A hybrid deep learning model for regional O3 and NO2 concentrations prediction based on spatiotemporal dependencies in air quality monitoring network.

Short-term prediction of urban air quality is critical to pollution management and public health. However, existing studies have failed to make full use of the spatiotemporal correlations or topological relationships among air quality monitoring networks (AQMN), and hence exhibit low precision in regional prediction tasks. With this consideration, we proposed a novel deep learning-based hybrid model of Res-GCN-BiLSTM combining the residual neural network (ResNet), graph convolutional network (GCN), and bidirectional long short-term memory (BiLSTM), for predicting short-term regional NO2 and O3 concentrations. Auto-correlation analysis and cluster analysis were first utilized to reveal the inherent temporal and spatial properties respectively. They demonstrated that there existed temporal daily periodicity and spatial similarity in AQMN. Then the identified spatiotemporal properties were sufficiently leveraged, and monitoring network topological information, as well as auxiliary pollutants and meteorology were also adaptively integrated into the model. The hourly observed data from 51 air quality monitoring stations and meteorological data in Shanghai were employed to evaluate it. Results show that the Res-GCN-BiLSTM model was better adapted to the pollutant characteristics and improved the prediction accuracy, with nearly 11% and 17% improvements in mean absolute error for NO2 and O3, respectively compared to the best performing baseline model. Among the three types of monitoring stations, traffic monitoring stations performed the best for O3, but the worst for NO2, mainly due to the impacts of intensive traffic emissions and the titration reaction. These findings illustrate that the hybrid architecture is more suitable for regional pollutant concentration.

Assessing the effects of short-term traffic restriction policies on traffic-related air pollutants.

The implementation of short-term traffic restriction policies (TRPs) during major events positively influences the traffic emission reduction. However, few studies explore the impact of diesel vehicle emissions on air quality during short-term TRP. In particular, the intertwined influences of short-term TRP and Spring Festival remains unclear. Based on Beijing 2022 Olympic Games, this study analyzed the spatiotemporal changes in urban air quality and diesel vehicle emission during short-term TRP. The results showed that the TRPs and Spring Festival contributed equally to the improvement of air quality and reduction of diesel vehicle emissions. The "interruption-recovery" pattern of short-term TRPs is characterized by a longer duration and a slower decline/recovery rate. Additionally, the individual contribution rate of diesel vehicle emissions to urban air pollutants was 15-20 % higher than that of meteorological factors during short-term TRPs.

To what extent the traffic restriction policies can improve its air quality? An inspiration from COVID-19.

In hazy days, several local authorities always implemented the strict traffic-restriction measures to improve the air quality. However, owing to lack of data, the quantitative relationships between them are still not clear. Coincidentally, traffic restriction measures during the COVID-19 pandemic provided an experimental setup for revealing such relationships. Hence, the changes in air quality in response to traffic restrictions during COVID-19 in Spain and United States was explored in this study. In contrast to pre-lockdown, the private traffic volume as well as public traffic during the lockdown period decreased within a range of 60-90%. The NO2 concentration decreased by approximately 50%, while O3 concentration increased by approximately 40%. Additionally, changes in air quality in response to traffic reduction were explored to reveal the contribution of transportation to air pollution. As the traffic volume decreased linearly, NO2 concentration decreased exponentially, whereas O3 concentration increased exponentially. Air pollutants did not change evidently until the traffic volume was reduced by less than 40%. The recovery process of the traffic volume and air pollutants during the post-lockdown period was also explored. The traffic volume was confirmed to return to background levels within four months, but air pollutants were found to recover randomly. This study highlights the exponential impact of traffic volume on air quality changes, which is of great significance to air pollution control in terms of traffic restriction policy. Supplementary Information: The online version contains supplementary material available at 10.1007/s00477-022-02351-7.