On Tuesday 1 July 2025, a first version of the probabilistic model of the Artificial Intelligence Forecasting System (AIFS) was released and is now supported operationally. The model version is AIFS ENS v1, which replaced the experimental model AIFS ENS DIFF.
AIFS ENS data has undergone internal analysis, demonstrating significant skill and highlighting its transformative impact. We encourage users to read this webpage, which outlines outstanding known issues, before considering using the data for operational use/integration in applications. We would welcome any feedback.
Please note that this release does not impact users of the IFS and AIFS Single models in any way. The current operational version of IFS was successfully implemented on 12 November 2024. The current operational version of AIFS Single was successfully implemented on 25 February 2025.
If you missed the webinar introducing the AIFS ENS model on you can watch the recording at the bottom of this page.
Input and output parameters
The table below shows the parameters that are input and output by AIFS ENS v1.
Control and perturbed forecast products
Field | Level type | Input/Output |
---|---|---|
Geopotential (z) | Pressure level: 50, 100, 150, 200, 250, 300, 400, 500, 600, 700, 850, 925, 1000 | Both ("Prognostic") |
2 metre dewpoint temperature (2d) 2 metre temperature (2t) 10 metre U wind component (10u) 10 metre V wind component (10v) Mean sea level pressure (msl) Skin temperature (skt) Surface pressure (sp) Total column water (tcw) | Surface | Both ("Prognostic") |
Soil temperature (sot), at solid depth 1 and 2 | Soil layer level | Both ("Prognostic") |
Total precipitation (tp) | Surface | Output ("Diagnostic") |
Standard deviation of sub-gridscale orography (sdor) Land-sea mask (lsm), orography, insolation, latitude/longitude, time of day/day of year | Surface | Input ("Forcings") |
Post-processed products
Field | Statistic | Level type |
---|---|---|
2 metre temperature 10 metre wind speed 100 metre wind speed Mean sea level pressure | Ensemble mean and standard deviation | Surface |
Geopotential, temperature, wind speed | Ensemble mean and standard deviation | Pressure level: 250, 300, 500, 850, 1000 |
2 metre temperature less than 273.15 K Total precipitation of less than 0.1 mm Total precipitation of at least 1 mm/5 mm/10 mm/20 mm/25 mm/50 mm/100 mm Total precipitation rate less than 1 mm/day Total precipitation rate of at least 3 mm/day Total precipitation rate of at least 5 mm/day 10 metre Wind speed of at least 10 m/s and 15 m/s* | Probabilities | Surface |
*Due to technical issue these 2 parameters will be available one or two weeks after the implementation
More detailed information about the post processed parameters in AIFS ENS v1 is provided in the table below.
Technical content
GRIB encoding
The GRIB model generating process identification number for AIFS Single v1 will be changed as follows:
ecCodes key | Component | Model identifier | |
---|---|---|---|
v1 | |||
generatingProcessIdentifier | Atmospheric model | 1 |
Output data from AIFS ENS v1 are provided in GRIB 2 format. Users can confirm the grib edition with the ecCodes command grib_get:
|
Software
To handle the data of AIFS ENS v1, we recommend use of the ECMWF software packages:
ecCodes 2.40.0
CodesUI 1.8.0 (minimum version 1.7.3)
Magics 4.15.4 (minimum version 4.13.0)
Metview 5.22.1
ecmwf-opendata 0.3.22 (model
keyword should explicitly be provided as aifs-ens
)
On the ATOS HPC these versions correspond to ecmwf-toolbox/2025.02.0.0.
Older versions of eccodes and the ecmwf-toolbox still work in terms of reading the data from AIFS ENS v1.
Availability of AIFS ENS v1 test data
Data in ecCharts and Open Charts
Please note that test data were not available via ecCharts or Open Charts.
In the Open Charts they are available through the following link.
In the ecCharts, search 'aifs ens' from the list of available layers.
Test data in MARS
Test data was available from 01 December 2024 12z run in the MARS archive with experiment version 103. Use the MARS keywords expver=103, class=ai and model=aifs-ens to retrieve this data. Please note that only users registered with access to MARS are able to access these test datasets. The test data must not be used for operational forecasting. Please report any problems you find with this data via the ECMWF Support Portal.
Test data in dissemination
Test data are now available!
Dissemination file naming convention
The test data file names end with 'X0103', corresponding to the experiment version of the test data (see File naming convention and format for real-time data#Naming-AIFSviadissemination for further details about the AIFS file naming convention).
Dissemination requests
A new MARS keyword "model" is required in dissemination requests with class=ai. The model keyword identifies the AI model that was used to produce the forecast. For AIFS ENS v1, the model keyword is "aifs-ens".
To support this update, we have added Product Requirements Editor (PREd) snippets, available in your feeds requirements editor page, to help users include AIFS ENS data in their dissemination feeds. Member and Cooperating State users, and users with Gold and Silver service packs, were able to add AIFS ENS data in the PREd from 23 June 2025 until 30 June 2025 pre-operational and 1 July 2025 00 UTC run onwards operationally.
Test data on ECMWF's Open Data platform
Test data were available from 20 June 2025 06z run via the Open Data platform
AIFS ENS data is now available in the following path: e.g., https://data.ecmwf.int/forecasts/YYYYMMDD/XXz/aifs-ens/0p25/enfo/
Where YYYY is the year, MM is the month, DD is the day and XX is the base time.
Resources
Webinar
Webinar introducing AIFS-ENS was held on . If you missed it you can watch the recording.
References
- AIFS-CRPS: Ensemble forecasting using a model trained with a loss function based on the continuous ranked probability score, Lang, S., Alexe, M., Clare, M., Roberts, C., Adewoyin, R., Ben Bouallègue, Z., Chantry, M., Dramsch, J., Dueben, P., Hahner, S., Maciel, P., Prieto-Nemesio, A., O’Brien, C., Pinault, F., Polster, J., Raoult, B., Tietsche, S., Leutbecher, M.
- A new tool to understand changes in ensemble forecast skill, Leutbecher, M., Haiden, T., ECMWF Newsletter No 166 - Winter 2021