TKDE_2021_paper.pdf (1.17 MB)
Download file

Spatiotemporal Graph Convolutional Recurrent Neural Network Model for Citywide Air Pollution Forecasting

Download (1.17 MB)
posted on 2022-12-12, 20:28 authored by Van-Duc LeVan-Duc Le, Bui-Tien Cuong, Sang-Kyun Cha

This paper applies a Spatiotemporal Graph Convolutional Recurrent Neural Network which is a tight combination of a Graph Neural Network (GNN) to a Recurrent Neural Network (RNN) architecture for air pollution forecasting in long-term for the entire city. Our model can effectively learn the spatial and temporal features of the air pollution data and its influential factors (e.g. weather, traffic, external areas) at the time. Our method achieves better performance than a state-of-the-art ConvLSTM model in air pollution forecasting and a hybrid GNN-based model that separates GNN and RNN in discrete layers.


Email Address of Submitting Author

Submitting Author's Institution

Seoul National University

Submitting Author's Country

  • Korea, Republic of (South Korea)

Usage metrics