● Covered by 1 source · 1 reportLow impact1 neutral
OlmoEarth Studio now offers custom embedding exports for Earth observation data
Key points
- OlmoEarth Studio now supports custom embedding exports.
- Embeddings are compact numerical representations of Earth-observation data.
- Exports are delivered as Cloud-Optimized GeoTIFFs (COGs).
- Users can customize area, time, encoder, resolution, and imagery sources.
New Embedding Export Capability
OlmoEarth Studio, a platform for building Earth observation models, has added a feature allowing users to compute and export embedding vectors. These embeddings are compact numerical representations derived from Earth-observation data using the open-source OlmoEarth foundation models. The source code and model weights for these models are publicly available.
Utility for Downstream Analysis
The exported embeddings serve as an entry point for leveraging OlmoEarth models in various downstream tasks. These include similarity search, segmentation, and unsupervised exploration of Earth observation data. Locations with similar surface characteristics are represented by similar vectors, while differing locations are distinct.
Customization and Output Format
Users can customize the embedding generation process within OlmoEarth Studio by specifying the area of interest, time range, encoder variant (Nano, Tiny, or Base), spatial resolution (10m, 20m, 40m, 80m), and imagery sources (Sentinel-2 L2A, Sentinel-1 RTC, or both). The resulting embeddings are delivered as lightweight, shareable Cloud-Optimized GeoTIFFs (COGs).
Access and Further Options
Custom-computed embeddings are available to OlmoEarth Studio users. Instructions for computing embeddings using the publicly available OlmoEarth models are also provided. For applications requiring higher performance, Studio also supports supervised fine-tuning (SFT).
✨ This summary was generated by AI from the outlets' reporting listed below. It is not independently verified and may contain errors — check the original sources. How BrevFeed works →
The daily brief
One email each morning: the day's tech stories, clustered across outlets and summarized. No account needed.
One email a day. Unsubscribe in one click, any time.
Today's brief
Spend a few minutes, get the whole day. Every topic's top stories in one hands-free rundown — listen, watch, or read the transcript.
▶ Play today's brief
New every morning, and the back catalogue is archived by date.
Primary sources
GitHub allenai/olmoearth_pretrain GitHub allenai/rslearn GitHub allenai/olmoearth_projects arXiv 2603.02080Reporting from
OlmoEarth Studio has introduced the ability to compute and export embedding vectors from its open-source OlmoEarth foundation models. These embeddings provide compact numerical representations of Earth-observation data, enabling various downstream analytical tasks such as similarity search and segmentation.