Neural Network Algorithms for Estimating Snow Depth and Scattering Mean-Free-Path from ICESat-2 Measurements of Multiple Scattering Inside Snow

Lidar measurements of green laser light traveling inside snow can be modeled using Monte Carlo simulations. These simulations generate databases that link snow properties (such as depth and scattering mean free path) with lidar backscatter vertical profile measurements. In this study, such simulated data is used to train neural networks that can be applied to ICESat-2 lidar measurements. The networks are trained with simulated backscatter profiles as inputs and snow properties as outputs. Our results demonstrate that machine learning methods can accurately retrieve snow properties from lidar measurements, even when using only the near-surface portion of the snow backscatter signal.