A Comparison of LSTM and BiLSTM for Forecasting the Air Pollution Index and Meteorological Conditions in Jakarta

Jakarta is the capital city of Indonesia where air pollution becomes one of the problems that must be properly handled. The historical data of the air pollution index is beneficial for developing models for forecasting future values. One of the advantages of forecasting air pollution is to help people to arrange future plans to reduce the dangerous effect on health. Analyzing a record of meteorological conditions can be used to understand climate change. This paper reports the comparison of Long Short Term Memory (LSTM) and Bidirectional LSTM (BiLSTM) models for multivariate forecasting of the air pollution index and meteorological conditions in Jakarta. It also informs the performance of those algorithms for forecasting the observed variables before and during the Coronavirus disease (Covid-19) outbreak to analyze the effect of the pandemic on the environment. The experiments use a historical time series dataset from 2010-2021. The experimental results show that LSTM and BiLSTM work well to forecast PM10, temperature, humidity, and wind speed. In this case study, there are no significant differences in the performance of LSTM and BiLSTM. © 2022 IEEE.

Gaseous and Particulate Pollution in the Wu-Chang-Shi Urban Agglomeration on the Northern Slope of Tianshan Mountains from 2017 to 2021

Rapid social development has led to serious air pollution problems in cities, and air pollutants, including gaseous pollutants and particulate matter, have an important impact on climate, the environment, and human health. This study analyzed the characteristics, potential sources, and causes of air pollution in the Wu-Chang-Shi urban cluster. The results showed that NO2, CO, SO2, PM10, and PM2.5 had a tendency to decrease, while O-3 showed an increasing trend. The concentrations of SO2, NO2, CO, PM2.5, and PM10 showed the highest values in winter and the lowest values in summer, with similar seasonal variations. However, the concentration of O-3 was highest in the summer and lowest in the winter. Compared with the pollutant concentrations in other Chinese cities, PM2.5, PM10, and NO2 are more polluted in the Wu-Chang-Shi urban. Meteorological factors have a greater impact on pollutant concentrations, with higher concentrations of major pollutants observed when wind speeds are low and specific wind directions are observed, and higher secondary pollutant O-3 concentrations observed when wind speeds are low and specific wind directions are observed. The backward trajectory and concentration weighting analysis show that the particulate pollutants in the Wu-Chang-Shi urban in winter mainly come from Central Asia and surrounding cities. O-3 showed an increasing trend before and after the novel coronavirus outbreak, which may be related to changes in NOX, volatile organic compounds, and solar radiation intensity, and the concentrations of SO2, NO2, CO, PM10, and PM2.5 showed an overall decreasing trend after the outbreak and was smaller than before the outbreak, which is related to the reduction of industrial and anthropogenic source emissions during the outbreak.

Impact of Meteorological Conditions and Human Activities on Air Quality During the COVID-19 Lockdown in Northeast China

During the lockdown implemented to curb the spread of COVID-19, human activities have drastically reduced, providing a valuable opportunity to study and compare the impact of meteorological conditions and human activities on air quality. In this study, large-scale weather circulation, local meteorological conditions, and the impact of human activities are comprehensively considered, and changes in the concentration of major air pollutants in the northeast during this period are systematically studied. The large-scale weather circulation patterns that mainly affect the northeast region are divided into nine types by using the T-mode Principal components analysis objective circulation classification method. It is found that the northeast region is located at the edge of weak high pressure (Types 1, 2, and 7) and at the rear of high pressure (Type 4) and has higher concentrations of PM2.5, NO2, SO2, and CO;in cyclonic weather systems, low vortices (Types 3 and 5) and under the influence of the updraft (Type 6) in front of the trough, the ozone concentration is higher. The changes in the concentrations of PM2.5, NO2, CO, SO2, and O-3 in the three cities, namely Shenyang, Changchun, and Harbin, during the lockdown period are compared, and it is found that the concentrations of PM2.5, NO2, CO, and SO2 have a tendency to first decrease and then increase, while the changes of O-3 concentration are cyclical and increased significantly during this period. This demonstrates that pollutants such as PM2.5, NO2, CO, and SO2 are more susceptible to human activities and local meteorological conditions, and changes in O-3 concentration are more closely related to changes in weather circulation types. Finally, the FLEXPART-WRF model is used to simulate the pollution process of nine circulation types, which confirms that particulate pollution in the northeast is mainly affected by local emissions and local westward sinking airflow.

Analysis on the Influence and Cause of a Heavy Pollution Process on Air Quality in Baoding during COVID-19

Due to the outbreak of the novel coronavirus, China had implemented a strict home isolation policy after the Spring Festival, and human activities in many areas had been prohibited. However, Baoding still suffered heavy air pollution during February 2020, especially in February 8-13. The results showed that the concentrations of pollutants in February 2020 had a decrease from February 2019. The reduction of human activities during the epidemic significantly decreased the concentration of air pollutants and improved air quality. In addition, compared with non-pollution period (February 22-29), the PM2.5 concentration during pollution period (February 8-13) increased the most visibly. The analysis of OC and EC shows that there was a certain amount of civil coal combustion during the heavy pollution period;K+ and Mg2+ in PM2.5 revealed the huge influence of fireworks and firecrackers in Baoding. The backward trajectory and potential source analysis indicated that Baoding was influenced by air masses from southwest during the heavy pollution period, and the potential source areas were mainly distributed in southwest of Baoding. It can be seen that the impact of pollutants in the superimposed area of local emission and transportation with unfavorable meteorological condition in Baoding. © 2022, HARD Publishing Company. All rights reserved.

Impacts of COVID-19 on air quality in mid-eastern China: An insight into meteorology and emissions.

The coronavirus disease (COVID-19) spread rapidly worldwide in the first half of 2020. Stringent national lockdown policies imposed by China to prevent the spread of the virus reduced anthropogenic emissions and improved air quality. A weather research and forecasting model coupled with chemistry was applied to evaluate the impact of meteorology and emissions on air quality during the COVID-19 outbreak (from January 23 to February 29, 2020) in mid-eastern China. The results show that air pollution episodes still occurred on polluted days and accounted for 31.6%-60.5% of the total number of outbreak days in mid-eastern China from January 23 to February 29, 2020. However, anthropogenic emissions decreased significantly, indicating that anthropogenic emission reduction cannot completely offset the impact of unfavorable meteorological conditions on air quality. Favorable meteorological conditions in 2019 improved the overall air quality for a COVID-19 outbreak in 2019 instead of 2020. PM2.5 concentrations decreased by 4.2%-29.2% in Beijing, Tianjin, Shijiazhuang, and Taiyuan, and increased by 6.1%-11.5% in Jinan and Zhengzhou. PM2.5 concentrations increased by 10.9%-20.5% without the COVID-19 outbreak of 2020 in mid-eastern China, and the frequency of polluted days increased by 5.3%-18.4%. Source apportionment of PM2.5 during the COVID-19 outbreak showed that industry and residential emissions were the dominant PM2.5 contributors (32.7%-49.6% and 26.0%-44.5%, respectively) followed by agriculture (18.7%-24.0%), transportation (7.7%-15.5%), and power (4.1%-5.9%). In Beijing, industrial and residential contributions to PM2.5 concentrations were lower (32.7%) and higher (44.5%), respectively, than in other cities (38.7%-49.6% for industry and 26.0%-36.2% for residential). Therefore, enhancing regional cooperation and implementing a united air pollution control are effective emission mitigation measures for future air quality improvement, especially the development of new technologies for industrial and cooking fumes.

[Impacts of Meteorology and Emission Variations on PM2.5 Concentration Throughout the Country During the 2020 Epidemic Period].

This study analyzed the impacts of meteorological conditions and changes in air pollutant emissions on PM2.5 across the country during the first quarter of 2020 based on the WRF-CMAQ model. Results showed that the variations in meteorological conditions led to a national PM2.5 concentration decreased of 1.7% from 2020-01 to 2020-03, whereas it increased by 1.6% in January and decreased by 1.3% and 7.9% in February and March, respectively. The reduction of pollutants emissions led to a decrease of 14.1% in national PM2.5 concentration during the first quarter of 2020 and a decrease of 4.0%, 25.7%, and 15.0% in January, February, and March, respectively. Compared to the same period last year, the PM2.5 concentration measured in Wuhan City decreased more than in the entire country. This was caused by improved meteorological conditions and a higher reduction of pollutant emissions in Wuhan City. PM2.5 in Beijing increased annually before the epidemic outbreak and during the strict control period, mainly due to unfavorable meteorological conditions. However, the decrease in PM2.5 in Beijing compared to March 2019 was closely related to the substantial reduction of emissions. The measured PM2.5 in the "2+26" cities, the Fenwei Plain and the Yangtze River Delta (YRD) decreased during the first quarter of 2020, with the largest drop occurring in the Yangtze River Delta due to higher YRD emissions reductions. The meteorological conditions of "2+26" cities and Fenwei Plain were unfavorable before the epidemic outbreak and greatly improved during the strict control period, whereas the Yangtze River Delta had the most favorable meteorological conditions in March. The decrease in PM2.5 concentration caused by the reduction of pollutant emissions in the three key areas was highest during the strict control period.

Diverse response of surface ozone to COVID-19 lockdown in China.

Ozone (O3) is a key oxidant and pollutant in the lower atmosphere. Significant increases in surface O3 have been reported in many cities during the COVID-19 lockdown. Here we conduct comprehensive observation and modeling analyses of surface O3 across China for periods before and during the lockdown. We find that daytime O3 decreased in the subtropical south, in contrast to increases in most other regions. Meteorological changes and emission reductions both contributed to the O3 changes, with a larger impact from the former especially in central China. The plunge in nitrogen oxide (NOx) emission contributed to O3 increases in populated regions, whereas the reduction in volatile organic compounds (VOC) contributed to O3 decreases across the country. Due to a decreasing level of NOx saturation from north to south, the emission reduction in NOx (46%) and VOC (32%) contributed to net O3 increases in north China; the opposite effects of NOx decrease (49%) and VOC decrease (24%) balanced out in central China, whereas the comparable decreases (45-55%) in these two precursors contributed to net O3 declines in south China. Our study highlights the complex dependence of O3 on its precursors and the importance of meteorology in the short-term O3 variability.

Impact of meteorological condition changes on air quality and particulate chemical composition during the COVID-19 lockdown.

Stringent quarantine measures during the Coronavirus Disease 2019 (COVID-19) lockdown period (January 23, 2020 to March 15, 2020) have resulted in a distinct decrease in anthropogenic source emissions in North China Plain compared to the paralleled period of 2019. Particularly, 22.7% decrease in NO2 and 3.0% increase of O3 was observed in Tianjin, nonlinear relationship between O3 generation and NO2 implied that synergetic control of NOx and VOCs is needed. Deteriorating meteorological condition during the COVID-19 lockdown obscured the actual PM2.5 reduction. Fireworks transport in 2020 Spring Festival (SF) triggered regional haze pollution. PM2.5 during the COVID-19 lockdown only reduced by 5.6% in Tianjin. Here we used the dispersion coefficient to normalize the measured PM2.5 (DN-PM2.5), aiming to eliminate the adverse meteorological impact and roughly estimate the actual PM2.5 reduction, which reduced by 17.7% during the COVID-19 lockdown. In terms of PM2.5 chemical composition, significant NO3- increase was observed during the COVID-19 lockdown. However, as a tracer of atmospheric oxidation capacity, odd oxygen (Ox = NO2 + O3) was observed to reduce during the COVID-19 lockdown, whereas relative humidity (RH), specific humidity and aerosol liquid water content (ALWC) were observed with noticeable enhancement. Nitrogen oxidation rate (NOR) was observed to increase at higher specific humidity and ALWC, especially in the haze episode occurred during 2020SF, high air humidity and obvious nitrate generation was observed. Anomalously enhanced air humidity may response for the nitrate increase during the COVID-19 lockdown period.

Spatiotemporal variations of ambient air pollutants and meteorological influences over typical urban agglomerations in China during the COVID-19 lockdown.

To investigate the air quality change during the COVID-19 pandemic, we analyzed spatiotemporal variations of six criteria pollutants in nine typical urban agglomerations in China using ground-based data and examined meteorological influences through correlation analysis and backward trajectory analysis under different responses. Concentrations of PM2.5, PM10, NO2, SO2 and CO in urban agglomerations respectively decreased by 18%-45% (30%-62%), 17%-53% (22%-39%), 47%-64% (14%-41%), 9%-34% (0%-53%) and 16%-52% (23%-56%) during Lockdown (Post-lockdown) period relative to Pre-lockdown period. PM2.5 pollution events occurred during Lockdown in Beijing-Tianjin-Hebe (BTH) and Middle and South Liaoning (MSL), and daily O3 concentration rose to grade Ⅱ standard in Post-lockdown period. Distinct from the nationwide slump of NO2 during Lockdown period, a rebound (∼40%) in Post-lockdown period was observed in Cheng-Yu (CY), Yangtze River Middle-Reach (YRMR), Yangtze River Delta (YRD) and Pearl River Delta (PRD). With slightly higher wind speed compared with 2019, the reduction of PM2.5 (51%-62%) in Post-lockdown period is more than 2019 (15%-46%) in HC (Harbin-Changchun), MSL, BTH, CP (Central Plain) and SP (Shandong-Peninsula), suggesting lockdown measures are effective to PM2.5 alleviation. Although O3 concentrations generally increased during the lockdown, its increment rate declined compared with 2019 under similar sunlight duration and temperature. Additionally, unlike HC, MSL and BTH, which suffered from additional (> 30%) air masses from surrounding areas after the lockdown, the polluted air masses reaching YRD and PRD mostly originated from the long-distance transport, highlighting the importance of joint regional governance.

Effects of the COVID-19 lockdown on criteria air pollutants in the city of Daegu, the epicenter of South Korea's outbreak.

The outbreak of COVID-19 in Daegu, South Korea, early in 2020 has led this metropolitan city to become one of the major hotspots in the world. This study investigates the association of meteorology and the new daily COVID-19 confirmed cases and the effects of the city lockdown on the variation in criteria air pollutants (CAPs) in Daegu. Ambient temperature and relative humidity were negatively correlated to the new daily cases and played an important role in the spread of COVID-19. Wind speed could enhance the virus transmission through the inhalation of aerosols and/or droplets and contact with fomites. The lockdown has directly decreased the concentrations of CAPs. In particular, reductions of 3.75% (PM10), 30.9% (PM2.5), 36.7% (NO2), 43.7% (CO), and 21.3% (SO2) between the period before and during the outbreak were observed over the entire city. An increase in O3 (71.1%) was affected by natural processes and photochemical formation other than the lockdown effects. The three central districts were the areas most affected by the virus and showed the highest reductions in CAPs (except for O3) during the outbreak. Apart from the influence of the lockdown, the decreasing trend in CAPs may be a result of the actions taken by the government to mitigate air pollutants nationwide since 2019. The results of this study can be useful for government and medical organizations to understand the behavior of the virus in the atmosphere. Further studies are necessary to explore the detailed influences of the lockdown on the environment and public life.