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

The radiative forcing of anthropogenic aerosols associated with aerosol-cloud interactions (RF_aci) remains the largest source of uncertainty in climate prediction. The calculation of particle number concentration (PNC), one of the critical parameters affecting RF_aci, 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 RF_aci 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 RF_aci without compromising their computing efficiency.