Hugging Face Trending Papers
PiCo: Physics-Informed Concept Probing for Geo-Foundation Models
Read the original on Hugging Face Trending Papers →The Flow has not summarised this story yet — read it at Hugging Face Trending Papers.
Related stories
arXiv Computer Vision
Oct 16
PiCo: Physics-Informed Concept Probing for Geo-Foundation Models
PiCo is a post‑hoc framework that explains Geo‑foundation model predictions by identifying concept vectors in the model’s embedding space. It generates synthetic multispectral satellite data using a 3D radiative transfer model and a game engine to reveal physical sensitivities, then projects embeddings onto these vectors to quantify concept importance. Evaluations on three GFMs show that PiCo can recover most of the full‑embedding accuracy and uncover how different physical concepts influence predictions for tasks such as ground‑cover estimation and forest classification.
arXiv Machine Learning
Jul 31
Foundation-Model Earth Representations Enable Regional-Scale Forest Aboveground Biomass Monitoring Across the Northeastern United States
arXiv:2607. 27217v1 Announce Type: cross Abstract: Forest aboveground biomass (AGB) is a critical indicator of ecosystem productivity and terrestrial carbon storage, yet regional carbon monitoring remains constrained by the sparse spatial and temporal availability of field inventories and airborne structural measurements.
arXiv Computer Vision
Oct 8
Geometry-Centered 3D Latent World Models for Growing Surfaces
The paper introduces FOLIAGE, a geometry‑centered latent world model designed for systems that grow and change shape over time. FOLIAGE allocates higher‑resolution state to regions expected to grow while keeping mature areas compact, fusing RGB, point‑cloud, and mesh data into a deployable geometric state and conditioning dynamics on material controls. The authors evaluate the model on new benchmarks (SURF‑GARDEN and SURF‑BENCH) and demonstrate significant reductions in inverse‑material error, mesh forecasting error, and improved cross‑modal retrieval, with robust performance under sensor loss and correspondence corruption.
arXiv Machine Learning
Sep 1
Foundation Models Meet Agriculture: Challenges Beyond Pretraining
arXiv:2608.30392v1 Announce Type: new Abstract: Global food security and sustainable climate action increasingly rely on robust, scalable agricultural monitoring. Earth observation foundation models...
arXiv AI
Sep 1
A Composition-Aware Pretraining Framework for Geospatial Foundation Models
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.
Hugging Face Trending Papers
Jul 6
Probing Geospatial SSL Representations with Environmental Signals
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.