Reduction in vehicular emissions attributable to the Covid-19 lockdown in Shanghai: insights from 5-year monitoring-based machine learning

Abstract. Exposure to element carbon (EC) and NO_x is a public health issue that has been gaining increasing interest, with high exposure levels generally observed in traffic environments e.g., roadsides. Shanghai, home to approximately 25 million in the Yangtze River Delta (YRD) region in east China, has one of the most intensive traffic activities in the world. However, our understanding of the trend in vehicular emissions and, in particular, in response to the strict Covid-19 lockdown is limited partly due to a lack of long-term observation dataset and application of advanced mathematical models. In this study, NO_x and EC were continuously monitored at a near highway sampling site in west Shanghai for 5 years (2016–2020). The long-term dataset was used to train the machine learning model, rebuilding the NO_x and EC in a business-as-usual (BAU) scenario in 2020. The reduction in NO_x and EC attributable to lockdown was found to be smaller than it appeared because the first week of lockdown overlapped with the lunar new year holiday, whereas, at a later stage of lockdown, the reduction (50–70 %) attributable to the lockdown was more significant, confirmed by satellite monitoring of NO₂. In contrast, the impact of the lockdown on vehicular emissions cannot be well represented by simply comparing the concentration before and during the lockdown for conventional campaigns. This study demonstrates the value of continuous air pollutant monitoring at a roadside on a long-term basis. Combined with the advanced mathematical model, air quality changes upon future emission control and/or event-driven scenarios are expected to be better predicted.