Data-driven aeolian dust emission scheme for climate modelling evaluated with EMAC 2.55.2

Aeolian dust has significant impacts on climate, public health, infrastructure and ecosystems. Assessing dust concentrations and the impacts ischallenging because the emissions depend on many environmental factors and can vary greatly with meteorological conditions. We present a data-drivenaeolian dust scheme that combines machine learning components and physical equations to predict atmospheric dust concentrations and quantify thesources. The numerical scheme was trained to reproduce dust aerosol optical depth retrievals by the Infrared Atmospheric Sounding Interferometer onboard the MetOp-A satellite. The input parameters included meteorological variables from the fifth-generation atmospheric reanalysis of the EuropeanCentre for Medium-Range Weather Forecasts. The trained dust scheme can be applied as an emission submodel to be used in climate and Earth systemmodels, which is reproducibly derived from observational data so that a priori assumptions and manual parameter tuning can be largely avoided. Wecompared the trained emission submodel to a state-of-the-art emission parameterisation, showing that it substantially improves the representation ofaeolian dust in the global atmospheric chemistry-climate model EMAC.

Automated summary

This article presents a data-driven aeolian dust model that combines machine learning and physical equations to predict atmospheric dust concentrations and quantify the sources. The model was trained using satellite observations and meteorological data, and it shows significant improvement in representing aeolian dust in a global atmospheric chemistry-climate model.