GRIT: Graph Transformer For Internal Ice Layer Thickness Prediction

TL;DR

GRIT is a novel graph transformer model that effectively predicts internal ice layer thickness from radar imagery by capturing complex spatiotemporal dependencies, outperforming baseline graph neural networks.

Contribution

Introduces GRIT, a graph transformer integrating geometric graph learning and attention mechanisms for improved ice layer thickness prediction.

Findings

GRIT achieves lower prediction errors than baseline GNNs.

Attention mechanism effectively captures temporal changes in ice layers.

Combines transformer and graph neural network strengths for robust modeling.

Abstract

Gaining a deeper understanding of the thickness and variability of internal ice layers in Radar imagery is essential in monitoring the snow accumulation, better evaluating ice dynamics processes, and minimizing uncertainties in climate models. Radar sensors, capable of penetrating ice, capture detailed radargram images of internal ice layers. In this work, we introduce GRIT, graph transformer for ice layer thickness. GRIT integrates an inductive geometric graph learning framework with an attention mechanism, designed to map the relationships between shallow and deeper ice layers. Compared to baseline graph neural networks, GRIT demonstrates consistently lower prediction errors. These results highlight the attention mechanism's effectiveness in capturing temporal changes across ice layers, while the graph transformer combines the strengths of transformers for learning long-range dependencies with graph neural networks for capturing spatial patterns, enabling robust modeling of complex spatiotemporal dynamics.