Development of an integrated machine-learning and data assimilation framework for NOx emission inversion

Yiang Chen; Jimmy C H Fung; Dehao Yuan; Wanying Chen; Tung Fung; Xingcheng Lu

doi:10.1016/j.scitotenv.2023.161951

Development of an integrated machine-learning and data assimilation framework for NO_x emission inversion

Sci Total Environ. 2023 May 1:871:161951. doi: 10.1016/j.scitotenv.2023.161951. Epub 2023 Feb 1.

Authors

Yiang Chen¹, Jimmy C H Fung², Dehao Yuan³, Wanying Chen¹, Tung Fung⁴, Xingcheng Lu⁵

Affiliations

¹ Division of Environment and Sustainability, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong SAR, China.
² Division of Environment and Sustainability, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong SAR, China; Department of Mathematics, Hong Kong University of Science and Technology, Clear Water Bay, Hong Kong SAR, China.
³ Department of Computer Science, University of Maryland, College Park, MD, USA.
⁴ Department of Geography and Resource Management, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China.
⁵ Department of Geography and Resource Management, The Chinese University of Hong Kong, Shatin, Hong Kong SAR, China. Electronic address: xingchenglu2011@gmail.com.

PMID: 36737010
DOI: 10.1016/j.scitotenv.2023.161951

Abstract

As major air pollutants, nitrogen oxides (NO_x, mainly comprising NO and NO₂) not only have adverse effects on human health but also contribute to the formation of secondary pollutants, such as ozone and particulate nitrate. To acquire reasonable NO_x simulation results for further analysis, a reasonable emission inventory is needed for three-dimensional chemical transport models (3D-CTMs). In this study, a comprehensive emission adjustment framework for NO_x emission, which integrates the simulation results of the 3D-CTM, surface NO₂ measurements, the three-dimensional variational data assimilation method, and an ensemble back propagation neural network, was proposed and applied to correct NO_x emissions over China for the summers of 2015 and 2020. Compared with the simulation using prior NO_x emissions, the root-mean-square error, normalized mean error, and normalized mean bias decreased by approximately 40 %, 40 %, and 60 % in NO₂ simulation using posterior NO_x emissions corrected by the framework proposed in this work. Compared with the emissions for 2015, the NO_x emission generally decreased by an average of 5 % in the simulation domain for 2020, especially in Henan and Anhui provinces, where the percentage reductions reached 24 % and 19 %, respectively. The proposed framework is sufficiently flexible to correct emissions in other periods and regions. The framework can provide reliable and up-to-date emission information and can thus contribute to both scientific research and policy development relating to NO_x pollution.

Keywords: 3D-Var data assimilation method; Emission inversion; Machine learning; NO(x) emissions; WRF-CAMx.