The field of weather forecasting and disaster response is rapidly advancing, driven by innovations in machine learning, satellite imaging, and physics-informed modeling. Researchers are developing new frameworks for 3D cloud reconstruction, precipitation nowcasting, and flood depth mapping, which are improving the accuracy and reliability of weather forecasts and disaster response systems. These advancements have the potential to save lives, reduce economic losses, and mitigate the impacts of climate change. Noteworthy papers in this area include: The introduction of a new framework for global 3D cloud reconstruction from satellite observations, which can create instantaneous 3D cloud maps and accurately reconstruct the 3D structure of intense storms. The development of a machine learning system for detecting methane emissions, which has facilitated the verification of over 1,000 distinct methane leaks and represents a critical step towards a global AI-assisted methane leak detection system.