against newly recorded landslides shows that inventory incompleteness and selection bias translate directly into susceptibility underestimation in poorly mapped regions.

In this paper, we provide a brief introduction of the paradigm shift from managing disasters to managing risks, followed by single-hazard to multi-risk assessment. We highlight four global strategies that address disaster risk reduction and call for action. Subsequently, we present a conceptual approach for multi-risk assessment which was designed to serve potential users like disaster risk managers, urban planners or operators of critical infrastructure to increase their capabilities.