Leveraging Deep Learning for Physical Model Bias of Global Air Quality Estimates
This work addresses air pollution modeling for environmental policy by providing incremental improvements in estimating ozone bias at urban scales.
The paper tackled the challenge of modeling surface ozone at urban scales by using a 2D Convolutional Neural Network to estimate biases in physics-based models, demonstrating improved capture of residuals compared to traditional methods in North America and Europe.
Air pollution is the world's largest environmental risk factor for human disease and premature death, resulting in more than 6 million permature deaths in 2019. Currently, there is still a challenge to model one of the most important air pollutants, surface ozone, particularly at scales relevant for human health impacts, with the drivers of global ozone trends at these scales largely unknown, limiting the practical use of physics-based models. We employ a 2D Convolutional Neural Network based architecture that estimate surface ozone MOMO-Chem model residuals, referred to as model bias. We demonstrate the potential of this technique in North America and Europe, highlighting its ability better to capture physical model residuals compared to a traditional machine learning method. We assess the impact of incorporating land use information from high-resolution satellite imagery to improve model estimates. Importantly, we discuss how our results can improve our scientific understanding of the factors impacting ozone bias at urban scales that can be used to improve environmental policy.