Learning Snow Layer Thickness Through Physics Defined Labels

Increasing global temperatures are adversely affecting the polar ice sheets and contributing to sea level rise. The situation requires constant monitoring and analysis of the change in thickness of snow layers accumulated on top of ice sheets. The monitoring can be performed through radar sensors, but current methods aren't efficient enough to process the radar images since they are noisy, and lack quality annotations, which are required by state-of-the-art deep learning algorithms. In this work, we show that first learning the thickness of snow layers simulated through a physical model helps in building robust deep learning networks. Specifically we show that transfer learning from a network trained with physics-defined labels improves snow layer thickness estimates by 6-29% on the test set.