Uncertainty Quantification for Surface Ozone Emulators using Deep Learning

TL;DR

This paper develops an uncertainty-aware deep learning model to predict and quantify biases in surface ozone simulations, aiding regional air quality assessment and policy decision-making.

Contribution

It introduces a Bayesian U-Net architecture for uncertainty quantification in surface ozone bias prediction, incorporating land-use data for improved regional modeling.

Findings

Effective bias prediction in North America and Europe

Comparison of Bayesian and quantile regression UQ methods

Identification of optimal ground stations for bias correction

Abstract

Air pollution is a global hazard, and as of 2023, 94\% of the world's population is exposed to unsafe pollution levels. Surface Ozone (O3), an important pollutant, and the drivers of its trends are difficult to model, and traditional physics-based models fall short in their practical use for scales relevant to human-health impacts. Deep Learning-based emulators have shown promise in capturing complex climate patterns, but overall lack the interpretability necessary to support critical decision making for policy changes and public health measures. We implement an uncertainty-aware U-Net architecture to predict the Multi-mOdel Multi-cOnstituent Chemical data assimilation (MOMO-Chem) model's surface ozone residuals (bias) using Bayesian and quantile regression methods. We demonstrate the capability of our techniques in regional estimation of bias in North America and Europe for June 2019. We highlight the uncertainty quantification (UQ) scores between our two UQ methodologies and discern which ground stations are optimal and sub-optimal candidates for MOMO-Chem bias correction, and evaluate the impact of land-use information in surface ozone residual modeling.