Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Ai2 releases OlmoEarth v1.3 with global satellite embeddings

AI summary

Ai2 released OlmoEarth v1.3, a satellite embedding model that converts a year of Sentinel-1, Sentinel-2, and Landsat observations into 64- or 128-dimensional vectors for each 10-meter pixel. The release also includes precomputed annual embeddings for 2023–2025 worldwide, selective coverage for 2017–2022, and the browser-based OlmoEarth Embeddings Explorer. In Ai2’s evaluation, the 128-dimensional version ranked highest in 20 of 27 tests against AlphaEarth Foundations and Tessera v2, though that comparison is a vendor claim.

In-depth insight

The open model, global precomputed features, and no-sign-in explorer let researchers reuse satellite observations for land-cover, crop, and change-mapping tasks without first running a GPU-based model themselves.

OlmoEarth v1.3: State-of-the-art embeddings for the whole planet

October 22, 2026

Ai2


ModelsTech ReportDataCodeEmbeddings ExplorerInteractive story

Today, we’re releasing OlmoEarth v1.3, a state-of-the-art satellite embedding model. Alongside OlmoEarth v1.3, we’re sharing precomputed, annual embeddings for the whole planet (10m, 64- and 128-dimensions), plus a new browser-based tool to explore and customize maps based on those embeddings — the OlmoEarth Embeddings Explorer. This means anyone can put OlmoEarth v1.3 to work right away, from tracking change over time to finding similar places—no sign-in, and no advanced technical knowledge required.

#Ai2#OlmoEarth v1.3#OlmoEarth Embeddings Explorer#OlmoEarth Studio#AlphaEarth Foundations#Tessera v2#Sentinel-1#Sentinel-2#Landsat#PLANTEUR#Source Cooperative

Original · 6 min readRead the original
Group chat

No comments yet. Start the conversation.