Ground-level gaseous pollutants across China: daily seamless mapping and long-term spatiotemporal variations

Abstract

Abstract. Gaseous pollutants at the ground level seriously threaten the urban air quality environment and public health. There are few estimates of gaseous pollutants that are spatially and temporally resolved and continuous over long periods in China. This study takes advantage of big data and artificial intelligence technologies to generate seamless daily maps of three major pollutant gases, i.e., NO2, SO2, and CO, across China from 2013 to 2020 at a uniform spatial resolution of 10 km. Cross-validation illustrated a high data quality on a daily basis for NO2, SO2, and CO, with mean out-of-bag coefficients of determination (root-mean-square errors) of 0.84 (7.99 μg/m3), 0.84 (10.7 μg/m3), and 0.80 (0.29 mg/m3), respectively. They have experienced significant declines and then recoveries during and after the COVID-19 lockdown associated with changes in anthropogenic emissions in eastern China, while surface CO recovered faster than SO2 and NO2. All gaseous pollutants decreased significantly by 0.23, 2.01, and 49 μg/m3 per year (p < 0.001) across China during 2013–2020, especially in three urban agglomerations. The declining rates were larger during 2013–2017 but slowed down in recent years. Both the areas and occurrence probabilities of days exceeding air quality standards also gradually shrank and weakened over time, especially for SO2 and CO, which almost disappeared during 2018–2020, suggesting significant improvements in air quality in China. This reconstructed dataset of surface gaseous pollutants, i.e., ChinaHighNO2, ChinaHighSO2, and ChinaHighCO, will benefit future (especially short-term) air pollution and environmental health-related studies.

Short‐Term Exposure to Ambient Air Pollution and Hospital Admissions for Sequelae of Stroke in Chinese Older Adults

“…We collected daily PM 2.5 , PM 10 , SO 2 , NO 2 , CO, and O 3 concentrations during 2016–2019 in Guangdong province from a full‐coverage, high‐quality, and ground‐level air pollutant data set for China (ChinaHighAirPollutants [CHAP]) with a spatial resolution of 10 × 10 km (Wei, Li, Li, et al., 2022 ; Wei, Li, Lyapustin, et al., 2021 ; Wei, Li, Wang, et al., 2022 ; Wei, Li, Xue, et al., 2021 ; Wei, Liu, et al., 2022 ; Wei et al., 2020 ). Generated based on our proposed artificial intelligence models combining with big data (including ground measurements, satellite remote sensing products, and atmospheric reanalysis), the CHAP data set has relatively high cross‐validation coefficients of determination ( R 2 ) ranging from 0.80 to 0.91 for the six ambient air pollutants.…”

Estimation of the ground-level SO2 concentration in eastern China based on the LightGBM model and Himawari-8 TOAR

“…The comparison of model performance between this study and other studies is shown in Table 5. In studies that cover a large area rather than just a city, the Space-Time Extra-Tree (STET) model (Wei et al, 2022) has the best effect, followed by our model. But our model has higher temporal and spatial resolution compared with the STET model.…”