The organizations best positioned to use Earth-observation models – those working in conservation, food security, & disaster response – often can't run these models at the scale they need.
That's an infrastructure problem. So we built the OlmoEarth Platform to solve it. 🧵
The OlmoEarth Platform takes geospatial models from fine-tuning all the way through large-scale inference.
Today it can run inference across a continent in roughly a day, processing dozens of TB of imagery at a cost of fractions of a penny per km².
At its core is OlmoEarth Run, the engine that takes the area an OlmoEarth Platform job covers, splits it into partitions, then into smaller windows the models process.
Because each window is independent, the same work can run across thousands of machines at once.
Each OlmoEarth Platform job runs in three hardware-matched stages – prep (CPU), inference (GPU), postprocess (CPU) – inside runners that spin up, do one task, & shut down.
Every task is idempotent, so a stalled provider or crashed job is just retried or rerouted.
inference — Running a trained model to get answers — the phase where AI is actually used, as opposed to trained.
Why it matters
A concrete recipe for continent-scale inferenceRunning a trained model to get answers — the phase where AI is actually used, as opposed to trained.Full definition →: split work into independent windows, separate CPU prep from GPU inference, make every task idempotent so failures reroute, and index your source data so fetching stops being the bottleneck.
Read the full thread on X ↗
