Datasets

This chart provides information on the verification of forecasts of Accumulated Cyclone Energy ...

The ECMWF seasonal forecasts (SEAS5) are produced every month with a 51-member ensemble at a ...

ECMWF is now running a series of data-driven forecasts as part of its experimental suite. These machine-learning based models are very fast, and they produce a 10-day forecast with 6-hourly time steps in approximately one minute. The outputs are available in graphical form.

Currently, three of these models are available:

The diagram shows mean errors in position and intensity of tropical cyclones for HRES and ENS. ...

The ECMWF seasonal forecasts (SEAS5) are produced every month with a 51-member ensemble at a ...

These charts provide information on current Tropical Cyclone activity. Select the ...

This chart shows the potential for tropical cyclone activity at different time ranges during the ...

The ECMWF seasonal forecasts (SEAS5) are produced every month with a 51-member ensemble at a ...

The ECMWF seasonal forecasts (SEAS5) are produced every month with a 51-member ensemble at a ...

The charts show mean frequency and accumulated cyclone energy of tropical storm activity. ...

This chart provides information on the verification of forecasts of the expected number of ...

The charts show the evolution of existing and potential tropical cyclone activity. ...

ECMWF is now running its own Artificial Intelligence Forecasting System (AIFS). The AIFS consists of a deterministic model and an ensemble model. The deterministic model has been running operationally since 25 February 2025; further details can be found on the dedicated Implementation of AIFS Single v1 page.

The ECMWF seasonal forecasts (SEAS5) are produced every month with a 51-member ensemble at a ...

This chart provides information on the verification of forecasts of the number of tropical ...