Madrid: the models split by day 6
Four forecasts from the 16 Sep 12Z run: ECMWF's learned model (AIFS), its physics model (HRES), Google DeepMind's WeatherNext 2, and the ECMWF ensemble mean, with the ensemble's 10–90% range shaded behind them.
Driven by temperature. 50 means the models disagree as much as the ensemble expects.
Disagreement by day
How it's measuredDay number after the run. Hover a chip for the date and the variable behind it.
2 m temperature, every model
Hover or tap the chart to read each model at that hour. The grey band is the range the ensemble puts 80% of its members in.
Day by day
Each model's high and low for the 24 hours ending at the time shown, °C. Δ is how much that model's high moved since its previous run, twelve hours earlier.
| Day | DI | AIFS | HRES | WN2 | ENS mean | ENS range | Spread of highs |
|---|---|---|---|---|---|---|---|
| Day 1to Thu 17 12Z | 4temperature | 23° 14°Δ -1 | 24° 14°Δ 0 | 24° 15°Δ 0 | 23° 14°Δ -1 | 23–24° | 1° |
| Day 2to Fri 18 12Z | 27temperature | 25° 14°Δ 0 | 25° 15°Δ 0 | 25° 14°Δ 0 | 25° 14°Δ 0 | 24–25° | 0° |
| Day 3to Sat 19 12Z | 30temperature | 26° 14°Δ 0 | 26° 16°Δ 0 | 26° 15°Δ +1 | 26° 15°Δ 0 | 26–26° | 0° |
| Day 4to Sun 20 12Z | 46temperature | 27° 14°Δ 0 | 28° 17°Δ 0 | 27° 15°Δ +1 | 28° 15°Δ 0 | 27–28° | 1° |
| Day 5to Mon 21 12Z | 53temperature | 28° 14°Δ 0 | 29° 17°Δ 0 | 27° 15°Δ 0 | 29° 16°Δ 0 | 28–30° | 2° |
| Day 6to Tue 22 12Z | 61temperature | 29° 14°Δ 0 | 31° 19°Δ 0 | 29° 15°Δ +1 | 30° 16°Δ +1 | 29–31° | 2° |
| Day 7to Wed 23 12Z | 44temperature | 29° 16°Δ 0 | 31° 18°Δ 0 | 29° 16°Δ +1 | 29° 17°Δ 0 | 28–31° | 2° |
| Day 8to Thu 24 12Z | 54pressure | 30° 16°Δ +1 | 30° 19°Δ 0 | 28° 16°Δ 0 | 29° 17°Δ 0 | 27–31° | 2° |
| Day 9to Fri 25 12Z | 61temperature | 31° 15°Δ +3 | 31° 19°Δ +2 | 28° 15°Δ 0 | 30° 17°Δ +1 | 27–32° | 3° |
| Day 10to Sat 26 12Z | 57temperature | 29° 14°Δ 0 | 30° 18°Δ +1 | 27° 15°Δ 0 | 29° 17°Δ +1 | 26–32° | 3° |
Open this place on the map
Values are what Forecast Euro's ingest sampled from each model's grid at this city, rounded to whole degrees at source. This page compares models; it is not a forecast to plan by.