Machine Learning Uncovers Aerosol Size Information From Chemistry and Meteorology to Quantify Potential Cloud‐Forming Particles
Arshad Arjunan Nair, Fangqun Yu, Pedro Campuzano‐Jost, Paul J. DeMott, Ezra J. T. Levin, J. L. Jiménez, Jeff Peischl, I. B. Pollack, Carley D. Fredrickson, A. J. Beyersdorf, Benjamin A. Nault, Minsu Park, Seong Soo Yum, Brett B. Palm, Lu Xu, Ilann Bourgeois, B. E. Anderson, Athanasios Nenes, Luke D. Ziemba, Richard H. Moore, Taehyoung Lee, Taehyun Park, Chelsea R. Thompson, F. Flocke, L. G. Huey, Michelle Kim, Qiaoyun Peng
Abstract
Abstract Cloud condensation nuclei (CCN) are mediators of aerosol‐cloud interactions, which contribute to the largest uncertainty in climate change prediction. Here, we present a machine learning (ML)/artificial intelligence (AI) model that quantifies CCN from model‐simulated aerosol composition, atmospheric trace gas, and meteorological variables. Comprehensive multi‐campaign airborne measurements, covering varied physicochemical regimes in the troposphere, confirm the validity of and help probe the inner workings of this ML model: revealing for the first time that different ranges of atmospheric aerosol composition and mass correspond to distinct aerosol number size distributions. ML extracts this information, important for accurate quantification of CCN, additionally from both chemistry and meteorology. This can provide a physicochemically explainable, computationally efficient, robust ML pathway in global climate models that only resolve aerosol composition; potentially mitigating the uncertainty of effective radiative forcing due to aerosol‐cloud interactions (ERF aci ) and improving confidence in assessment of anthropogenic contributions and climate change projections.