Modeling assessment of air pollution control measures and COVID-19 pandemic on air quality improvements over Greater Bay Area of China.

A remarkable progress has been made toward the air quality improvements over the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) of China from 2017 to 2020. In this study, for the first time, the emission reductions of regional control measures together with the COVID-19 pandemic were considered simultaneously into the development of the GBA's emission inventories for the years of 2017 and 2020. Based on these collective emission inventories, the impacts of control measures, meteorological variations together with temporary COVID-19 lockdowns on the five major air quality index pollutants (SO2, NO2, PM2.5, PM10, and O3, excluding CO) were evaluated using the WRF-CMAQ and SMAT-CE model attainment assessment tool over the GBA region. Our results revealed that control measures in the Pearl River Delta (PRD) region affected significantly the GBA, resulting in pollutant reductions ranging from 48 % to 64 %. In contrast, control measures in Hong Kong and Macao contributed to pollutant reductions up to 10 %. In PRD emission sectors, stationary combustion, on-road, industrial processes and dust sectors stand out as the primary contributors to overall air quality improvements. Moreover, the COVID-19 pandemic during period I (Jan 23-Feb 23) led to a reduction of NO2 concentration by 7.4 %, resulting in a negative contribution (disbenefit) for O3 with an increase by 2.4 %. Our findings highlight the significance of PRD control measures for the air quality improvements over the GBA, emphasizing the necessity of implementing more refined and feasible manageable joint prevention and control policies.

Development of a recurrent spatiotemporal deep-learning method coupled with data fusion for correction of hourly ozone forecasts.

Ambient ozone (O3) predictions can be very challenging mainly due to the highly nonlinear photochemistry among its precursors, and meteorological conditions and regional transport can further complicate the O3 formation processes. The emission-based chemical transport models (CTM) are broadly used to predict O3 formation, but they may deviate from observations due to input uncertainties such as emissions and meteorological data, in addition to the treatment of O3 nonlinear chemistry. In this study, an innovative recurrent spatiotemporal deep-learning (RSDL) method with model-monitor coupled convolutional recurrent neural networks (ConvRNN) has been developed to improve O3 predictions of CTM. The RSDL method was first used to build the ConvRNN within a 24-h scale to characterize the spatiotemporal relationships between the monitored O3 data and CTM simulations, and then incorporated the recurrent pattern to achieve 72-h multi-site forecasts based on a pilot study over the Pearl River Delta (PRD) region of China. The results showed that the RSDL method predicted O3 with high accuracy over this case study, with an increase of 27.54% in the correlation coefficient (R) average for all sites as well as an increase in R of 0.14-0.21 for all cities compared to CTM. Moreover, the regional distribution of CTM was further improved by the RSDL predictions with the data fusion technique, which greatly reduced the underpredictions of O3 concentrations, particularly in high O3-level areas (concentrations >160 µg/m3), with a 33.55% reduction in the mean absolute error (MAE).