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

This is a Preprint and has not been peer reviewed. The published version of this Preprint is available: https://doi.org/10.1029/2021MS002926. This is version 1 of this Preprint.

Downloads

Download Preprint

Authors

Makoto Michael Kelp, Daniel J. Jacob, Haipeng Lin, Melissa P Sulprizio

Abstract

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 year-long simulations and allow for re-initialization 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 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 essential 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 NOx 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.

DOI

https://doi.org/10.31223/X52K7J

Subjects

Engineering, Physical Sciences and Mathematics

Keywords

machine learning, atmospheric chemical mechanism, chemical transport modeling, model emulation, neural network chemical solver, machine learning chemical solver

Dates

Published: 2021-12-02 11:24

License

CC BY Attribution 4.0 International

Add a Comment

You must log in to post a comment.


Comments

There are no comments or no comments have been made public for this article.