OlmoEarth Platform Scans an Entire Continent in 30 Hours Using Nearly 1,000 GPUs
The Allen Institute for AI has built a system that can run an AI wildfire-risk model across all of North America in about a day, at a cost of fractions of a penny per square kilometre. Here's what that actually means.
Key points
- The Allen Institute for AI (Ai2) launched the OlmoEarth Platform to run large-scale AI analysis on satellite imagery for environmental organisations.
- A single North America wildfire-risk map run used 19,600 CPUs and 994 GPUs in parallel, finishing in roughly 30.5 hours instead of an estimated 4,737 hours.
- The platform processes dozens of terabytes of imagery at a cost of fractions of a penny per square kilometre.
- Governments and NGOs are already using the underlying OlmoEarth models for deforestation monitoring, food security work and wildfire risk mapping.
- OlmoEarth was pretrained on roughly 10 terabytes of satellite data and is open for organisations to build on.
Satellites photograph every inch of Earth constantly. Making sense of all those pictures fast enough to act on them is another matter entirely.
The Allen Institute for AI, known as Ai2, has built infrastructure called the OlmoEarth Platform to do exactly that. It takes its family of OlmoEarth models, AI systems trained specifically on roughly 10 terabytes of satellite imagery, and runs them at a scale most organisations couldn't manage on their own.
What did this system actually accomplish?
To map wildfire risk across all of North America, the platform split the continent into thousands of small patches, analysed each one separately, then stitched the results back into a single map. At peak load, it ran on 19,600 CPUs (general-purpose computer processors) and 994 GPUs (the specialised chips that do the heavy number-crunching AI needs) simultaneously. Network traffic between machines hit 168 gigabytes per second. The whole job finished in about 30.5 hours. Without that parallelism, running tasks sequentially, the same work would have taken an estimated 4,737 hours, a 155-times speedup.
The cost sits at fractions of a penny per square kilometre, which makes continent-wide scans financially realistic for NGOs and government agencies. We first covered OlmoEarth on 28 July 2026 and this is the third geospatial AI story AI2Day has reported in the last 90 days.
Why is satellite AI so much harder than ordinary AI?
Most AI models handle a few megabytes of data and return an answer in under a second. Satellite inference is a different category of problem. A single analysis job can move terabytes of data and run for hours.
Images come from multiple providers, each using different coordinate systems and resolutions. Clouds block optical sensors. Some data arrives minutes after capture; other datasets lag by days. Every prediction must line up precisely on a geographic grid so the final output is an accurate map, not a patchwork.
Downloading and preparing imagery often takes longer than running the AI model itself.
How does the platform handle all of that?
Ai2 splits each job into three stages matched to different hardware. CPUs handle the fetch and alignment of raw imagery. GPUs run the actual AI analysis. CPUs then handle the final stitching and export into formats like GeoTIFF, a standard file type used in mapping software.
Keeping GPUs busy only on the AI step is what makes the economics work. To avoid flooding satellite data providers with thousands of simultaneous requests, the platform keeps its own internal index of available imagery, updated as new scenes are published. Requests to external services stay at a steady trickle rather than a sudden surge.
Who is this for, and what does it mean for ordinary people?
Most environmental organisations, the ones doing deforestation monitoring or tracking food supply risks in drought-prone regions, don't have the engineering teams to run this kind of infrastructure themselves. The OlmoEarth Platform is designed to close that gap.
For people living in wildfire-prone areas, faster satellite analysis means the organisations watching for those threats can update their maps more frequently and act earlier. That's the practical argument here, and it's a more honest one than "AI predicts wildfires" headlines tend to suggest.
OlmoEarth's models are open, meaning any organisation with a capable technical team can download and build on them directly. The platform is the managed layer built on top for everyone else.
Common questions
Does this mean AI can now predict wildfires?
Not exactly. The platform produces risk maps based on current satellite data, showing which areas have conditions associated with higher fire danger. It's a monitoring tool, not a precise forecast.
Is the OlmoEarth model free to use?
The underlying OlmoEarth models are open: organisations can download and adapt them. The OlmoEarth Platform, the managed infrastructure for running them at scale, is a separate Ai2 product aimed at organisations without large engineering teams.
