Many communities rely on snowmelt from the mountains for their water supply. However, monitoring snow from space is challenging because clouds and other factors can obscure satellite observations. We present SnowGalileo, an AI model that combines data from multiple satellites to produce snow maps. The model can produce accurate maps even when clouds are present and high-resolution data are missing. This helps to improve our understanding of snow conditions and their impact on water resources.

As glaciers move, cracks called crevasses form, and knowing where they occur matters both for science and for safety. We created the first nationwide map of visible crevasses across all glaciers in Austria, using aerial images. We found that crevasses are most common on steep, fast-moving glaciers and rarer on large, gently sloping ones, with surface shape and flow influencing where they appear. This dataset is already being used to improve hiking maps, helping people plan safer mountain routes

PolarLakes is a new open dataset tracking meltwater lakes on Antarctic ice shelves every two weeks from 2015–2024. Using AI and satellite data from different sensors the monitoring of lakes is improved even during cloudy conditions. The record shows significant variations in ponding and lake formation, with a continent-wide peak occurring in 2020 within the observed period. To end, the PolarLakes dataset helps us to better understand the dynamics of surface hydrology in Antarctica.

Researchers from DLR and University Oxford created Shelf-Bench, a dataset to help AI track Antarctic ice shelf edges using satellite radar images (1992–2021). Testing five AI models revealed ice shelf delineation remains challenging and requires new model developments. This public benchmark will help researchers build better tools for monitoring ice front changes, detecting iceberg calving events, supporting operational logistics, and generating up-to-date continental maps.

Snow stored in winter snowpacks supplies water to rivers that millions of people depend on. As warming reduces snow amounts, we studied whether melting snow still matters for river flow. Using long records from river basins on four continents, and cause and effect analysis, we found that in some basins melting snow can become more important for river flow even when less snow is available.