


Understanding the Earth


With it, we're releasing the Finch embeddings of every sample of all 34 benchmark tasks we report, 207 GB under CC BY 4.0, with checksums. Blog: locamage.com/blog/finch-1-0-… Model card: locamage.com/finch-1.0-model… Embeddings: embeddings.locamage.com




On public benchmark test sets: • Crops (PASTIS): +11.3 vs AlphaEarth • Radar crop mapping (CropHarvest China): +8.4 vs OlmoEarth v1.3 Step through the season: locamage.com/blog/what-chang…

Day 3 of Finch 1: what changed. Crop types in France through a whole season, and crop mapping from radar alone. Same frozen model, same single linear layer.
Day 2 of Finch 1: what it sees. Land cover in France, buildings in Khartoum, roads and roofs around the Chesapeake Bay, and a wildfire scar in the US, from 20 cm aerial photos to 30 m satellite imagery. Every map comes from one frozen model and a single linear layer.

Every example comes from a public benchmark: FLAIR2, SpaceNet2, m-Chesapeake and HLS Burn Scars. See them all, with a slider between imagery and map: locamage.com/blog/what-finch…

Day 2 of Finch 1: what it sees. Land cover in France, buildings in Khartoum, roads and roofs around the Chesapeake Bay, and a wildfire scar in the US, from 20 cm aerial photos to 30 m satellite imagery. Every map comes from one frozen model and a single linear layer.
Meet Finch 1, our first step toward one model that works with any sensor, at any resolution, anywhere on Earth. Trained on imagery from 50+ sensors across satellites, aircraft and drones.



And it keeps getting better as we scale. Full results and how we compared: locamage.com/blog/finch-1


