Temporal Difference-Based Graph Transformer Networks For Air Quality PM2.5 Prediction: A Case Study in China

Frontiers in Environmental Science

Shiqing Zhang¹  Xiaoming Zhao¹  Linjian Chen²  Zhen Zhang³  Jun Yao³ 

[1]Institute of Intelligent Information Processing, Taizhou University, Taizhou, China

[2]Yuhuan Branch of Taizhou Ecological Environment Bureau, Yuhuan, China

[3]Zhejiang Provincial Key Laboratory of Evolutionary Ecology and Conservation, Taizhou University, Taizhou, China

关键词: air quality prediction;    deep learning;    temporal difference;    graph attention;    transformer;    long-term dependency;   

DOI  :  10.3389/fenvs.2022.924986

来源: DOAJ

【 摘 要 】

Air quality PM2.5 prediction is an effective approach for providing early warning of air pollution. This paper proposes a new deep learning model called temporal difference-based graph transformer networks (TDGTN) to learn long-term temporal dependencies and complex relationships from time series PM2.5 data for air quality PM2.5 prediction. The proposed TDGTN comprises of encoder and decoder layers associated with the developed graph attention mechanism. In particular, considering the similarity of different time moments and the importance of temporal difference between two adjacent moments for air quality PM2.5prediction, we first construct graph-structured data from original time series PM2.5 data at different moments without explicit graph structure. Then we improve the self-attention mechanism with the temporal difference information, and develop a new graph attention mechanism. Finally, the developed graph attention mechanism is embedded into the encoder and decoder layers of the proposed TDGTN to learn long-term temporal dependencies and complex relationships from a graph prospective on air quality PM2.5 prediction tasks. Experiment results on two collected real-world datasets in China, such as Beijing and Taizhou PM2.5 datasets, show that the proposed method outperforms other used methods on both short-term and long-term air quality PM2.5 prediction tasks.

【 授权许可】

Unknown