An Online-Learned Neural Network Chemical Solver for Stable Long-Term Global Simulations of Atmospheric Chemistry

A major computational barrier in global modeling of atmospheric chemistry is the numerical integration of the coupled kinetic equations describing the chemical mechanism. Machine-learned (ML) solvers can offer order of magnitude speedup relative to conventional implicit solvers but past implementations have suffered from fast error growth and only run for short simulation times (<1 month). A successful ML solver for global models must avoid error growth over yearlong simulations and allow for reinitialization of the chemical trajectory by transport at every time step. Here, we explore the capability of a neural network solver equipped with an autoencoder to achieve stable full-year simulations of tropospheric oxidant chemistry in the global 3-D Goddard Earth Observing System (GEOS)-Chem model, replacing its standard mechanism (228 species) by the Super-Fast mechanism (12 species) to avoid the curse of dimensionality. We find that online training of the ML solver within GEOS-Chem is important for accuracy, whereas offline training from archived GEOS-Chem inputs/outputs produces large errors. After online training, we achieve stable 1-year simulations with five-fold speedup compared to the standard implicit Rosenbrock solver with global tropospheric normalized mean biases of −0.3% for ozone, 1% for hydrogen oxide radicals, and −5% for nitrogen oxides. The ML solver captures the diurnal and synoptic variability of surface ozone at polluted and clean sites. There are however large regional biases for ozone and NO_x under remote conditions where chemical aging leads to error accumulation. These regional biases remain a major limitation for practical application, and ML emulation would be more difficult in a more complex mechanism.