This study presented a semi-supervised method to map recent urban growth in Metropolitan Lima using satellite images and partial reference data. It reveals that the city expanded into several districts and in areas exposed to hazards such as landslides, earthquakes, and tsunamis. The approach helps detect early land occupations and supports safer land-use planning and better local decision-making.

This study shows how tsunamis interacting with coastal sediments intensify flooding risks in Tumaco Bay, Colombia. Using computer simulations, we found that including sediment transport raises water levels, flood depths, and affected areas, while proposed defenses reduce flooding but also reflect waves. These insights underscore the importance of incorporating sediment into tsunami models to design more robust protection and enhance coastal resilience.

We compiled an inventory of building condition (destroyed vs. survived) following the 2024 Noto Peninsula earthquake for the entire affected area, totaling over 140 000 structures. We discuss how we fused freely available data of different types and from different sources to generate the final dataset. We show that our method produces highly accurate results relative to those obtained by on-site surveys. These data can be used to train AI to quickly detect damaged structures in future disasters.