Abstract
Air pollution exposure remains a leading public health problem in China. The use of chemical transport models to quantify the impacts of various emission changes on air quality is limited by their large computational demands. Machine learning models can emulate chemical transport models to provide computationally efficient predictions of outputs based on statistical associations with inputs. We developed novel emulators relating emission changes in five key anthropogenic sectors (residential, industry, land transport, agriculture, and power generation) to winter ambient fine particulate matter (PM2.5) concentrations across China. The emulators were optimized based on Gaussian process regressors with Matern kernels. The emulators predicted 99.9% of the variance in PM2.5 concentrations for a given input configuration of emission changes. PM2.5 concentrations are primarily sensitive to residential (51%–94% of first‐order sensitivity index), industrial (7%–31%), and agricultural emissions (0%–24%). Sensitivities of PM2.5 concentrations to land transport and power generation emissions are all under 5%, except in South West China where land transport emissions contributed 13%. The largest reduction in winter PM2.5 exposure for changes in the five emission sectors is by 68%–81%, down to 15.3–25.9 μg m−3, remaining above the World Health Organization annual guideline of 10 μg m−3. The greatest reductions in PM2.5 exposure are driven by reducing residential and industrial emissions, emphasizing the importance of emission reductions in these key sectors. We show that the annual National Air Quality Target of 35 μg m−3 is unlikely to be achieved during winter without strong emission reductions from the residential and industrial sectors.
Highlights
Air pollution exposure is a leading public health problem in China (GBD 2017 Risk Factor Collaborators, 2018; Yin et al, 2020)
We developed emulators to predict how PM2.5 concentrations change as emissions from the residential (RES), industrial (IND), land transport (TRA), agricultural (AGR), and power generation (ENE) sectors change within mainland China
In all regions except in South West China, sensitivities of PM2.5 concentrations to land transport emissions are under 5%
Summary
Air pollution exposure is a leading public health problem in China (GBD 2017 Risk Factor Collaborators, 2018; Yin et al, 2020). Despite recent improvements in the air quality of China, air pollution exposure remains high, requiring further emission reductions to improve public health (Silver et al, 2020; Zhao et al, 2018). The impacts of potential emission changes on air quality can be determined through chemical transport model simulations. Y. Chen et al (2020) trained machine learning models on simulation data from chemical transport models to predict changes in Indian air quality from emission changes, enabling extensive sensitivity analyses to be undertaken. Zhang et al, 2020), to fuse model simulations with ground observations (Lyu et al, 2019), to optimize economic pathways to achieve air quality goals (Huang et al, 2020), and for the prediction of air pollution concentrations Other machine learning approaches concerning Chinese air quality have been used to decouple the effects of meteorology and policies (Y. Zhang et al, 2020), to fuse model simulations with ground observations (Lyu et al, 2019), to optimize economic pathways to achieve air quality goals (Huang et al, 2020), and for the prediction of air pollution concentrations (G. Chen et al, 2018; Q. Li et al, 2018; Ma et al, 2019; Wei et al, 2020; Zhan et al, 2017)
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
