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

The acceleration of industrialization and urbanization has recently brought about serious air pollution problems, which threaten human health and lives, the environmental safety, and sustainable social development. Air quality prediction is an effective approach for providing early warning of air pollution and supporting cleaner industrial production. However, existing approaches have suffered from a weak ability to capture long-term dependencies and complex relationships from time series PM2.5 data. To address this problem, 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 prediction, we first construct graph-structured data from original time series PM2.5 data at different moments without explicit graph structure. Then, based on the constructed graph, 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. To verify the effectiveness of the proposed method, we conduct air quality prediction experiments on two real-world datasets in China, such as Beijing PM2.5 dataset ranging from 01/01/2010 to 12/31/2014 and Taizhou PM2.5 dataset ranging from 01/01/2017 to 12/31/2019. Compared with other air quality forecasting methods, such as autoregressive moving average (ARMA), support vector regression (SVR), convolutional neural network (CNN), long short-term memory (LSTM), the original Transformer, our experiment results indicate that the proposed method achieves more accurate results on both short-term (1 hour) and long-term (6, 12, 24, 48 hours) air quality prediction tasks.

The Process and Platform for Predicting PM2.5 Inhalation and Retention during Exercise

In recent years, people have been increasingly concerned about air quality and pollution since a number of studies have proved that air pollution, especially PM2.5 (particulate matter), can affect human health drastically. Though the research on air quality prediction has become a mainstream research field, most of the studies focused only on the prediction of urban air quality and pollution. These studies did not predict the actual impact of these pollutants on people. According to the researchers’ best knowledge, the amount of polluted air inhaled by people and the amount of polluted air that remains inside their body are two important factors that affect their health. In order to predict the quantity of PM2.5 inhaled by people and what they have retained in their body, a process and a platform have been proposed in the current research work. In this research, the experimental process is as follows: (1) First, a personalized PM2.5 sensor is designed and developed to sense the quantity of PM2.5 around people. (2) Then, the Bruce protocol is applied to collect the information and calculate the relationship between heart rate and air intake under different activities. (3) The amount of PM2.5 retained in the body is calculated in this step using the International Commission on Radiological Protection (ICRP) air particle retention formula. (4) Then, a cloud platform is designed to collect people’s heart rate under different activities and PM2.5 values at respective times. (5) Finally, an APP is developed to show the daily intake of PM2.5. The result reveals that the developed app can show a person’s daily PM2.5 intake and retention in a specific population.