Ensemble forecasting (AIFS-ENS) brings an ability to quantify uncertainty and to identify possible extremes in the evolution.  An ensemble of the AI forecast procedure can be executed because AI forecasting is rapid and cheap to run. At present AIFS-ENS has 50 members and is run at six hour intervals.   However there is potential for much larger and/or more frequent  ensembles.  Essentially each ensemble member is similar to AIFS single.

Observations are assimilated using 4D-var to IFS grid point values over the whole globe with resolution about 9km.   The starting point for the ensemble control member is this IFS data assimilation.   The initial conditions for the AI ensemble members are the IFS Ensemble Data Assimilation recentered (EDA) with singular vectors as with the perturbations in the IFS ensemble.   However, the perturbations applied to each ensemble member are derived differently, and have different values to those applied to the physical models.  Strictly, there is no unperturbed ensemble control member as appears in the IFS ensemble, because all ensemble members, including the control member, are generated probabilistically.  So, in that sense, they are statistically equivalent.

Currently the AI procedures use grid points at a lower resolution about 0.25 of a degree (~25km).  The IFS analysed data is "encoded" to values at the AI grid point.  These data are then fed to the AI procedure which uses the algorithms derived by the ML trained by minimising CRPS.   The algorithm is not complicated and consequently has fast execution allowing a complete global forecast to be made much faster than IFS and other physics-based models.  Forecasts are made in six hour time steps and output from one time step is used as the input for the next step.  Currently the AI forecasts use 12 repeated six hour time steps to extend the forecast to T+72.   Intermediate forecast data is only available at the simulated six hour time steps; no information is available at smaller intervals than six hours.

There is only one set of algorithms produced by the ML process for the ensemble and this is used throughout the forecast and for all ensemble members.  There is not a different set of algorithms for each ensemble member.  The spread in the ensemble members is generated by the difference in the initial conditions (perturbations) and the white noise injected in the model.

The limitation in horizontal and vertical resolutions mean that:

• Interpretation is necessary before using any forecast product.
• it is only possible to derive a few post-processed products (e.g. precipitation and convective precipitation).

Making a forecast with AI is very efficient.  It requires only a single Graphics Processing Unit (GPU), takes less than a minute to run, and consumes a tiny fraction of the energy required for an IFS forecast.  This brings the prospect of more frequent and/or quite large ensembles of AI forecasts.

Points to consider when using AIFS output

In addition to points for consideration outlined in the AIFS single section

AIFS-ENS forecasts:

• High-quality ensemble forecasts that outperform ECMWF’s traditional physics-based ensemble system in medium-range forecasts on most accuracy and reliability scores.
• Very fast and economical to produce a forecast sequence.
• The principle for construction of meteograms and charts is very similar to that used by IFS ensembles.
• Individual ensemble members do not exhibit the smoothing seen in AIFS-SIngle and have similar levels of forecast activity to IFS.  This is because the CRPS loss function does not encourage smoothing.
• AIFS-ENS control verifies better than AIFS-ENS members (possibly with 6-12h gain).
• Are currently little bit over-dispersive.
• Very small totals can appear in the precipitation fields far too often.  This will be fixed in upcoming cycles.
• Physical consistency in the output is unlikely to be as good as with IFS.  This is being investigated.
• Cloud fields appear very "blocky" after T+0.  This is being investigated.

Practical use of AIFS output

Forecasters should consider:

• When a variable level is nominally underground - e.g. for mean sea level pressure in very mountainous areas, or 1000hPa or even 850hPa temperature in very mountainous areas, extreme unrealistic values can develop in the course of a forecast, in some or all ensemble members.  In turn this can manifest as extreme ensemble spread in that particular variable. One problem area is the Andes, but there are others too. These 'glitches' do not always happen, and their onset is not always at the same lead time (e.g. Fig2).
• Some extreme weather events appear less intense than IFS ensemble (e.g. windstorms).
• Temperature extremes are more consistently handled, generally beating classical NWP forecasts.
• The AIFS-ENS contrail has a slight advantage over other AIFS-ENS members because it starts from unperturbed initial conditions.  However, because of the ML training it contains model uncertainty.  It is not the same as IFS ensemble control (Ex-HRES).
• Extremes are better identified than with AIFS-Single.

Fig1: An example of an AIFS-ENS meteogram for Warsaw DT00UTC 26 Jun 2025.  The plots are in standard box and whisker form and includes the AIFS-ENS control.  The AIFS single is shown as a continuous blue line. Note AIFS single departs outside the AIFS-ENS box and whisker in places.  This may be due to the difference in the ML derivation of the algorithms for AIFS single and AIFS-ENS.

FIG2: An example of AIFS-ENS chart output from AIFS-ENS mean and spread VT12UTC 30 Jun 2025, DT12UTC 24 Jun 2025.  Large uncertainty over the southern Andes as high as 8-14C locally. This can be due to 1000hPa contour lying below the model surface in mountainous areas.