Ai2 releases OlmoEarth v1.3 for satellite mapping

Oct 22, 2026
OlmoEarth v1.3 converts annual satellite observations into numerical representations of land, with precomputed data covering the planet and a browser based mapping tool.

The Allen Institute for AI (Ai2) has released OlmoEarth v1.3, precomputed annual satellite embeddings covering the planet, and a browser based mapping tool, according to SiliconANGLE. The model compresses one year of observations into a numerical representation for each area, with its finest resolution covering patches measuring 10 by 10 meters.

OlmoEarth processes radar, visible light, and infrared data from sources including Sentinel-1, Sentinel-2, and Landsat. Software can use its embeddings to identify crops, forests, mines, and other types of land cover or compare changes across years.

The OlmoEarth Embeddings Explorer lets users create maps from a small set of labels without signing in or using a GPU. Ai2 says v1.3 required 53% of the computing time and produced 50% of the carbon emissions of v1.2 during training. Compared with the first version, it required 18% of the computing time and produced 22% of the emissions.

We hope you enjoyed this article

Consider subscribing to one of our newsletters like Daily AI Brief.

Also, consider following us on social media:

AI Brief AI Brief (X)
Free newsletter

Daily AI Brief

Daily report covering major AI developments and industry news, with both top stories and complete market updates

AI Token Webinar

Whitepaper

Tensordyne Napier: What If One Rack Could Do the Work of Nine?

Tensordyne

This Tensordyne whitepaper presents Napier, an inference-focused AI processor and rack-scale system based on the company’s TDN Math logarithmic number system. It examines infrastructure requirements for large mixture-of-experts and agentic models, compares major inference architecture approaches, and details the TDN AIP processor, TDN72 pod, TDN Link fabric, and Napier Ultra configuration. The paper reports simulation-based performance, cost, and accuracy-validation results, including Tensordyne’s projected comparison of one Napier rack with a nine-rack Nvidia Rubin plus Groq deployment; the chip is reported as taped out and in fabrication.

Read more

You may also like

Free, six days a week

Daily AI Brief: the AI news that matters, in your inbox.