OlmoEarth v1.3: State-of-the-art embeddings for the whole planet
Source
huggingface.co
Date
Why it matters
Precomputed 10m annual embeddings for the whole planet let you do change detection and similarity search without GPUs or downloading satellite imagery.
Key takeaways · AI-distilled
OlmoEarth v1.3 turns a year of Sentinel-1 radar and Sentinel-2 and Landsat imagery into one 128-dimension vector per 10-meter pixel, and the first 64 dimensions also work alone. Ai2 precomputed these for the planet, roughly 150 TB per year.
Against AlphaEarth Foundations and Tessera v2 across 27 evaluations, Ai2 reports its 128-dimension embeddingA list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.Full definition → scored highest on 20 and the 64-dimension version led on 18. The evaluations include PLANTEUR, a new crop-type benchmarkA standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.Full definition → for tropical farming.
With precomputed embeddings, a crop or land-cover map becomes a small classifier trained locally instead of a GPU fine-tuningTaking a trained model and training it a bit more on your own examples so it gets better at one specific job.Full definition → run, and change detection can compare a pixel's vectors across years with no training at all.
v1.3 took 53% of v1.2's training computing time and 18% of v1's. Ai2 estimates the final Base pretrainingThe first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.Full definition → run would cost roughly $2,720 of rented H100 time to reproduce, and the weights, data and code are open.
Coverage is uneven at launch: 2023 to 2025 are global, while 2017 to 2022 cover select countries. Provenance tables for each 20 km tile and year list the Sentinel-1, Sentinel-2 and Landsat scenes behind the embeddings.
Terms in this piece · Glossary
embedding — A list of numbers representing a piece of text's meaning, so that similar meanings end up numerically close and can be searched.
benchmark — A standard public test set for comparing AI models — the shared scoreboards behind every "model X beats model Y" claim.
fine-tuning — Taking a trained model and training it a bit more on your own examples so it gets better at one specific job.
pretraining — The first, biggest phase of building a model: training it on enormous amounts of text so it learns language, facts, and reasoning in general.
