Open the dashboard

Which model is most accurate in Gipuzkoa?

In Gipuzkoa, the Atlas Forecast, the model median, Météo-France's ARPEGE and ECMWF IFS do about equally well on tomorrow's temperature (the first has an average error of 1.2 °C): the difference between them could be chance.

Last 30 days (11 October to 9 November) · 3 stations from AEMET

Temperature

For today (0–24 h)

In Gipuzkoa, the Atlas Forecast and Météo-France's ARPEGE do about equally well on today's temperature (the first has an average error of 1.0 °C): the difference between them could be chance.

  1. 1Atlas Forecast (estimated)1.0 °C
  2. 2ARPEGE (Météo-France)1.1 °C
  3. 3Model median1.1 °C
  4. 4ICON1.3 °C
  5. 5ECMWF IFS1.3 °C
  6. 6ECMWF AIFS (AI)1.4 °C
  7. 7UKMO (Met Office)1.6 °C
  8. 8GFS1.9 °C
  9. 9Google AI (WeatherNext 2) (estimated)2.8 °C

3 stations · 30 days

For tomorrow (24–48 h)

In Gipuzkoa, the Atlas Forecast, the model median, Météo-France's ARPEGE and ECMWF IFS do about equally well on tomorrow's temperature (the first has an average error of 1.2 °C): the difference between them could be chance.

  1. 1Atlas Forecast (estimated)1.2 °C
  2. 2Model median1.3 °C
  3. 3ARPEGE (Météo-France)1.4 °C
  4. 4ECMWF IFS1.5 °C
  5. 5ECMWF AIFS (AI)1.5 °C
  6. 6ICON1.5 °C
  7. 7UKMO (Met Office)1.7 °C
  8. 8GFS2.0 °C
  9. 9Google AI (WeatherNext 2) (estimated)2.8 °C

3 stations · 30 days

Average error in the temperature for each hour, at the stations in the area. The shorter the bar, the better. Highlighted: the leaders, where the difference between them cannot be put down to chance.

Wind

For today (0–24 h)

In Gipuzkoa, the Atlas Forecast is the most accurate this month: its average error on today's wind is 3.8 km/h, and its lead over the second is not down to chance.

  1. 1Atlas Forecast (estimated)3.8 km/h
  2. 2ICON4.1 km/h
  3. 3Model median4.1 km/h
  4. 4GFS4.2 km/h
  5. 5UKMO (Met Office)4.6 km/h
  6. 6ECMWF IFS4.6 km/h
  7. 7ECMWF AIFS (AI)5.3 km/h

3 stations · 30 days

For tomorrow (24–48 h)

In Gipuzkoa, the Atlas Forecast and the model median do about equally well on tomorrow's wind (the first has an average error of 3.8 km/h): the difference between them could be chance.

  1. 1Atlas Forecast (estimated)3.8 km/h
  2. 2Model median4.1 km/h
  3. 3ICON4.1 km/h
  4. 4GFS4.1 km/h
  5. 5ECMWF IFS4.6 km/h
  6. 6UKMO (Met Office)4.7 km/h
  7. 7ECMWF AIFS (AI)5.1 km/h

3 stations · 30 days

Rain

For today (0–24 h)

In Gipuzkoa, the model median, GFS, ICON and Météo-France's ARPEGE do about equally well on today's rain (the first has an average error of 0.7 l/m² per day): the difference between them could be chance.

  1. 1Model median0.7 l/m² per day
  2. 2GFS0.7 l/m² per day
  3. 3ICON0.8 l/m² per day
  4. 4ARPEGE (Météo-France)0.9 l/m² per day
  5. 5ECMWF AIFS (AI)1.0 l/m² per day
  6. 6ECMWF IFS1.0 l/m² per day
  7. 7UKMO (Met Office)1.1 l/m² per day

3 stations · 30 days

For tomorrow (24–48 h)

In Gipuzkoa, the model median, ICON, GFS and Météo-France's ARPEGE do about equally well on tomorrow's rain (the first has an average error of 0.8 l/m² per day): the difference between them could be chance.

  1. 1Model median0.8 l/m² per day
  2. 2ICON0.8 l/m² per day
  3. 3GFS0.9 l/m² per day
  4. 4ARPEGE (Météo-France)1.0 l/m² per day
  5. 5ECMWF AIFS (AI)1.1 l/m² per day
  6. 6ECMWF IFS1.1 l/m² per day
  7. 7UKMO (Met Office)1.2 l/m² per day

3 stations · 30 days

Error in the total rain for each day, in litres per square metre.

The Atlas Forecast is active here: its error is an estimate based on the days when it could be verified, compared with the model median over the same hours.

Google's AI (WeatherNext 2) is now in the league. As we only compare it every 6 hours (that is how often it runs) and measure it at one station per province, its error is an estimate: the model median's error plus how much more or less Google's AI misses than the median at those hours.

See San Sebastián in the dashboard

Weather in Gipuzkoa

All towns in Gipuzkoa · The league in the other provinces

How it is calculated

We compare what each model had forecast for the same day (0–24 h) and for the next day (24–48 h) with what the Meteocat (in Catalonia) and AEMET weather stations measured over the last 30 days. They all compete over the same hours. Being first is not enough to win: the difference has to pass a day-by-day statistical test (otherwise it could be chance) and at least 14 days are needed.

Winning this month does not mean winning every month: every model has its good and bad days. More detail in Accuracy and, for your exact spot, in «Which model is right here?» in the dashboard.