Open the dashboard

Which model is most accurate in the Balearic Islands?

In the Balearic Islands, Google's AI is the most accurate this month: its average error on tomorrow's temperature is 0.8 °C, and its lead over the second is not down to chance.

Last 30 days (11 October to 9 November) · 12 stations from AEMET

Temperature

For today (0–24 h)

In the Balearic Islands, Google's AI and the Atlas Forecast 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. 1Google AI (WeatherNext 2) (estimated)1.0 °C
  2. 2Atlas Forecast (estimated)1.1 °C
  3. 3ARPEGE (Météo-France)1.2 °C
  4. 4UKMO (Met Office)1.4 °C
  5. 5Model median1.4 °C
  6. 6GFS1.6 °C
  7. 7ICON1.6 °C
  8. 8ECMWF AIFS (AI)1.7 °C
  9. 9ECMWF IFS1.7 °C

12 stations · 30 days

For tomorrow (24–48 h)

In the Balearic Islands, Google's AI is the most accurate this month: its average error on tomorrow's temperature is 0.8 °C, and its lead over the second is not down to chance.

  1. 1Google AI (WeatherNext 2) (estimated)0.8 °C
  2. 2Atlas Forecast (estimated)1.2 °C
  3. 3ARPEGE (Météo-France)1.2 °C
  4. 4Model median1.4 °C
  5. 5UKMO (Met Office)1.5 °C
  6. 6GFS1.6 °C
  7. 7ICON1.7 °C
  8. 8ECMWF IFS1.7 °C
  9. 9ECMWF AIFS (AI)1.9 °C

12 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 the Balearic Islands, the Atlas Forecast and ICON do about equally well on today'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. 2ICON4.0 km/h
  3. 3UKMO (Met Office)4.8 km/h
  4. 4Model median5.0 km/h
  5. 5ECMWF AIFS (AI)5.8 km/h
  6. 6ECMWF IFS6.0 km/h
  7. 7GFS6.2 km/h

9 stations · 30 days

For tomorrow (24–48 h)

In the Balearic Islands, the Atlas Forecast and ICON do about equally well on tomorrow's wind (the first has an average error of 4.1 km/h): the difference between them could be chance.

  1. 1Atlas Forecast (estimated)4.1 km/h
  2. 2ICON4.3 km/h
  3. 3Model median5.1 km/h
  4. 4UKMO (Met Office)5.4 km/h
  5. 5ECMWF AIFS (AI)5.8 km/h
  6. 6ECMWF IFS6.2 km/h
  7. 7GFS6.3 km/h

9 stations · 30 days

Rain

For today (0–24 h)

In the Balearic Islands, the model median, ICON, the Met Office's UKMO, ECMWF AIFS and GFS do about equally well on today's rain (the first has an average error of 2.0 l/m² per day): the difference between them could be chance.

  1. 1Model median2.0 l/m² per day
  2. 2ICON2.1 l/m² per day
  3. 3UKMO (Met Office)2.2 l/m² per day
  4. 4ECMWF AIFS (AI)2.3 l/m² per day
  5. 5GFS2.3 l/m² per day
  6. 6ECMWF IFS2.4 l/m² per day
  7. 7ARPEGE (Météo-France)3.2 l/m² per day

12 stations · 30 days

For tomorrow (24–48 h)

In the Balearic Islands, the model median, ECMWF AIFS, the Met Office's UKMO, GFS and ICON do about equally well on tomorrow's rain (the first has an average error of 2.2 l/m² per day): the difference between them could be chance.

  1. 1Model median2.2 l/m² per day
  2. 2ECMWF AIFS (AI)2.4 l/m² per day
  3. 3UKMO (Met Office)2.4 l/m² per day
  4. 4GFS2.5 l/m² per day
  5. 5ICON2.6 l/m² per day
  6. 6ECMWF IFS2.7 l/m² per day
  7. 7ARPEGE (Météo-France)2.9 l/m² per day

12 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 Palma de Mallorca in the dashboard

Weather in the Balearic Islands

All towns in the Balearic Islands · 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.