Third party models

meteoblue uses not only its proprietary weather models, but also various models of third party providers (which usually are national weather services). The models are combined - by applying modern machine learning techniques - to a multimodel forecast that reaches a much higher precision than any of the single models.
meteoblue accesses and distributes the following third party models:

Third-party domains:

Model           Region                   Resolution           Source                   
GFS22 Global 22 km 180 h (@ 3 h) NOAA NCEP
GFS40 Global 40 km 180 h (@ 3 h) NOAA NCEP
GFSENS05 Global 40 km 384 h (@ 6 h) NOAA NCEP
NAM5 North America 5 km 48 h NOAA NCEP
NAM12 North America 12 km 84 h (@ 3 h) NOAA NCEP
ICON7 Europe 7 km 120 h (@ 3 h) Deutscher Wetterdienst
ICON13 Global 13 km 180 h Deutscher Wetterdienst
COSMO2 Germany  2.5 km 27 h Deutscher Wetterdienst
GEM25 Global 25 km 168 h (@ 3 h) Environment Canada
AROME2 France 2 km 36 h METEO FRANCE
ARPEGE11 Europe 11 km 96 h METEO FRANCE
ARPEGE40 Global 40 km 96 h (@ 3 h) METEO FRANCE
HIRLAM11 Europe 11 km 48 h KNMI

DWD models (ICON13, ICON7, COSMO2)

meteoblue offers three different models from the German weather service (DWD): These are COSMO2 (covering Germany in 2 km resolution), ICON7 (covering Europe in 7 km resolution) and ICON13 (covering the whole world in 13 km resolution). 


The COSMO2 model is a model for Germany with a very high resolution of 2 km. More information can be found under the following links:


The ICON7 models cover Europe in 7 km. ICON13 presently is the global model with the highest resolution accessible to meteoblue. Thus, it is often used for our multimodels. A detailed specification of ICON13 can be seen in the table below:

Field Metadata
Title Icosahedral Nonhydrostatic Model
Short Title ICON13
Version 1
Theme weather, forecast, model, global
Period of Time 2017 to present
Frequency daily
Update timelag < 24 h
Time-resolution hourly
Spatial Type Irregular, unstructured icosahedral based triangular mesh
Spatial extend Global
Spatial resolution 13 km, every point represents a triangular area of 173 km2
Coordinate system WGS-84
Earth model WGS-84
Spatial reference system  
Publisher DWD (“Deutscher Wetterdienst”, German Weather Service)
Date First Published 2017
Date Obsolete -
Description The most important prognostic variables of ICON are air density and virtual potential temperature (which allows diagnosing the pressure), horizontal and vertical wind speed, humidity, cloud water, cloud ice, rain and snow. These variables are calculated for all grid cells on 90 terrain-following model levels extending from the surface to a height of 75 km, yielding a total of about 265 million grid points. Over land, additional prognostic equations are solved for soil temperature and soil water content, for 7 soil levels. If snow cover is present, snow water equivalent and snow density are predicted in addition. Sea surface temperature over ice-free ocean surfaces is analyzed once per day from observations and is kept constant during the ICON forecast. For ice-covered parts of the oceans, the sea ice fraction is analyzed once per day from observations, whereas the ice thickness and the ice surface temperature are predicted with a simple sea-ice model. Besides horizontal and vertical transport processes (so-called adiabatic processes) in the atmosphere, diabatic processes like radiation, turbulence, formation of clouds, and precipitation play a major role for NWP. Describing these processes taking place on much smaller horizontal scales than the model mesh size is the task of the physics parameterizations.
Detailed specification
Homepage URL
Security Classification public
Access Level

open data - may be re-used without any restrictions provided that the source reference is indicated, as laid down in the GeoNutzV ordinance ("Verordnung zur Festlegung der Nutzungsbestimmungen für die Bereitstellung von Geodaten des Bundes = Ordinance to Determine the Conditions for Use for the Provision of Spatial Data of the Federation). As to the layout of source references, the DWD requests adherence to the following guidelines (cf. § 7 of the DWD Law and § 3 of the GeoNutzV ordinance):

The obligation to indicate the enclosed source references shall apply to any spatial data and other services of the DWD that are used without alteration. Source references must also be indicated even if extracts or excerpts are used or if the data format has been changed. Displaying the DWD logo shall be considered as meeting the requirement of source reference in meaning of the GeoNutzV ordinance.

In the event of more advanced alteration, processing, new design or other adaptation, DWD at least expects to be mentioned in a central list of references or in an imprint.

Indication of alteration according to the GeoNutzV ordinance may read as follows: "Data basis: Deutscher Wetterdienst, gridded data reproduced graphically"; "Data basis: Deutscher Wetterdienst, averaged over individual values", or "Data basis: Deutscher Wetterdienst, own elements added".

If a service provided by the DWD is used in a way that does not comply with its intended purpose, the enclosed source references have to be deleted. This shall especially apply to weather warnings for which there is no guarantee that they are delivered to all users at all times completely and without delay.


Other third-party models

There are more third-party weather models, that offer high resolution data for a specific area or an additional global alternative, available. In the following, their description is kept short, as it is repetitive or of minor importance.

NOAA models (NAM5, NAM12, GFS22, GFS40)

NAM is a high-resolution model for North America with a resolution of 5 km (NAM5) and 12 km (NAM12). It is run by NOAA and therefore it is using the same algorithms as the meteoblue NEMS model domains. When high resolution data for North America is needed, this should be your first choice.

GFS is the global forecasting system of the U.S. weather service NOAA. It covers the whole world in 22 km (GFS22) and 40 km (GFS40) resolution.

Météo-France models (MFFR, MFEU, MFGLOBAL)

MF is the abbreviation for Météo-France that is the French national weather service. They run the ARPEGE model for the whole world in 40 km resolution (ARPEGE40 = MFGLOBAL) and for the European continent in 11 km resolution (ARPEGE11 = MFEU). Furthermore, Météo-France provides a high-resolution model with 2 km grid size for France (AROME2 = MFFR). More information about the ARPEGE models can be found on the website of Météo-France:

KNMI model (HIREU)

HIREU is the abbreviation for the HIRLAM model, that is covering Europe in 12 km resolution and provided by the Dutch national weather service KNMI.

Canada Environment model (GEM)

GEM is a global model run by the Canadian National weather service in 25 km resolution.