Deep Learning to Evaluate US NOx Emissions Using Surface Ozone Predictions. Issue 4 (11th February 2022)

• Record Type: Journal Article
• Authors: He, Tai‐Long; Jones, Dylan B. A.; Miyazaki, Kazuyuki; Huang, Binxuan; Liu, Yuyang; Jiang, Zhe; White, E. Charlie; Worden, Helen M.; Worden, John R.
• Is Part Of: Journal of geophysical research. Volume 127:Issue 4(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-02-11
• Subjects: Atmospheric physics -- Periodicals; Geophysics -- Periodicals; 551.5
• DOI: 10.1029/2021JD035597
• Languages: English
• ISSNs: 2169-897X

Abstract

Abstract: Emissions of nitrogen oxides (NOx = NO + NO2 ) in the United States have declined significantly during the past three decades. However, satellite observations since 2009 indicate total column NO2 is no longer declining even as bottom‐up inventories suggest continued decline in emissions. Multiple explanations have been proposed for this discrepancy including (a) the increasing relative importance of nonurban NOx to total column NO2, (b) differences between background and urban NOx lifetimes, and (c) that the actual NOx emissions are declining more slowly after 2009. Here, we use a deep learning model trained by NOx emissions and surface observations of ozone to assess consistency between the reported NOx trends between 2005 and 2014 and observations of surface ozone. We find that the satellite‐derived trends best reproduce ozone in low NOx emission (background) regions. The 2010–2014 trend from older satellite‐derived emission estimates produced at low spatial resolution results in the largest bias in surface ozone in regions with high NOx emissions, reflecting the blending of urban and background NOx in these low‐resolution top‐down analyses. In contrast, the trend from higher resolution satellite‐based estimates, which are more capable of capturing the urban emission signature, is in better agreement with ozone in high NOx emission regions, and is consistent with the trend based on surface observations of NO2 . Our results confirm that the satellite‐derived trends reflect anthropogenic and background influences. Plain Language Summary: Air pollution regulations have led to significant reductions in NOx emissions in the US in the past two decades. However, satellite‐based analyses have suggested a slow‐down in the reduction of US NOx emissions after 2010. Here, we use a deep learning model to evaluate NOx emission trends in the US. We find that the satellite‐based trends are consistent with trends in surface NO2 observations in high NOx emission regions, but in rural regions the satellite‐based trends reflect the influence of changes in background and anthropogenic NOx emissions. Key Points: We have developed a deep learning model that predicts well daily averaged summertime surface ozone in the United States Satellite‐based emission estimates of NOX are influenced by anthropogenic and background NOX, but their relative contributions are unclear Trends in high‐resolution space‐based NOX emission estimates and in surface NO2 are consistent in high emission regions