Interpreting hourly mass concentrations of PM_(2.5)chemical components with an optimal deep-learning model  

作　　者：Hongyi Li Ting Yang Yiming Du Yining Tan Zifa Wang 

机构地区：[1]State Key Laboratory of Atmospheric Boundary Layer Physics and Atmospheric Chemistry(LAPC),Institute of Atmospheric Physics,Chinese Academy of Sciences,Beijing 100029,China [2]Center for Excellence in Regional Atmospheric Environment,Institute of Urban Environment,Chinese Academy of Sciences,Xiamen 361021,China [3]University of Chinese Academy of Sciences,Beijing 100049,China [4]Shenyang Environmental Monitoring Center,Shenyang 110167,China

出　　处：《Journal of Environmental Sciences》2025年第5期125-139,共15页环境科学学报(英文版)

基　　金：supported by the National Key Research and Development Program for Young Scientists of China(No.2022YFC3704000);the National Natural Science Foundation of China(No.42275122);the National Key Scientific and Technological Infrastructure project“Earth System Science Numerical Simulator Facility”(EarthLab).

摘　　要：PM_(2.5)constitutes a complex and diversemixture that significantly impacts the environment,human health,and climate change.However,existing observation and numerical simulation techniques have limitations,such as a lack of data,high acquisition costs,andmultiple uncertainties.These limitations hinder the acquisition of comprehensive information on PM_(2.5)chemical composition and effectively implement refined air pollution protection and control strategies.In this study,we developed an optimal deep learning model to acquire hourly mass concentrations of key PM_(2.5)chemical components without complex chemical analysis.The model was trained using a randomly partitioned multivariate dataset arranged in chronological order,including atmospheric state indicators,which previous studies did not consider.Our results showed that the correlation coefficients of key chemical components were no less than 0.96,and the root mean square errors ranged from 0.20 to 2.11μg/m^(3)for the entire process(training and testing combined).The model accurately captured the temporal characteristics of key chemical components,outperforming typical machine-learning models,previous studies,and global reanalysis datasets(such asModern-Era Retrospective analysis for Research and Applications,Version 2(MERRA-2)and Copernicus Atmosphere Monitoring Service ReAnalysis(CAMSRA)).We also quantified the feature importance using the random forest model,which showed that PM_(2.5),PM_(1),visibility,and temperature were the most influential variables for key chemical components.In conclusion,this study presents a practical approach to accurately obtain chemical composition information that can contribute to filling missing data,improved air pollution monitoring and source identification.This approach has the potential to enhance air pollution control strategies and promote public health and environmental sustainability.

关 键 词：Pm2.5 chemical composition Hourly mass concentration Deep learning Bayesian optimization Feature importance 

分 类 号：X513[环境科学与工程—环境工程]