Air temperature

24 hour forecast of historical and forecast data

Our results show that the meteoblue learning multimodel (MLM), which is used in the operational forecast, performs significantly better than MOS simulations and the historical reanalysis model ERA5 (MAE = 1.2 K vs. MAE = 1.5 K). The accuracy of stand-alone numerical weather forecast models (e.g. NEMS, GFS) is significantly worse than MOS and MLM in particular. 

Over 90 % of all meteorological stations have an accuracy better than 2 K by using the meteoblue learning multimodel (MLM). This number is reduced to 85 % by using the reanalysis model ERA5 and to 50 % (36%) by using the stand-alone numerical weather forecast model NEMS (GFS).

Continental regions and regions in high elevation are typically simulated worse than maritime and low elevated regions. The errors in Europe and North America are typically lower than on the Southern Hemisphere. Air temperatures are typically worse simulated in Northern Hemispheric winter than in summertime.

Model performance of the 24h forecast of the MLM (top panel), the reanalysis model ERA5 (bottom left) and the numerical weather forecast model GFS (bottom right) for September – October 2018. 

Sensitivity to the forecast hours

The model performance typically decreases with increasing forecast hours. The accuracy of the 2 m air temperature by choosing the meteoblue learning multimodel (MLM) is within 1.2 K for the 24h forecast and within 2.0 K for the 6 day forecast. This implies that the 24h forecast of the MLM is as good as the 6 day forecast of the stand-alone numerical weather forecast models.   

MAE [K] as a function of the forecast hours for the MLM for single analysis days and the average (black). The 24h forecast error for MOS (blue) and the raw models (red) is additionally shown. 

A quick introduction to the meteoblue learning multimodel can be downloaded below: 

mlm_leaflet.pdf (6.96 MB)