About Odeai
We develop fast-refresh, observation-driven weather models that learn from radar and satellite, for short-range precision.
The company
Odeai builds end-to-end forecasting models. By running the entire forecasting chain ourselves, from data assimilation to delivery, and by combining physics with artificial intelligence, we give our clients forecasts that refresh within minutes. At short range, they are significantly more accurate than those of conventional radar apps and numerical weather models.
Current production model · September 2026
- Forecast horizon
- 3 h
- Forecast refresh
- 10 min
- Grid spacing
- 4 km
- Inputs: NOAA MRMS, GOES, OPERA
- Radar + satellite
How the pipeline works
Conventional prediction passes observations through a chain of processing steps, each adding error and delay. We run the chain ourselves, from raw observation to forecast, in three steps.
- 01
Every sensor, read together
One encoder brings radar, satellite imagery, and other sensor data into a shared representation the model reasons over.
- 02
Forecasts that stay sharp
The model predicts the future in its internal representation instead of pixel by pixel, which keeps forecasts sharp at longer lead times.
- 03
New data in minutes
New observations flow in continuously and refine the model state, so a new forecast is ready minutes after the data lands.
The full argument is in the white paper, April 2026.
Read the white paperLeadership
The story of the name

In Basque mythology, Odei is the spirit who causes lightning to strike and triggers storms.
Our name carries it, and says two more things: ODE, for the Ordinary Differential Equations at the heart of numerical weather prediction, and AI, for the Artificial Intelligence that now works alongside them.


Our mark comes from a discoidal stele in Sainte‑Engrâce, in the Basque Country.
Make the call with the forecast in hand.
Tell us the decision you make and where. We will show you the forecast on your own past events.


