Use of Machine Learning to Reduce Uncertainties in Particle Number Concentration and Aerosol Indirect Radiative Forcing Predicted by Climate Models

Abstract

AbstractThe radiative forcing of anthropogenic aerosols associated with aerosol‐cloud interactions (RFaci) remains the largest source of uncertainty in climate prediction. The calculation of particle number concentration (PNC), one of the critical parameters affecting RFaci, is generally simplified in climate models. Here we employ outputs from long‐term (30‐year) simulations of a global size‐resolved (sectional) aerosol microphysics model and a machine‐learning tool to develop a Random Forest Regression Model (RFRM) for PNC. We have implemented the PNC RFRM in GISS‐ModelE2.1 with a mass‐based One‐Moment Aerosol module, which is one of CMIP6 models. Compared to the default setting, the GISS‐ModelE2.1 simulation based on RFRM reduces the changes of cloud droplet number concentration associated with anthropogenic emissions, and decreases the RFaci from −1.46 to −1.11 W·m−2. This work highlights a promising approach based on machine learning to reduce uncertainties of climate models in predicting PNC and RFaci without compromising their computing efficiency.