40 citations · 49 across the 10 of their papers we have counts for
13 papers
PiCo: Physics-Informed Concept Probing for Geo-Foundation Models
Yihang She, Andrew Blake, Jianbo Qi +1
Geo-foundation models (GFMs) are typically evaluated by downstream task predictive performance, revealing little about which physical features they are sensitive to or use in predi…
Geospatial embeddings detect old-growth forests but buffered spatial validation narrows their advantage over Sentinel features
Thomas Ratsakatika, Mihai Zotta, Srinivasan Keshav +1
Old-growth forests develop over centuries under minimal anthropogenic disturbance, producing structurally complex and biodiverse stands. In Europe, protecting them requires mapping…
Annual Earth-observation embeddings encode wildfire disturbance and support simplified burned area mapping
Jovana Knezevic, Clement Atzberger, Zhengpeng Feng +3
Medium-resolution (10-30 m) burned area mapping is vital for monitoring wildfires and their impacts, but remains difficult to scale. Existing methods require either curated fire-sp…
How Usable Are Geospatial Foundation Models? A Systematic Evaluation of 89 Models
Robin Young, Artyom Gabtraupov, Kenzy Soror +1
Geospatial foundation models (GeoFMs) offer transformative potential for environmental monitoring, yet adoption among ecologists is uneven. Most evaluations are model-centric, focu…
TESSERA v2: Scaling Pixel-wise Earth Foundation Models
Zhengpeng Feng, Sadiq Jaffer, Ira Shokar +12
Pixel-wise Earth-observation (EO) foundation models are now achieving state-of-the-art performance via generated spatial embeddings. However, how these models scale and how best to…
Neural Processes Maintain Calibrated Biomass Estimates Across Spatiotemporal Gaps and Disturbance
Robin Young, Srinivasan Keshav
Monitoring deforestation-driven carbon emissions requires both spatially explicit and temporally continuous estimates of aboveground biomass density (AGBD) with calibrated uncertai…
Below-ground Fungal Biodiversity Can be Monitored Using Self-Supervised Learning Satellite Features
Robin Young, Michael E. Van Nuland, E. Toby Kiers +4
Mycorrhizal fungi are vital to terrestrial ecosystem functioning. Yet monitoring their biodiversity at landscape scales is often unfeasible due to time and cost constraints. Curren…
Interpolation of GEDI Biomass Estimates with Calibrated Uncertainty Quantification
Robin Young, Srinivasan Keshav
Wall-to-wall biomass density estimation from NASA's GEDI mission requires interpolating sparse LIDAR observations across heterogeneous landscapes. While Random Forest and XGBoost a…
Embedding -based Crop Type Classification in the Groundnut Basin of Senegal
Madeline C. Lisaius, Srinivasan Keshav, Andrew Blake +1
Crop type maps from satellite remote sensing are important tools for food security, local livelihood support and climate change mitigation in smallholder regions of the world, but…
Scaling Up Forest Vision with Synthetic Data
Yihang She, Andrew Blake, David Coomes +1
Accurate tree segmentation is a key step in extracting individual tree metrics from forest laser scans, and is essential to understanding ecosystem functions in carbon cycling and…
TESSERA: Temporal Embeddings of Surface Spectra for Earth Representation and Analysis
Zhengpeng Feng, Clement Atzberger, Sadiq Jaffer +11
Satellite Earth-observation (EO) time series in the optical and microwave ranges of the electromagnetic spectrum are often irregular due to orbital patterns and cloud obstruction.…
PILA: Physics-Informed Low Rank Augmentation for Interpretable Earth Observation
Yihang She, Andrew Blake, Clement Atzberger +2
Physically meaningful representations are essential for Earth Observation (EO), yet existing physical models are often simplified and incomplete. This leads to discrepancies betwee…
From Spectra to Biophysical Insights: End-to-End Learning with a Biased Radiative Transfer Model
Yihang She, Clement Atzberger, Andrew Blake +1
Advances in machine learning have boosted the use of Earth observation data for climate change research. Yet, the interpretability of machine-learned representations remains a chal…