The paper introduces ICIBS, a deep‑learning approach that enhances ice‑boundary segmentation by incorporating additional spatial and geo‑spatial context into the model. It reports state‑of‑the‑art performance on the IceAnatomy benchmark, achieving mean errors of 10.9 m (FAU subset) and 43.4 m (CReSIS subset), and demonstrates strong generalisation to new Patagonia data, outperforming baselines by 49.6 %. The authors provide the model code and dataset publicly on GitHub and Zenodo.
Mountain glaciers and ice sheets are undergoing rapid loss of ice mass. To assess their current volume and ice-thickness distribution, and to accurately forecast their future, ground-penetrating radar...
arXiv:2512.12142v2 Announce Type: replace-cross Abstract: The Greenland ice sheet is melting at an accelerated rate due to processes that are not fully understood and hard to measure. The distributio...
arXiv:2604. 09922v2 Announce Type: replace Abstract: Subsurface stratigraphy contains important spatio-temporal information about accumulation, deformation, and layer formation in polar ice sheets.
arXiv:2609.16347v1 Announce Type: new Abstract: Sea-ice type prediction is important for climate monitoring, maritime navigation, and decision-making in polar regions. The main source of label data f...
Cryo-Bench is a new benchmark that evaluates foundation models for cryosphere mapping, comprising six semantic‑segmentation datasets across five cryospheric components (supraglacial debris, glacial lakes, sea ice, calving fronts, and Antarctic ice‑shelf extent). The benchmark includes multispectral, RGB, and SAR observations from under‑represented regions and tests thirteen geo‑foundation models alongside U‑Net and Vision Transformer baselines. Results show that with frozen encoders U‑Net slightly outperforms TerraMind, but the difference is not statistically significant; fine‑tuning with learning‑rate optimization can dramatically improve performance for some models, while in few‑shot scenarios several foundation models retain over 90 % of their full‑label accuracy.
arXiv:2607. 04117v1 Announce Type: new Abstract: ERA5 seasonal climate variables contain predictive information about future glacier retreat beyond what satellite imagery alone provides, yet existing deep learning methods focus on mapping current boundaries rather than forecasting future ones.
The paper introduces a multimodal foundation model for lunar remote sensing, trained from scratch on SomBench—a dataset of nearly two million co‑registered tile bundles across 11 modalities at 1 m and 100 m resolutions. The model extends the TerraMind masked‑token architecture with lunar‑specific features such as explicit acquisition geometry and joint training of two spatial scales, and employs FlexiViT patch embeddings for adaptable patch sizes. Evaluation on crater detection, irregular mare patch segmentation, and polar ice prospectivity regression shows that the pretrained model matches or surpasses ImageNet‑pretrained baselines, with notable label efficiency and effective adaptation via LoRA.
arXiv:2606. 06524v1 Announce Type: cross Abstract: Accurate and scalable flood mapping remains challenging due to limited ground observations, heterogeneous terrain conditions, and the difficulty of enforcing hydrodynamic consistency within data-driven models.
arXiv:2608. 12422v1 Announce Type: new Abstract: Two free satellite signals carry real information about glacial-lake outburst risk in the Nepal Himalaya: radar interferometry sees a moraine dam slowly sagging, and satellite weather marks the weeks when a primed lake is under stress.
arXiv:2607. 05207v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task.
arXiv:2608. 04706v1 Announce Type: new Abstract: Monitoring of offshore wind energy infrastructure life cycles, especially during the deployment phase, is an important contribution for stakeholders to make informed decisions in a phase of increasing deployment activities.
Self-supervised learning (SSL) is designed to learn generic, transferable representations rather than representations optimized for a single task. Most geospatial benchmarks evaluate representations solely through downstream tasks, providing limited insight into the information encoded within the representation itself.