Compressing Earth Embeddings
A single year of DINOv3 embeddings for Earth costs 6.1 PB — more than the Sentinel-2 archive that produced them. How much can you compress without losing accuracy?
GeoSpatial ML
Weekly dispatches on geospatial machine learning — remote sensing, earth observation, and everything in between.
Subscribe to NewsletterRecent Posts
Seeing the Roads Through the Trees: Do Segmentation Models Actually Use Long-Range Context?
Chesapeake RSC is a benchmark that tests whether segmentation models use long-range spatial context by asking them to label road pixels hidden under tree canopy. Spoiler: they mostly don't.
Characterizing Census Blocks with Satellite Embedding Statistics
Using Alpha Earth Foundation embeddings to predict urban/rural classification and population density at the census block level — with a simple linear model hitting 92.5% accuracy.
Training a Water Segmentation Model with TorchGeo
An end-to-end walkthrough of our ICLR 2026 ML4RS tutorial: train a DeepLabV3 model on the Earth Surface Water dataset and run inference on arbitrary Sentinel-2 scenes with TorchGeo.
Welcome to GeoSpatial ML
A new blog for geospatial machine learning explorations, experiments, and weekly finds.
