Traditional numerical weather forecasting relies upon a representation of the state of the atmosphere as accurate as possible at a given time. Initial status of each model forecast is based upon observations and upon background fields of parameters derived from previous executions of the forecast suite. This analysis is followed by time-step iterations using a simulation of physical laws and fluxes of heat, moisture and momentum. The ECMWF Integrated Forecast System (IFS) model is a complex but refined representation of the interactions in the model atmosphere. It is fully interactive with energy fluxes from land and sea surfaces. Computations are repeated at small simulated time-steps at a large number of grid points across the globe. Because of the complexity, it is relatively expensive in time and resources.
Artificial Intelligence weather forecasting models are radically different to the physics based techniques currently widely used. The aim is to define an empirical model that links observational data at one time with similar data for a short time later. The ECMWF Artificial Intelligence Model (AIFS) has been developed (or trained) using reanalysis fields as observations and then compared with reanalysis fields for the later time. Having found this empirical model it can be used iteratively to compute forecast fields at successive, fairly large, time steps into the future. There is no need to explicitly simulate the physics of the atmosphere; this is currently implicit in the reanalysis training data used. The user may not even know the impact of the local or large scale physical effects upon the process. Artificial Intelligence (AI) and Machine Learning (ML) are able to deal with massive amounts of data economically. There are major speed and cost benefits. Artificial Intelligence is destined to play a substantial role in meteorological forecasting in the future.
(FUG associated with Cy50r1)