AIFS-COMPO: A Global Data-Driven Atmospheric Composition Forecasting System

TL;DR

AIFS-COMPO is a transformer-based, data-driven global forecasting system for aerosols and reactive gases that offers comparable or better accuracy than traditional models with less computational cost.

Contribution

It introduces a novel AI-based atmospheric composition forecasting system that jointly models meteorology and chemistry using a transformer architecture, improving efficiency and forecast skill.

Findings

Achieves comparable or improved forecast skill for key atmospheric species.

Requires significantly less computational resources than traditional systems.

Enables forecasts beyond current operational horizons.

Abstract

We introduce AIFS-COMPO, a skilful medium-range data-driven global forecasting system for aerosols and reactive gases. Building on the ECMWF Artificial Intelligence Forecast System (AIFS), AIFS-COMPO employs a transformer-based encoder-processor-decoder architecture to jointly model meteorological and atmospheric composition variables. The model is trained on Copernicus Atmosphere Monitoring Service (CAMS) reanalysis, analysis, and forecast data to learn the coupled dynamics of weather, emissions, transport, and atmospheric chemistry. We evaluate AIFS-COMPO against a range of atmospheric composition observations and compare its performance with the operational CAMS global forecasting system IFS-COMPO. The results show that AIFS-COMPO achieves comparable or improved forecast skill for several key species while requiring only a fraction of the computational resources. Furthermore, the efficiency of the approach enables forecasts beyond the current operational horizon, demonstrating the potential of AI-based systems for fast and accurate global atmospheric composition prediction.