Prediction of Particulate Matter Concentration based on Traffic and Meteorological Data

Sunday, June 16, 2024

3:00 PM - 4:15 PM ET

Room: Galleria

Primary Author(s)

Jiayu Yang, /

Ph.D student
Central South University
Changsha, Hunan, China (People's Republic)

Co-Author(s)

LS

Linchang Shi, /

Master's student
Central South University
Changsha, Hunan, China (People's Republic)

Presenter(s)

Jaeyoung Lee, Ph.D.

Professor
Central South University
Florida, California, United States

Submitter(s)

JY

Jiayu Yang, /

Central South University
Changsha, Hunan, China (People's Republic)

Abstract:

Air pollution threatens worldwide human health, ecosystems, and climate change. Transportation is a major contributor to air pollution through emissions from vehicles. Public transportation has been encouraged as a solution to reduce air pollution. However, the link between public transportation and air pollution is intricate and influenced by multiple elements. This study employs spatiotemporal causal convolutional networks to predict air pollution levels by utilizing meteorological data, public transportation, and road traffic flow data as inputs. Using Seoul, South Korea as a case study, a dataset of 25 regional air monitoring stations is used for air pollutants prediction. The results demonstrate the contribution of meteorological data and traffic to the formation and dispersion of particulate matter. The model can potentially be utilized in a real-time air pollution tracking system to facilitate prompt interventions and reduce the harmful effects of air contamination on public health.

Learning Objectives:

Attendees can expect to learn the following from this session:

Upon completion, participant will be able to understand spatiotemporal prediction of Particulate Matter concentration based on traffic and meteorological Data.
Upon completion, participant will be able to utilize the model in a real-time air pollution tracking system to facilitate prompt interventions and reduce the harmful effects on public health.
Upon completion, participant will be able to utilize ST-CCN which can be extended to other transportation research fields where causal relationships between variables are of interest (e.g., traffic crash prediction).