Uncertainty Quantification in Reduced-Order Gas-Phase Atmospheric Chemistry Modeling using Ensemble SINDy

TL;DR

This paper introduces a probabilistic surrogate modeling approach combining PCA and Ensemble SINDy to simplify gas-phase atmospheric chemistry models and quantify the uncertainty introduced, demonstrated on a photochemical ozone formation model.

Contribution

The paper presents a novel probabilistic surrogate modeling method that automatically simplifies chemical mechanisms and quantifies uncertainty, improving accuracy over deterministic models.

Findings

High correlation between predicted uncertainty and actual model error (R-squared 0.96-0.98)

Probabilistic method improves prediction accuracy by ~50-60%

Ozone RMSE is 15.1% of its RMS concentration

Abstract

Uncertainty quantification during atmospheric chemistry modeling is computationally expensive as it typically requires a large number of simulations using complex models. As large-scale modeling is typically performed with simplified chemical mechanisms for computational tractability, we describe a probabilistic surrogate modeling method using principal components analysis (PCA) and Ensemble Sparse Identification of Nonlinear Dynamics (E-SINDy) to both automatically simplify a gas-phase chemistry mechanism and to quantify the uncertainty introduced when doing so. We demonstrate the application of this method on a small photochemical box model for ozone formation. With 100 ensemble members, the calibration $R$-squared value is 0.96 among the three latent species on average and 0.98 for ozone, demonstrating that predicted model uncertainty aligns well with actual model error. In addition to uncertainty quantification, this probabilistic method also improves accuracy as compared to an equivalent deterministic version, by $\sim$60% for the ensemble prediction mean or $\sim$50% for deterministic prediction by the best-performing single ensemble member. Overall, the ozone testing root mean square error (RMSE) is 15.1% of its root mean square (RMS) concentration. Although our probabilistic ensemble simulation ends up being slower than the reference model it emulates, we expect that use of a more complex reference model in future work will result in additional opportunities for acceleration. Versions of this approach applied to full-scale chemical mechanisms may result in improved uncertainty quantification in models of atmospheric composition, leading to enhanced atmospheric understanding and improved support for air quality control and regulation.