A novel spatiotemporal convolutional long short-term neural network for air pollution prediction

Congcong Wen; Shufu Liu; Xiaojing Yao; Ling Peng; Xiang Li; Yuan Hu; Tianhe Chi

doi:10.1016/j.scitotenv.2018.11.086

A novel spatiotemporal convolutional long short-term neural network for air pollution prediction

Sci Total Environ. 2019 Mar 1:654:1091-1099. doi: 10.1016/j.scitotenv.2018.11.086. Epub 2018 Nov 9.

Authors

Congcong Wen¹, Shufu Liu², Xiaojing Yao³, Ling Peng³, Xiang Li¹, Yuan Hu¹, Tianhe Chi³

Affiliations

¹ Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China; University of Chinese Academy of Sciences, Beijing 100049, China.
² Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China. Electronic address: liusf01@radi.ac.cn.
³ Institute of Remote Sensing and Digital Earth, Chinese Academy of Sciences, Beijing 100094, China.

PMID: 30841384
DOI: 10.1016/j.scitotenv.2018.11.086

Abstract

Air pollution is a serious environmental problem that has drawn worldwide attention. Predicting air pollution in advance has great significance on people's daily health control and government decision-making. However, existing research methods have failed to effectively extract the spatiotemporal features of air pollutant concentration data, and exhibited low precision in long-term predictions and sudden changes in air quality. In the present study, a spatiotemporal convolutional long short-term memory neural network extended (C-LSTME) model for predicting air quality concentration was proposed. In order to encompass the spatiality and temporality of the data, the model involved the historical air pollutant concentration of the present station, as well as that of the adaptive k-nearest neighboring stations, into the model. High-level spatiotemporal features were extracted through the combination of the convolutional neural network (CNN) and long short-term memory neural network (LSTM-NN), and meteorological data and aerosol data were also integrated, in order to improve model prediction performance. Hourly PM2.5 (particulate matter with an aerodynamic diameter of ≤2.5 mm) concentration data collected at 1233 air quality monitoring stations in Beijing and the whole China from January 1, 2016 to December 31, 2017 were used to validate the effectiveness of the proposed C-LSTME model. The results show that the present model has achieved better performance than current state-of-the-art models for different time predictions at different regional scales.

Keywords: 3D convolutional neural network (3D-CNN); Air pollutant concentration predictions; Long short-term memory neural network (LSTM NN); Long-term prediction; Spatiotemporal correlation.