A novel spatiotemporal convolutional long short-term neural network for air pollution prediction.

Deep learning-based PM2.5 prediction considering the spatiotemporal correlations: A case study of Beijing, China.

Spatiotemporal trends in PM2.5 levels from 2013 to 2017 and regional demarcations for joint prevention and control of atmospheric pollution in China.

Control of both PM2.5 and O3 in Beijing-Tianjin-Hebei and the surrounding areas

. The fine particles (PM 2.5 ) in China have decreased significantly in
recent years as a result of the implementation of Chinese Clean Air Action Plan
since 2013, while the O3 pollution is getting worse, especially in
megacities such as Beijing and Shanghai. Better understanding of the elevated
 O3 pollution in Chinese megacities and its response to emission change
is important for developing an effective emission control strategy in
the future. In this study, we analyze the significant increasing trend of daily
maximum O3 concentration from 2006 to 2015 in the megacity Shanghai
with the variability of 0.8–1.3 ppbv yr −1 . It could likely be attributed to
the notable reduction in NOx concentrations with the decreasing rate of
1.86–2.15 ppbv yr −1 accompanied by the small change in VOCs during
the same period by excluding the weak trends of meteorological impacts on
local dispersion (wind speed), regional transport (wind direction), and
 O3 photolysis (solar radiation). It is further illustrated by using a
state-of-the-art regional chemical and dynamical model (WRF-Chem) to explore the
 O3 variation response to the reduction in NOx emissions in
Shanghai. The control experiment conducted for September of 2009 shows
excellent performance for O3 and NOx simulations, including both
the spatial distribution pattern and the day-by-day variation through
comparison with six in situ measurements from the MIRAGE-Shanghai field campaign.
Sensitivity experiments with 30 % reduction in NOx emissions from 2009
to 2015 in Shanghai estimated by Shanghai Environmental Monitoring Center
shows that the calculated O3 concentrations exhibit obvious enhancement
by 4–7 ppbv in urban zones with increasing variability of 0.96–1.06 ppbv yr −1 , which is consistent with the observed O3 trend as a
result of the strong VOC-limited condition for O3 production. The large
reduction in NOx combined with less change in VOCs in the past 10
years promotes the O3 production in Shanghai to move towards
an NOx -limited regime. Further analysis of the WRF-Chem experiments and
 O3 isopleth diagram suggests that the O3 production downtown
is still under a VOC-limited regime after 2015 despite the remarkable
 NOx reduction, while it moves to the transition regime between
 NOx -limited and VOC-limited in sub-urban zones. Supposing the
insignificant VOC variation persists, the O3 concentration downtown
would keep increasing until 2020 with the further 20 % reduction in
 NOx emission after 2015 estimated by Shanghai Clean Air Action Plan.
The O3 production in Shanghai will switch from a VOC-limited to
an NOx -limited regime after 2020 except for downtown area, which is likely
close to the transition regime. As a result the O3 concentration will
decrease by 2–3 ppbv in sub-urban zones and by more than 4 ppbv in rural areas as a response to a 20 % reduction in NOx emission after 2020, whereas it is not
sensitive to both NOx and VOC changes downtown. This result reveals
that the control strategy of O3 pollution is a very complex process
and needs to be carefully studied.

/pdf/measurement-and-model-analyses-of-the-ozone-variation-during-4xmvgmucw6.pdf

Measurement and model analyses of the ozone variation during 2006 to 2015 and its response to emission change in megacity Shanghai, China

Numerical air quality forecasting over eastern China: An operational application of WRF-Chem

To analyze the characteristics and formation mechanism of a heavy air pollution episode in Shanghai City from January 23th to January 24th, 2013, the observed data of PM₂.₅ concentration and ground meteorological data and the WRF-Chem model were collected. The analysis revealed that the synoptic necessary mechanism of the heavy air pollution episode could be characterized by the following patterns: Accompanied with weak cold front activities, the city experienced weak winds (i. e. stable atmosphere) at first and then northerly winds (i. e. pollutant transport process ), causing the continuous increase and maintaining of pollutant concentration. The detailed results are shown as follows: Firstly, the stable atmosphere circulation pattern which lasted for 10 hours was not good for air pollution dispersion, as a result, local PM₂.₅ concentrations continued to increase and reached severe pollution level and the high concentrations maintained for 7 hours caused by the stable boundary layer (e. g. static surface winds and low level temperature inversion) during nighttime, and the average PM₂.₅ concentrations during the stable weather process was 172.4 μg · m⁻³. Secondly, the dispersion condition was slightly improved later on with the arrival of a weak cold front, the upstream pollution transportation occurred at the same time, leading to further increase of PM₂.₅ concentration (up to 280 μg · m⁻³), and the average PM₂.₅ concentration during the upstream transportation process was 213.6 μg · m⁻³. Numerical simulation with the WRF-Chem model showed that, average contribution of upstream transportation to local PM₂.₅ concentrations during the episode was 23% . Among them, the contribution during the stable weather and upstream transportation stage was 17.2% and 32.2% . Our results suggested that there were significant differences in the contribution of upstream transportation to the local PM₂.₅ concentration of Shanghai due to variation of weather conditions. Therefore, the government can design effective emission control strategy in advance taking pollution weather forecasting into account.

[A Numerical Study of Typical Heavy Air Pollution Episode of PM₂.₅ in Shanghai].

Based on the Shanghai Meteorological Service WRF ADAS Real-time Modeling System (SMS-WARMS) and the Community Multi-scale Air Quality (CMAQ) model, a chemical weather forecasting system is being established for Eastern China. Anthropogenic emissions are based on Hemispheric Transport of Air Pollution (HTAP) 2010 dataset, and biogenic emissions are estimated using the Model of Emissions of Gases and Aerosols from Nature (MEGAN). Forecasting results during 7 August to 1 September 2016 are evaluated for Shanghai and eight provincial cities in Eastern China. The results exhibit large differences in model performance for different regions. The overestimation of NO2 and PM2.5 for the cities within or adjacent to the Yangtze River Delta (YRD) region suggests air quality measures taken in preparation of the 2016 G20 Summit were effective in reducing pollutants concentrations. The results also show that large reductions in HTAP 2010 NOx and SO2 emissions are required, suggesting that regular updates of emission inventories are necessary to capture the rapid changes in pollutant emissions in Eastern China.

Ying Xie

Papers

Numerical air quality forecasting over eastern China: An operational application of WRF-Chem

[A Numerical Study of Typical Heavy Air Pollution Episode of PM₂.₅ in Shanghai].

Chemical Weather Forecasting for Eastern China