Spatial-Temporal Dynamic Graph Convolution Neural Network for Air Quality Prediction
Authors:
- 18 July 2021
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-8
Abstract
Air quality prediction has received widespread attention from both the governments and citizens due to its close relation to our lives. Analyzing the spatial relations and temporal trends in air quality data is essential for air quality prediction task. However, most existing approaches require a pre-defined graph structure to capture the spatial dependencies of air quality data, and thus they can not be applied when a well-defined graph structure is unavailable. Besides, those methods do not give sufficient consideration to the latent relationships among entities of the graph over time. To overcome the above limitations, we propose a Spatial-Temporal Dynamic Graph Convolution Neural Network (ST-DGCN) in this paper. Our approach develops a dynamic adjacency matrix into graph convolution layer, which extracts the potential and time-varying spatial dependencies. To jointly model the spatial and temporal correlations, we combine dynamic graph convolution with gated recurrent unit and propose a unified DGC-GRU block. Next, a residual operation is further introduced into the DGC-GRU to simultaneously handle the information from different particles. Experimental results demonstrate that the proposed method outperforms the state-of-art baselines on two real-world air quality datasets.Keywords
Funding Information
- National Key R&D Program of China (2019YFB2101801)
- National Natural Science Foundation of China (61976247)
This publication has 23 references indexed in Scilit:
- Identity Mappings in Deep Residual Networks2016
- RAQ–A Random Forest Approach for Predicting Air Quality in Urban Sensing SystemsSensors, 2016
- Forecasting Fine-Grained Air Quality Based on Big Data2015
- PM 2.5 in China: Measurements, sources, visibility and health effects, and mitigationParticuology, 2014
- Forecasting of daily air quality index in DelhiScience of The Total Environment, 2011
- Human health effects of air pollutionEnvironmental Pollution, 2008
- Statistical models for the prediction of respirable suspended particulate matter in urban citiesAtmospheric Environment, 2006
- Air quality forecasting using a hybrid autoregressive and nonlinear modelAtmospheric Environment, 2006
- Long Short-Term MemoryNeural Computation, 1997
- Divergence measures based on the Shannon entropyIEEE Transactions on Information Theory, 1991