Recurrent Graph Convolutional Networks for Spatiotemporal Prediction of Snow Accumulation Using Airborne Radar
This work addresses the need for accurate snow accumulation predictions to monitor climate change impacts on Greenland, representing an incremental improvement in domain-specific modeling.
The paper tackles the problem of predicting annual snow accumulation using airborne radar data by proposing a recurrent graph convolutional network model, which outperforms non-geometric and non-temporal baselines with more consistent results.
The accurate prediction and estimation of annual snow accumulation has grown in importance as we deal with the effects of climate change and the increase of global atmospheric temperatures. Airborne radar sensors, such as the Snow Radar, are able to measure accumulation rate patterns at a large-scale and monitor the effects of ongoing climate change on Greenland's precipitation and run-off. The Snow Radar's use of an ultra-wide bandwidth enables a fine vertical resolution that helps in capturing internal ice layers. Given the amount of snow accumulation in previous years using the radar data, in this paper, we propose a machine learning model based on recurrent graph convolutional networks to predict the snow accumulation in recent consecutive years at a certain location. We found that the model performs better and with more consistency than equivalent nongeometric and nontemporal models.