Toward a Learnable Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI) based on the Multi-Head Self-Attention Algorithm

Abstract. Simulating aerosol chemistry and interactions (ACI) is crucial in climate and atmospheric model, yet conventional numerical schemes are computationally intensive due to stiff differential equations and iterative methods involved. While artificial intelligence (AI) have demonstrated the potential in accelerating photochemistry simulations, it has not been applied for simulating the full ACI processes which encompass not only chemical reactions but also other processes such as nucleation and coagulation. To bridge this gap, we develop a novel Artificial Intelligence Model for Aerosol Chemistry and Interactions (AIMACI), focusing initially on inorganic aerosols. Trained based on conventional numerical scheme, it has been validated both offline and online coupled into three dimensional numerical atmospheric model. Results demonstrate that AIMACI are not only comparable to those with the conventional numerical scheme in spatial distributions, temporal variations, and evolution of particle size distribution of 8 aerosol species including water content in aerosols, but also exhibits robust generalization ability, reliably simulating one month under different environmental conditions across four seasons despite being trained on limited data from merely 16 days. Remarkably, it exhibits a ~5× speedup with a single CPU and ~277× speedup with a single GPU compared to conventional numerical scheme. While global long-term simulations have not yet been implemented, AIMACI’s robust generalization capability, coupled with our easily plug-and-play solution, paves the way for its coupling into global climate models for further testing in near future. This advancement promises to enhance the precision and efficiency of atmospheric aerosol simulations in climate modeling.