Prediction of Annual Snow Accumulation Using a Recurrent Graph Convolutional Approach
This work addresses snow accumulation prediction for climate science, but it is incremental as it builds on previous temporal graph convolutional networks with minor modifications.
The researchers tackled predicting annual snow accumulation using a graph attention network-based model, achieving only a slight negative impact on performance despite using fewer input data points on a larger dataset.
The precise tracking and prediction of polar ice layers can unveil historic trends in snow accumulation. In recent years, airborne radar sensors, such as the Snow Radar, have been shown to be able to measure these internal ice layers over large areas with a fine vertical resolution. In our previous work, we found that temporal graph convolutional networks perform reasonably well in predicting future snow accumulation when given temporal graphs containing deep ice layer thickness. In this work, we experiment with a graph attention network-based model and used it to predict more annual snow accumulation data points with fewer input data points on a larger dataset. We found that these large changes only very slightly negatively impacted performance.