Neural networks have begun finding use in glaciology, becoming a critical new tool in the study of climate change and its effects on receding glaciers. A recent publication in The Cryosphere releases and evaluates a new neural network known as the Calving Front Machine (CALFIN), a program capable of automatically identifying the calving fronts of ocean-terminating glaciers from decades of satellite imagery. Programs such as CALFIN could make it possible to catalog and monitor the rates of glacier loss all around the world, even at sites that scientists haven’t been able to study manually.

Read the full story at Phys.org.