AIFS -- ECMWF's data-driven forecasting system

TL;DR

AIFS is a novel data-driven weather forecasting system using graph neural networks and transformers, developed by ECMWF, that provides accurate medium-range forecasts and complements traditional NWP models.

Contribution

Introduces AIFS, a modular, high-resolution, data-driven forecasting system based on GNNs and transformers, enhancing ECMWF's weather prediction capabilities.

Findings

AIFS achieves high skill in forecasting upper-air and surface variables.

AIFS accurately predicts tropical cyclone tracks.

AIFS forecasts are comparable to ECMWF's NWP analyses.

Abstract

Machine learning-based weather forecasting models have quickly emerged as a promising methodology for accurate medium-range global weather forecasting. Here, we introduce the Artificial Intelligence Forecasting System (AIFS), a data driven forecast model developed by the European Centre for Medium-Range Weather Forecasts (ECMWF). AIFS is based on a graph neural network (GNN) encoder and decoder, and a sliding window transformer processor, and is trained on ECMWF's ERA5 re-analysis and ECMWF's operational numerical weather prediction (NWP) analyses. It has a flexible and modular design and supports several levels of parallelism to enable training on high-resolution input data. AIFS forecast skill is assessed by comparing its forecasts to NWP analyses and direct observational data. We show that AIFS produces highly skilled forecasts for upper-air variables, surface weather parameters and tropical cyclone tracks. AIFS is run four times daily alongside ECMWF's physics-based NWP model and forecasts are available to the public under ECMWF's open data policy.