72-hour real-time forecasting of ambient PM2.5 by hybrid graph deep neural network with aggregated neighborhood spatiotemporal information

Mengfan Teng; Siwei Li; Jia Xing; Chunying Fan; Jie Yang; Shuo Wang; Ge Song; Yu Ding; Jiaxin Dong; Shansi Wang

doi:10.1016/j.envint.2023.107971

72-hour real-time forecasting of ambient PM_2.5 by hybrid graph deep neural network with aggregated neighborhood spatiotemporal information

Environ Int. 2023 Jun:176:107971. doi: 10.1016/j.envint.2023.107971. Epub 2023 May 12.

Authors

Mengfan Teng¹, Siwei Li², Jia Xing³, Chunying Fan¹, Jie Yang⁴, Shuo Wang⁵, Ge Song¹, Yu Ding¹, Jiaxin Dong¹, Shansi Wang¹

Affiliations

¹ Hubei Key Laboratory of Quantitative Remote Sensing of Land and Atmosphere, School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China.
² Hubei Key Laboratory of Quantitative Remote Sensing of Land and Atmosphere, School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, China. Electronic address: siwei.li@whu.edu.cn.
³ Department of Civil and Environmental Engineering, the University of Tennessee, Knoxville, TN 37996, USA.
⁴ Hubei Key Laboratory of Quantitative Remote Sensing of Land and Atmosphere, School of Remote Sensing and Information Engineering, Wuhan University, Wuhan 430079, China; Hubei Luojia Laboratory, Wuhan University, Wuhan 430079, China.
⁵ School of Systems Science, Beijing Normal University, Beijing 100875, China.

PMID: 37220671
DOI: 10.1016/j.envint.2023.107971

Abstract

The observation-based air pollution forecasting method has high computational efficiency over traditional numerical models, but a poor ability in long-term (after 6 h) forecasting due to a lack of detailed representation of atmospheric processes associated with the pollution transport. To address such limitation, here we propose a novel real-time air pollution forecasting model that applies a hybrid graph deep neural network (GNN_LSTM) to dynamically capture the spatiotemporal correlations among neighborhood monitoring sites to better represent the physical mechanism of pollutant transport across the space with the graph structure which is established with features (angle, wind speed, and wind direction) of neighborhood sites to quantify their interactions. Such design substantially improves the model performance in 72-hour PM_2.5 forecasting over the whole Beijing-Tianjin-Hebei region (overall R² increases from 0.6 to 0.79), particularly for polluted episodes (PM_2.5 concentration > 55 µg/m³) with pronounced regional transport to be captured by GNN_LSTM model. The inclusion of the AOD feature further enhances the model performance in predicting PM_2.5 over the sites where the AOD can inform additional aloft PM_2.5 pollution features related to regional transport. The importance of neighborhood site (particularly for those in the upwind flow pathway of the target area) features for long-term PM_2.5 forecast is demonstrated by the increased performance in predicting PM_2.5 in the target city (Beijing) with the inclusion of additional 128 neighborhood sites. Moreover, the newly developed GNN_LSTM model also implies the "source"-receptor relationship, as impacts from distanced sites associated with regional transport grow along with the forecasting time (from 0% to 38% in 72 h) following the wind flow. Such results suggest the great potential of GNN_LSTM in long-term air quality forecasting and air pollution prevention.

Keywords: AOD; Hybrid graph deep neural network; PM(2.5); Physical mechanism.

Publication types

Research Support, U.S. Gov't, Non-P.H.S.

MeSH terms

Air Pollutants* / analysis
Air Pollution* / analysis
Environmental Monitoring / methods
Forecasting
Neural Networks, Computer
Particulate Matter / analysis

Substances

Air Pollutants
Particulate Matter