ECMWF AIFS vs AROME
ECMWF AIFS or AROME: AI global model or high-resolution local model?
They are at opposite ends. AIFS is ECMWF's machine-learning global model on a 28 km grid, looking 15 days ahead: good for a second opinion on the large-scale pattern. AROME is Météo-France's physics model at 1.3 km for French waters, looking two days ahead: built for local winds near the coast. They complement each other rather than compete.
| ECMWF AIFS | AROME | |
|---|---|---|
| Provider | ECMWF | Météo-France |
| Type | AI model | Regional model |
| Area | Global | France, Channel, Biscay, western Mediterranean |
| Grid size | about 28 km | about 1.3 km |
| Updates | 4 times a day | 8 times a day |
| Looks ahead | 15 days | 2 days |
| Data licence | CC-BY-4.0 (open data) | Etalab Open Licence 2.0 |
Choose ECMWF AIFS when
- You want a check on the large-scale pattern days ahead.
- You are outside the AROME area.
- You want to see how an AI model reads the situation.
Choose AROME when
- You are coastal sailing in French waters in the next two days.
- You want sea breezes, headland effects and showers.
- You want local winds such as the Mistral or Tramontane.
On the water
Don't use AIFS for coastal detail: its grid is too coarse. Use it with ECMWF IFS for the plan, and AROME for the day.
More: AI weather models
Figures come from the Ilma catalog and the providers' own pages. Forecast skill changes as models are upgraded, so this page describes what each model is built for, not a ranking.