Spatiotemporal adaptive attention graph convolution network for city-level air quality prediction

• Published in: Scientific reports Vol. 13; no. 1; pp. 13335 - 16
• Main Authors: Liu, Hexiang, Han, Qilong, Sun, Hui, Sheng, Jingyu, Yang, Ziyu
• Format: Journal Article
• Language: English
• Published: London Nature Publishing Group UK 16.08.2023; Nature Publishing Group; Nature Portfolio
• Subjects: 631/114/116; 631/114/2397; Air pollution; Air quality; Convolution; Deep learning; Humanities and Social Sciences; multidisciplinary; Outdoor air quality; Particulate matter; Predictions; Science; Science (multidisciplinary); Spatial analysis
• ISSN: 2045-2322; 2045-2322
• DOI: 10.1038/s41598-023-39286-0

Air pollution is a leading cause of human diseases. Accurate air quality predictions are critical to human health. However, it is difficult to extract spatiotemporal features among complex spatiotemporal dependencies effectively. Most existing methods focus on constructing multiple spatial dependencies and ignore the systematic analysis of spatial dependencies. We found that besides spatial proximity stations, functional similarity stations, and temporal pattern similarity stations, the shared spatial dependencies also exist in the complete spatial dependencies. In this paper, we propose a novel deep learning model, the spatiotemporal adaptive attention graph convolution model, for city-level air quality prediction, in which the prediction of future short-term series of PM2.5 readings is preferred. Specifically, we encode multiple spatiotemporal dependencies and construct complete spatiotemporal interactions between stations using station-level attention. Among them, we design a Bi-level sharing strategy to extract shared inter-station relationship features between certain stations efficiently. Then we extract multiple spatiotemporal features with multiple decoders, which it is extracted from the complete spatial dependencies between stations. Finally, we fuse multiple spatiotemporal features with a gating mechanism for multi-step predictions. Our model achieves state-of-the-art experimental results in several real-world datasets.