GRIT-LP: Graph Transformer with Long-Range Skip Connection and Partitioned Spatial Graphs for Accurate Ice Layer Thickness Prediction
Not on the map. Why?
Abstract (arXiv)
Graph transformers have demonstrated remarkable capability on complex spatio-temporal tasks, yet their depth is often limited by oversmoothing and weak long-range dependency modeling. To address these challenges, we introduce GRIT-LP, a graph transformer explicitly designed for polar ice-layer thickness estimation from polar radar imagery. Accurately estimating ice layer thickness is critical for understanding snow accumulation, reconstructing past climate patterns and reducing uncertainties in projections of future ice sheet evolution and sea level rise. GRIT-LP combines an inductive geometric graph learning framework with self-attention mechanism, and introduces two major innovations that jointly address challenges in modeling the spatio-temporal patterns of ice layers: a partitioned spatial graph construction strategy that forms overlapping, fully connected local neighborhoods to preserve spatial coherence and suppress noise from irrelevant long-range links, and a long-range skip connection mechanism within the transformer that improves information flow and mitigates oversmoothing in deeper attention layers. We conducted extensive experiments, demonstrating that GRIT-LP outperforms current state-of-the-art methods with a 24.92% improvement in root mean squared error. These results highlight the effectiveness of graph transformers in modeling spatiotemporal patterns by capturing both localized structural features and long-range dependencies across internal ice layers, and demonstrate their potential to advance data-driven understanding of cryospheric processes.
Key facts. Cited by 1 paper in the map (data through 14 Oct 2026). Builds on 21 of its 39 references that are in the map. First posted on arXiv 24 Nov 2025.
Builds on
21 of 39 references.
References · 21
- 2017Attention Is All You Needcited by 60,361
- 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,713
- 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,361
- 2016Densely Connected Convolutional Networkscited by 6,720
- 2017Inductive Representation Learning on Large Graphscited by 6,320
- 2018Graph Neural Networks: A Review of Methods and Applicationscited by 1,576
- 2019Measuring and Relieving the Over-smoothing Problem for Graph Neural Networks from the Topological Viewcited by 545
- 2019EvolveGCN: Evolving Graph Convolutional Networks for Dynamic Graphscited by 447
- 2021Do Transformers Really Perform Bad for Graph Representation?cited by 320
- 2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Predictioncited by 218
- 2021GraphiT: Encoding Graph Structure in Transformerscited by 147
- 2021Gophormer: Ego-Graph Transformer for Node Classificationcited by 63
9 more
- 2020Deep Ice Layer Tracking and Thickness Estimation using Fully Convolutional Networkscited by 15
- 2023Recurrent Graph Convolutional Networks for Spatiotemporal Prediction of Snow Accumulation Using Airborne Radarcited by 9
- 2023Prediction of Annual Snow Accumulation Using a Recurrent Graph Convolutional Approachcited by 8
- 2023Prediction of Deep Ice Layer Thickness Using Adaptive Recurrent Graph Neural Networkscited by 8
- 2024Learning Spatio-Temporal Patterns of Polar Ice Layers With Physics-Informed Graph Neural Networkcited by 5
- 2024Multi-branch Spatio-Temporal Graph Neural Network For Efficient Ice Layer Thickness Predictioncited by 5
- 2025ST-GRIT: Spatio-Temporal Graph Transformer For Internal Ice Layer Thickness Predictioncited by 5
- 2025GRIT: Graph Transformer For Internal Ice Layer Thickness Predictioncited by 4
- 2023Skip-WaveNet: A Wavelet based Multi-scale Architecture to Trace Snow Layers in Radar Echogramscited by 3
Built on by
Citing papers per year: 2026: 1.
1 paper.