A hybrid model for spatiotemporal forecasting of PM2.5 based on graph convolutional neural network and long short-term memory

Yanlin Qi; Qi Li; Hamed Karimian; Di Liu

doi:10.1016/j.scitotenv.2019.01.333

A hybrid model for spatiotemporal forecasting of PM_2.5 based on graph convolutional neural network and long short-term memory

Sci Total Environ. 2019 May 10:664:1-10. doi: 10.1016/j.scitotenv.2019.01.333. Epub 2019 Feb 1.

Authors

Yanlin Qi¹, Qi Li², Hamed Karimian¹, Di Liu³

Affiliations

¹ Institute of Remote Sensing and Geographic Information System, Peking University, Beijing, China.
² Institute of Remote Sensing and Geographic Information System, Peking University, Beijing, China. Electronic address: liqi@pku.edu.cn.
³ School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, Hubei, China.

PMID: 30743109
DOI: 10.1016/j.scitotenv.2019.01.333

Abstract

Increasing availability of data related to air quality from ground monitoring stations has provided the chance for data mining researchers to propose sophisticated models for predicting the concentrations of different air pollutants. In this paper, we proposed a hybrid model based on deep learning methods that integrates Graph Convolutional networks and Long Short-Term Memory networks (GC-LSTM) to model and forecast the spatiotemporal variation of PM_2.5 concentrations. Specifically, historical observations on different stations are constructed as spatiotemporal graph series, and historical air quality variables, meteorological factors, spatial terms and temporal attributes are defined as graph signals. To evaluate the performance of the GC-LSTM, we compared our results with several state-of-the-art methods in different time intervals. Based on the results, our GC-LSTM model achieved the best performance for predictions. Moreover, evaluations of recall rate (68.45%), false alarm rate (4.65%) (both of threshold: 115 μg/m³) and correlation coefficient R² (0.72) for 72-hour predictions also verify the feasibility of our proposed model. This methodology can be used for concentration forecasting of different air pollutants in future.

Keywords: Air pollution forecasting; Deep learning; Graph convolutional neural network; Long short-term memory; Spatiotemporal data modelling.