Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networks

TL;DR

This paper introduces an adaptive recurrent graph neural network model that predicts deep ice layer thickness from snow accumulation data, aiding climate change studies by providing more accurate ice sheet analysis.

Contribution

The paper presents a novel adaptive recurrent graph convolutional network for predicting ice layer thickness, improving accuracy over previous models and incorporating temporal and geometric data.

Findings

Model outperforms previous non-temporal models

Achieves greater consistency in predictions

Effective in capturing ice layer variations

Abstract

As we deal with the effects of climate change and the increase of global atmospheric temperatures, the accurate tracking and prediction of ice layers within polar ice sheets grows in importance. Studying these ice layers reveals climate trends, how snowfall has changed over time, and the trajectory of future climate and precipitation. In this paper, we propose a machine learning model that uses adaptive, recurrent graph convolutional networks to, when given the amount of snow accumulation in recent years gathered through airborne radar data, predict historic snow accumulation by way of the thickness of deep ice layers. We found that our model performs better and with greater consistency than our previous model as well as equivalent non-temporal, non-geometric, and non-adaptive models.