Multi-branch Spatio-Temporal Graph Neural Network For Efficient Ice Layer Thickness Prediction

TL;DR

This paper introduces a multi-branch spatio-temporal graph neural network that improves ice layer thickness prediction accuracy and efficiency by focusing on geometric deep learning and specialized branches for different tasks.

Contribution

The paper presents a novel multi-branch spatio-temporal graph neural network using GraphSAGE and temporal convolution, enhancing prediction performance over existing methods.

Findings

Outperforms existing fused spatio-temporal GNNs in accuracy.

Achieves higher efficiency in ice layer thickness prediction.

Effectively captures spatio-temporal patterns in ice data.

Abstract

Understanding spatio-temporal patterns in polar ice layers is essential for tracking changes in ice sheet balance and assessing ice dynamics. While convolutional neural networks are widely used in learning ice layer patterns from raw echogram images captured by airborne snow radar sensors, noise in the echogram images prevents researchers from getting high-quality results. Instead, we focus on geometric deep learning using graph neural networks, aiming to build a spatio-temporal graph neural network that learns from thickness information of the top ice layers and predicts for deeper layers. In this paper, we developed a novel multi-branch spatio-temporal graph neural network that used the GraphSAGE framework for spatio features learning and a temporal convolution operation to capture temporal changes, enabling different branches of the network to be more specialized and focusing on a single learning task. We found that our proposed multi-branch network can consistently outperform the current fused spatio-temporal graph neural network in both accuracy and efficiency.