Toward Stable, General Machine-Learned Models of the Atmospheric Chemical System

Atmospheric chemistry models—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 exponential error accumulation and (2) can reversibly compress the number of modeled chemical species by >80% without further decreasing accuracy. We observe an ~260× speedup (~1,900× with 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 (concentrations ranging from 0–70 ppb), our model predictions over a 24-hr simulation period match those of the reference solver with median error of 2.7 and <19 ppb error across 99% of simulations initialized with random noise. Error can be significantly higher in the remaining 1% of simulations, which include extreme concentration fluctuations simulated by the reference model. Results are similar for total particulate matter (median error of 16 and <32 μg/m³ across 99% of simulations with concentrations ranging from 0–150 μg/m³). Finally, we discuss practical implications of our modeling framework and next steps for improvements. The machine learning models described here are not yet replacements for traditional chemistry solvers but represent a step toward that goal.