Toward stable, general machine-learned models of the atmospheric chemical system

Abstract

Atmospheric chemistry models—used as components in models that simulate air pollution and climate change—are computationally expensive. Previous studies have shown that machine-learned atmospheric chemical solvers can be orders of magnitude faster than traditional integration methods but tend to suffer from numerical instability. Here, we present a modeling framework that reduces error accumulation compared to previous work while maintaining computational efficiency. Our approach is novel in that it: 1) uses a recurrent training regime that results in extended (>1 week) simulations without runaway error accumulation, and 2) can reversibly compress the number of modeled chemical species by >80% without further decreasing accuracy. We observe a ~260× reduction in computation time (~1900× when run on specialized hardware) compared to the traditional solver. We use random initial conditions in training to promote general applicability across a wide range of atmospheric conditions. For ozone (with an initial concentration range of 0–70 ppb), our model predictions over a 24-hour simulation period match those of the traditional solvers with median error of 2.7 ppb and less than 19 ppb error across 99% of simulations initialized with random noise. Error can be significantly higher in the remaining 1% of simulations, which include among the most extreme concentration fluctuations simulated by the reference model. Results are similar for total particulate matter (median error of 16 ug/m3 and <32 ug/m3 across 99% of simulations with concentrations ranging from 0-150 ug/m3). Finally, we discuss practical implications of our choice of modeling framework and next steps for improving performance. The machine learning models described here are not yet suitable replacements for traditional chemistry solvers but represent a step toward that goal.

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

“…Figure 4 shows the error statistics for surface ozone when using the different ML solvers. None of the ML solvers show runaway error growth, unlike in previous studies (Keller & Evans, 2019; Kelp et al., 2020), which we attribute to the relatively low dimensionality of the Super‐Fast mechanism boosted by the use of the encoder/decoder to further reduce dimensionality.…”

“…Kelp et al. (2020) found that a cost function that equally prioritizes all species is significantly less accurate than one that is specialized toward a single species of interest. Here, we create 12 separate ML solvers prioritizing each of the output species individually, all with the same 20 input variables listed from above.…”

“…Kelp et al. (2020) found that recursive training of 1‐hr chemical time steps over 24‐hr time horizons was critical in their box model application to capture slow chemical modes and prevent error growth. We implemented this recursive training here by mimicking the effects of operator splitting between chemistry and other operators in GEOS‐Chem.…”

“…Success in applying ML solvers to box models, such as in Kelp et al. (2020), may not translate to a global CTM.…”

“…Kelp et al. (2020) trained a neural network integrator in a chemical box model, including an encoder/decoder (Lusch et al., 2018) to decrease dimensionality, and a recursive feedback loop over 24‐hr integration time to control error growth. They found that they could compress the 101‐species dimension of their mechanism into fewer than 20 features without significant error penalty and that they could avoid error growth over a 1‐week integration time.…”