Regional Prediction of Ozone and Fine Particulate Matter Using Diffusion Convolutional Recurrent Neural Network

Dongsheng Wang, Hong-Wei Wang, Kai-Fa Lu, Zhong-Ren Peng and Juanhao Zhao
Additional contact information
Dongsheng Wang: Center for Intelligent Transportation Systems and Unmanned Aerial Systems Applications Research, State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Hong-Wei Wang: Center for Intelligent Transportation Systems and Unmanned Aerial Systems Applications Research, State Key Laboratory of Ocean Engineering, School of Naval Architecture, Ocean and Civil Engineering, Shanghai Jiao Tong University, Shanghai 200240, China
Kai-Fa Lu: International Center for Adaptation Planning and Design, College of Design, Construction and Planning, University of Florida, P.O. Box 115706, Gainesville, FL 32611, USA
Zhong-Ren Peng: International Center for Adaptation Planning and Design, College of Design, Construction and Planning, University of Florida, P.O. Box 115706, Gainesville, FL 32611, USA
Juanhao Zhao: Department of Computer Science, Viterbi School of Engineering, University of Southern California, Los Angeles, CA 90089, USA

IJERPH, 2022, vol. 19, issue 7, 1-15

Abstract: Accurate air quality forecasts can provide data-driven supports for governmental departments to control air pollution and further protect the health of residents. However, existing air quality forecasting models mainly focus on site-specific time series forecasts at a local level, and rarely consider the spatiotemporal relationships among regional monitoring stations. As a novelty, we construct a diffusion convolutional recurrent neural network (DCRNN) model that fully considers the influence of geographic distance and dominant wind direction on the regional variations in air quality through different combinations of directed and undirected graphs. The hourly fine particulate matter (PM 2.5 ) and ozone data from 123 air quality monitoring stations in the Yangtze River Delta, China are used to evaluate the performance of the DCRNN model in the regional prediction of PM 2.5 and ozone concentrations. Results show that the proposed DCRNN model outperforms the baseline models in prediction accuracy. Compared with the undirected graph model, the directed graph model considering the effects of wind direction performs better in 24 h predictions of pollutant concentrations. In addition, more accurate forecasts of both PM 2.5 and ozone are found at a regional level where monitoring stations are distributed densely rather than sparsely. Therefore, the proposed model can assist environmental researchers to further improve the technologies of air quality forecasts and could also serve as tools for environmental policymakers to implement pollution control measures.

Keywords: fine particulate matter; ozone; air quality forecast; diffusion convolutional recurrent neural network; deep learning (search for similar items in EconPapers)
JEL-codes: I I1 I3 Q Q5 (search for similar items in EconPapers)
Date: 2022
References: View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/1660-4601/19/7/3988/pdf (application/pdf)
https://www.mdpi.com/1660-4601/19/7/3988/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jijerp:v:19:y:2022:i:7:p:3988-:d:780886

Access Statistics for this article

IJERPH is currently edited by Ms. Jenna Liu

More articles in IJERPH from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().