Related Experiment Video
Updated: Nov 24, 2025
Real-time Breath Analysis by Using Secondary Nanoelectrospray Ionization Coupled to High Resolution Mass Spectrometry
Published on: March 9, 2018
Roadside Air Quality Forecasting in Shanghai with a Novel Sequence-to-Sequence Model
Dongsheng Wang1, Hong-Wei Wang1, Chao Li1
1Center 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.
This study developed a novel air quality forecasting model that incorporates weekly periodicity, improving predictions for fine particulate matter (PM2.5) and carbon monoxide (CO). The model enhances urban air quality management and traffic control strategies.
Area of Science:
- Environmental Science
- Atmospheric Chemistry
- Data Science
Background:
- Effective roadside air quality forecasting is crucial for traffic management and public health.
- Existing models often neglect the temporal periodicity of air pollutants.
Purpose of the Study:
- To develop a novel sequence-to-sequence model incorporating weekly periodicity for improved air quality forecasting.
- To analyze temporal variations of air pollutants and their relationship with traffic flow.
Main Methods:
- Utilized two-year observational data from Shanghai roadside air quality monitoring stations.
- Developed and evaluated a sequence-to-sequence model with weekly periodicity.
- Compared the proposed model against a baseline model.
Main Results:
- Fine particulate matter (PM2.5) and carbon monoxide (CO) concentrations exhibit distinct daily and weekly variations linked to traffic flow.
- The proposed model demonstrated superior accuracy compared to the baseline model.
- Achieved higher linear consistency in PM2.5 prediction and reduced errors in CO prediction.
Conclusions:
- Incorporating temporal periodicity significantly enhances air quality forecasting models.
- The developed model offers a valuable tool for urban air quality management, traffic control, and policy implementation.
