ECMWF AIFS ENS forecast
| Spatial domain | Global |
| Spatial resolution | 0.25 degrees (~20km) |
| Time domain | Forecasts initialized 2025-07-02 00:00:00 UTC to Present |
| Time resolution | Forecasts initialized every 6 hours |
| Forecast domain | Forecast lead time 0-360 hours (0-15 days) ahead |
| Forecast resolution | 6 hourly |
STAC (browse) · validation report
The Artificial Intelligence Forecasting System (AIFS) is a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS ENS is the ensemble configuration of AIFS, containing 51 ensemble members. AIFS is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses.
This dataset is an archive of past and present ECMWF AIFS ENS forecasts. Forecasts are identified by an initialization time (init_time) denoting the start time of the model run, as well as by the ensemble_member. Each forecast steps forward in time along the lead_time dimension.
Examples
|
Quickstart (Github) |
|
Quickstart (Colab) |
import dynamical_catalog # dynamical-catalog>=0.7.0
ds = dynamical_catalog.open("ecmwf-aifs-ens-forecast")
ds["temperature_2m"].sel(init_time="2025-08-01T00", latitude=0, longitude=0).max().compute()Dimensions
| min | max | units | |
|---|---|---|---|
| ensemble_member | 0 | 50 | 1 |
| init_time | 2025-07-02T00:00:00Z | Present | seconds since 1970-01-01 |
| latitude | -90 | 90 | degree_north |
| lead_time | 0 | 1296000 | seconds |
| longitude | -180 | 179.75 | degree_east |
Variables
Access a variable by its name (the bold identifier, e.g. ds["dew_point_temperature_2m"]).
Dimensions: init_time × lead_time × ensemble_member × latitude × longitude
| variable | units |
|---|---|
dew_point_temperature_2m
2 metre dewpoint temperature (2d)
|
degree_Celsius |
downward_long_wave_radiation_flux_surface
Surface downward long-wave radiation flux (sdlwrf)
|
W m-2 |
downward_short_wave_radiation_flux_surface
Surface downward short-wave radiation flux (sdswrf)
|
W m-2 |
geopotential_height_500hpa
Geopotential height (gh)
|
m |
geopotential_height_850hpa
Geopotential height (gh)
|
m |
geopotential_height_925hpa
Geopotential height (gh)
|
m |
precipitation_surface
Precipitation rate (prate)Average precipitation rate since the previous forecast step. Units equivalent to mm/s.
|
kg m-2 s-1 |
pressure_reduced_to_mean_sea_level
Pressure reduced to MSL (prmsl)
|
Pa |
pressure_surface
Surface pressure (sp)
|
Pa |
temperature_2m
2 metre temperature (2t)
|
degree_Celsius |
temperature_850hpa
Temperature (t)
|
degree_Celsius |
temperature_925hpa
Temperature (t)
|
degree_Celsius |
total_cloud_cover_atmosphere
Total cloud cover (tcc)
|
percent |
wind_u_100m
100 metre U wind component (100u)
|
m s-1 |
wind_u_10m
10 metre U wind component (10u)
|
m s-1 |
wind_v_100m
100 metre V wind component (100v)
|
m s-1 |
wind_v_10m
10 metre V wind component (10v)
|
m s-1 |
Details
License
Dataset licensed under CC BY 4.0 and ECMWF Terms of Use.
Attribution and citation
ECMWF AIFS ENS forecast data processed by dynamical.org from ECMWF Open Data.
Or ECMWF AIFS ENS from dynamical.org.
Source
The source grib files this archive is constructed from are provided by ECMWF Open Data and accessed from the AWS Open Data Registry.
ECMWF does not provide user support for the free & open datasets. Users should refer to the public User Forum for any questions related to the source material.
Model updates
AIFS ENS is updated annually. Find details of recent and upcoming changes to the forecasting system on the ECMWF website.
Storage
Storage for this dataset is generously provided by AWS Open Data.
Chunks & shards
This dataset is stored in Zarr format, which splits each variable into a grid of chunks — the smallest unit read from storage. Chunks are grouped into larger shards (the objects actually written to storage), which keeps the object count manageable for long-archive datasets. When possible, aligning your reads with this dataset's chunk grid can significantly improve data access speed.
The element count and coordinate span of this dataset:
| dimension | chunk | shard |
|---|---|---|
| init_time | 1 (6 hours) | 1 (6 hours) |
| lead_time | 61 (366 hours) | 61 (366 hours) |
| ensemble_member | 51 | 51 |
| latitude | 32 (8°) | 384 (96°) |
| longitude | 32 (8°) | 288 (72°) |
| uncompressed | 12.2 MiB | 1.3 GiB |
Compression
The data values in this dataset have been rounded in their binary floating point representation to improve compression. See Klöwer et al. 2021 for more information on this approach. The exact number of rounded bits can be found in our reformatting code.