NASA Ran a Google AI Model Inside a Satellite. Here Is What It Found.
A small, efficient AI model analyzed real images from orbit and sent back plain-text descriptions instead of raw data. It could cut wildfire alerts from 90 minutes to near-instant.
Key points
- NASA's Jet Propulsion Laboratory ran Google's Gemma 3 AI model aboard the YAM-9 satellite in 2025, marking the first time a vision-language AI processed images in orbit from its own camera.
- The system, called NAVI-Orbital, scored 88 percent accuracy classifying 7,960 images in a ground-based test before launch.
- The model runs on just 8 GB of memory, small enough for a laptop, yet powerful enough to describe satellite imagery from space.
- Bandwidth limits currently delay wildfire satellite alerts by up to 90 minutes; text summaries from an onboard AI could cut that close to zero.
- Scientists can now direct the satellite using plain-English prompts rather than writing complex structured commands through an operations team.
A Google AI model is orbiting Earth right now, looking out a satellite window and writing down what it sees.
NASA's Jet Propulsion Laboratory (JPL) recently flew Google's Gemma 3, an open-source large language model (a type of AI that reads and generates text and, in this case, understands images too), aboard a commercial satellite called YAM-9, built by a company called Loft Orbital. The experiment, first reported by IEEE Spectrum AI, marks the first time a vision-language AI has analyzed images from a satellite's own camera while still in orbit.
What did the AI actually do up there?
The system looked at photos taken by the satellite's camera and wrote plain-English descriptions of them. No raw image files were beamed back to Earth. Just words.
The software framework running it is called NAVI-Orbital. During two live tests, the satellite passed over Toulouse, France and the coast of Argentina. The AI studied each image and answered scripted questions: Is this a commercial or residential area? Are there natural features visible?
All that processing happened on a small Nvidia Jetson Orin AGX, a compute module (a self-contained mini-computer) about the size of a thick paperback, commonly used in robots. The version of Gemma 3 on board uses a compressed format that needs only 8 GB of memory. Delfa put it bluntly: "You can run it in a tiny, tiny computer."
| Detail | Figure |
|---|---|
| Ground-test accuracy | 88% across 7,960 images |
| Model size (memory) | 8 GB |
| On-board power available | 150 to 500 watts (solar) |
| Current wildfire alert delay | Up to 90 minutes |
| Data saved vs. raw images | Kilobytes vs. hundreds of megabytes |
Why does it matter that the AI is on the satellite rather than on the ground?
Satellites can only beam data to Earth at set intervals, and the connection is often slow. Sending a full high-resolution image can take significant bandwidth. Sending a two-sentence text description takes almost nothing.
Loft Orbital's general manager Paul Lasserre calls this "semantic compression": the AI summarizes what is important, and only that summary travels home. "It doesn't matter if the link is slow, because you're downlinking dozens of kilobytes instead of dozens or hundreds of megabytes," Lasserre said.
The wildfire example makes this concrete. Satellites already spot wildfires, but data processing and download delays push alerts back by up to 90 minutes. An onboard AI that flags a fire in plain text could compress that window dramatically.
What changes for scientists who use satellites?
Today, directing a satellite requires writing precise, structured commands, usually through a specialist operations team. NAVI-Orbital lets a researcher type a plain-English question or instruction instead, upload it, and the satellite acts on it.
"Now, a scientist can write a prompt, upload it to the spacecraft, and that will be taken into account by the system," said Juan Delfa, the technical group lead at NASA JPL who led the project. To change what the satellite looks for, say, switching from urban mapping to wildfire detection, you edit a text prompt. No new software. No retraining the AI.
The system is deliberately walled off from flight controls for now. It reads images and returns descriptions. Nothing more. But Delfa's longer vision is bigger: he wants AI to act as a natural-language companion for astronauts, helping them operate equipment inside a spacesuit where dexterity is limited.
That future is still years of research away. What NAVI-Orbital proved is that the two foundations, running a capable AI model in space and controlling it with plain language, both work today.
Takeaway: If you work with satellite data, Earth observation, or emergency response systems, watch this project. The practical payoff, faster alerts, simpler commands, is closer than most space technology tends to be.
