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.
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.
The study trains a convolutional LSTM on ten annual Earth Observation variables to forecast desertification dynamics in Ceará, Brazil, achieving modest improvements over persistence and capturing 53‑69% of the regional degradation trend. While the model slightly outperforms simple baselines one to four years ahead, it explains only a small fraction of cell‑level variance, indicating that EO data are more reliable for regional trends than for individual pixel predictions. The authors also demonstrate that elevation and EVI channels degrade forecast skill, and use Monte Carlo dropout to quantify uncertainty in future degradation maps.
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.
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. 04190v1 Announce Type: new Abstract: Global reanalysis products such as ERA5-Land provide spatially complete weather fields but at resolutions too coarse for local applications, particularly in mountainous regions where temperature can vary by several degrees over short distances.
arXiv:2608. 12271v1 Announce Type: new Abstract: Global weather reanalyses and forecasts resolve the evolving atmospheric state on coarse grids, but site-specific applications require predictions at arbitrary locations where near-surface conditions also depend on unresolved terrain and land-surface properties.
The paper evaluates the Quebec-specific 10‑m land‑cover product COTQ against three global 10‑m datasets (ESA WorldCover, ESRI LandCover, and Google DynamicWorld). Using structural indicators, spectral separability metrics, and photo‑interpretation, the study finds that COTQ most closely resembles ESA WorldCover but shows systematic differences in urban, wetland, and rocky classes. The analysis clarifies COTQ’s relative strengths and weaknesses for operational land monitoring in Quebec.
arXiv:2606. 23833v1 Announce Type: new Abstract: Terrestrial water storage (TWS) integrates snow, soil moisture, surface water, and groundwater and is a key indicator of how climate variability and human activity reshape the global water cycle.
arXiv:2610.27793v1 Announce Type: cross Abstract: Uncertainty in the terrestrial carbon cycle remains a major constraint in climate projections, partly due to imperfect land surface representations i...
arXiv:2606. 05731v1 Announce Type: new Abstract: In-season crop type mapping is critical for food security in the face of increasingly extreme climate-related threats to crops.
The paper introduces a dual‑framework Vision Transformer (ViT) method for estimating diffuse horizontal irradiance (DHI) from sky images in data‑scarce settings. It combines physics‑based atmospheric parameters, a sequential pipeline that first predicts synthetic global horizontal irradiance (GHI), and a dual‑parallel architecture that processes raw and physics‑informed overlay‑enhanced fisheye images. Tested on Chilbolton Observatory data, the approach achieves RMSE within 2–6 W/m² of a ViT trained on a full dataset, demonstrating a scalable, cost‑effective solution for solar resource assessment when long‑term sky imagery is limited.