Abstract

Global models of atmospheric chemistry are computationally expensive. A bottleneck is the chemical solver that integrates the large-dimensional coupled systems of kinetic equations describing the chemical mechanism. Machine learning (ML) could be transformative for reducing the cost of an atmospheric chemistry simulation by replacing the chemical solver with a faster emulator. However, past work found that ML chemical solvers experience rapid error growth and become unstable over time. In this talk, I will present the culmination of several years of research focused on developing ML methods for atmospheric chemistry simulations. We started by establishing stable emulation in 0-D box models and then progressed to achieving for the first time a stable full-year global chemical transport model (CTM) simulation of atmospheric chemistry using ML solvers. The ML solver gains five-fold speedup in computational performance over the reference Fortran solver during a CTM simulation. We show that online training of the ML solver synchronously with the CTM simulation produces considerably more stable results than offline training from a static data set of simulation results. Although our work represents an important step for using ML solvers in global atmospheric chemistry models, more work is needed to extend it to large chemical mechanisms and to reduce errors during long-term chemical aging.