The study evaluates the use of frozen geospatial foundation embeddings (AlphaEarth) for mapping cultivated versus non‑cultivated land in Maine. Using 192 spatially separated patches and USDA Cropland Data Layer labels, a lightweight classifier achieved 93.7% overall accuracy without fine‑tuning, and a nearest‑class‑centroid rule reached 90.2%. A balanced sample of 60,000 labeled pixels was nearly as effective as the full 8.6 million‑pixel pool, and classifiers trained in one year remained accurate across 2018‑2023. In a blind human validation of 385 points, the AlphaEarth‑plus‑random‑forest map matched 95.3% of the consensus, outperforming the CDL reference (91.7%).
arXiv:2609.28194v1 Announce Type: new Abstract: Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, pro...
arXiv:2609.36975v1 Announce Type: new Abstract: Operational estimation of wheat-cultivated area is persistently constrained by discordance between administrative record-keeping and remotely sensed cl...
arXiv:2606. 29664v1 Announce Type: cross Abstract: Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic transferability has not been systematically tested, especially in agriculture applications.
arXiv:2607. 21881v1 Announce Type: cross Abstract: Agricultural field maps are often proprietary, incomplete, or outdated, yet they provide the spatial framework for crop monitoring, production accounting, and land-conversion analysis.
The paper introduces a composition‑aware pretraining framework for geospatial foundation models that explicitly encodes fractional land‑cover mixtures as histogram targets for each satellite image cell. By using Earth Mover’s Distance to distill these composition targets into a 36.8 M‑parameter backbone, the authors demonstrate significant improvements on region‑level tasks such as zero‑shot image retrieval and scene classification, while maintaining competitive performance on fine‑grained tasks like segmentation and object detection. The method outperforms larger models (SatMAE and Prithvi‑EO‑2.0) and achieves a 55.6 % relative boost on the ForestNet‑12 dataset, evidencing the benefit of explicit composition modeling.
arXiv:2608. 04792v1 Announce Type: new Abstract: Accurate estimation of Above-Ground Biomass (AGB) from satellite imagery is essential for the large-scale monitoring of carbon stocks, yet it remains a challenging regression task at global scale.
The study presents a new approach to detect Christmas tree plantations in high‑resolution aerial imagery, treating the task as a rare‑target semantic segmentation problem. It introduces a Hard Negative Mining strategy that significantly improves precision‑recall performance, achieving an IoU of 0.733 and an F1‑score of 0.846 on a 2020 test set. Temporal transfer experiments demonstrate the model’s ability to generalize across years, while large‑scale validation highlights the challenge posed by the plantations’ small spatial footprint.
Geospatial foundation models pretrained on satellite imagery promise broad generalization across remote sensing tasks and regions, but their geographic transferability has not been systematically tested, especially in agriculture applications. This paper presents a controlled benchmark that evaluates three models, Prithvi, SpectralGPT, and SatMAE, on multi-temporal crop segmentation and change detection across four U.
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 study evaluates how the length of observation windows affects the performance of Tessera embeddings for land‑use/land‑cover mapping. By freezing the encoder and recomputing embeddings from a full year down to a single day, the authors benchmark linear probes and UNet heads on LUCAS, DynamicEarthNet, and PASTIS‑R datasets. Results show that embeddings are highly task‑dependent: for phenology‑driven classes (PASTIS‑R) they outperform from‑scratch models by ~46%, while for temporally stable classes (DynamicEarthNet, LUCAS) they match only with full supervision, yet remain more label‑efficient across all datasets.
The study maps tree species across Denmark using National Forest Inventory plots and Earth Observation data, comparing manually engineered spectral‑temporal features (STF) from Sentinel‑1 and Sentinel‑2 with embeddings from the foundation models TESSERA and AlphaEarth. Random forest, XGBoost, and MLP classifiers were evaluated, with the STF‑based MLP achieving the highest macro F1 scores for pure and mixed stands. The best model was applied nationally to produce a 10 m resolution tree species map, achieving 79.9% area‑adjusted accuracy and released as an open‑access product.
AgroBench is a reproducible benchmark that converts U.S. county-level crop yield statistics into weakly supervised pixel‑level crop time series. The data generation pipeline fuses USDA yield data with land cover masks, Sentinel‑2 and Sentinel‑1 imagery, climatic variables, and terrain information to produce multimodal sequences for individual crop pixels across the growing season. The benchmark includes over 13 million observations from 788,654 crop pixels, covering 5,107 county‑year combinations for five major U.S. crops from 2017 to 2024, and establishes a Leave‑One‑Year‑Out evaluation protocol with baseline machine learning results.