Convolutional Neural Networks Facilitate Process Understanding of Megacity Ozone Temporal Variability.

Ozone pollution is profoundly modulated by meteorological features such as temperature, air pressure, wind, and humidity. While many studies have developed empirical models to elucidate the effects of meteorology on ozone variability, they predominantly focus on local weather conditions, overlooking the influences from high-altitude and broader regional meteorological patterns. Here, we employ convolutional neural networks (CNNs), a technique typically applied to image recognition, to investigate the influence of three-dimensional spatial variations in meteorological fields on the daily, seasonal, and interannual dynamics of ozone in Shenzhen, a major coastal urban center in China. Our optimized CNNs model, covering a 13° × 13° spatial domain, effectively explains over 70% of daily ozone variability, outperforming alternative empirical approaches by 7 to 62%. Model interpretations reveal the crucial roles of 2-m temperature and humidity as primary drivers, contributing 16% and 15% to daily ozone fluctuations, respectively. Regional wind fields account for up to 40% of ozone changes during the episodes. CNNs successfully replicate observed ozone temporal patterns, attributing -5-6 µg·m-3 of interannual ozone variability to weather anomalies. Our interpretable CNNs framework enables quantitative attribution of historical ozone fluctuations to nonlinear meteorological effects across spatiotemporal scales, offering vital process-based insights for managing megacity air quality amidst changing climate regimes.

[Impacts of COVID-19 Lockdown on Air Quality in Shenzhen in Spring 2022].

The short-term reduction of air pollutant emissions is an important emergency control measure for avoiding air pollution exceedances in Chinese cities. However, the impacts of short-term emission reductions on the air qualities in southern Chinese cities in spring has not been fully explored. We analyzed the changes in air quality in Shenzhen, Guangdong before, during, and after a city-wide lockdown associated with COVID-19 control during March 14 to 20, 2022. Stable weather conditions prevailed before and during the lockdown, such that local air pollution was strongly affected by local emissions. In-situ measurements and WRF-GC simulations over the Pearl River Delta (PRD) both showed that, due to reductions in traffic emissions during the lockdown, the concentrations of nitrogen dioxide (NO2), respirable particulate matter (PM10), and fine particulate matters (PM2.5) in Shenzhen decreased by (-26±9.5)%, (-28±6.4)%, and (-20±8.2)%, respectively. However, surface ozone (O3) concentration did not change significantly[(-1.0±6.5)%]. TROPOMI satellite observations of formaldehyde and nitrogen dioxide column concentrations indicated that the ozone photochemistry in the PRD in spring 2022 was mainly controlled by the volatile organic compound (VOCs) concentrations and was not sensitive to the reduction in nitrogen oxide (NOx) concentrations. Reduction in NOx may even have increased O3, because the titration of O3 by NOx was weakened. Due to the small spatial-temporal extent of emission reductions, the air quality effects caused by this short-term urban-scale lockdown were weaker than the air quality effects across China during the widespread COVID-19 lockdown in 2020. Future air quality management in South China cities should consider the impacts of NOx emission reduction on ozone and focus on the co-reduction scenarios of NOx and VOCs.

Quantitative evaluation of impacts of the steadiness and duration of urban surface wind patterns on air quality.

The complexity and heterogeneity of urban land surfaces result in inconsistencies in near-surface winds, which in turn influence the diffusion and dispersion of air pollutants. In this study, we classified urban surface wind fields, quantified their steadiness, duration, and influence on air quality using hourly wind observations from 50 meteorological stations, as well as hourly PM2.5 and NO2 concentrations from 18 monitoring stations during 2017-2018 in Shenzhen, a mega city in southern China. We found that the K-means clustering technique was reliable for distinguishing surface wind patterns within the city. Urban surface-wind patterns greatly affected pollutant concentrations. When dominated by calm, northerly wind, high PM2.5/NO2 concentration episodes occurred more frequently than those during other surface wind patterns. The urban surface transport index (USTI) was used to quantify the steadiness of surface wind classes. High pollutant concentrations were present during both high wind speed periods with a large USTI, indicating external pollutant transport, and during low wind speed periods with a small USTI, indicating pollutant accumulation. The threshold durations for surface wind fields (TDSWF) was proposed to quantify the impacts of surface wind persistence on air quality. We found that poor air quality occurred during the first several hours of a dominant wind pattern, indicating that transitions between wind patterns should be a particular focus when assessing air-quality deterioration. USTI and TDSWF are potentially applicable to other urban areas, owing to their clear definitions and simple calculation. In combination with wind speeds, these indices are likely to improve air quality forecasting and strategic decisions on air pollution emergencies, based on long time series of multiple wind and pollutant concentration observations.

The Influence of Air Pollutants and Meteorological Conditions on the Hospitalization for Respiratory Diseases in Shenzhen City, China.

Air pollutants have significant direct and indirect adverse effects on public health. To explore the relationship between air pollutants and meteorological conditions on the hospitalization for respiratory diseases, we collected a whole year of daily major air pollutants' concentrations from Shenzhen city in 2013, including Particulate Matter (PM10, PM2.5), Nitrogen dioxide (NO2), Ozone (O3), Sulphur dioxide (SO2), and Carbon monoxide (CO). Meanwhile, we also gained meteorological data. This study collected 109,927 patients cases with diseases of the respiratory system from 98 hospitals. We investigated the influence of meteorological factors on air pollution by Spearman correlation analysis. Then, we tested the short-term correlation between significant air pollutants and respiratory diseases' hospitalization by Distributed Lag Non-linear Model (DLNM). There was a significant negative correlation between the north wind and NO2 and a significant negative correlation between the south wind and six pollutants. Except for CO, other air pollutants were significantly correlated with the number of hospitalized patients during the lag period. Most of the pollutants reached maximum Relative Risk (RR) with a lag of five days. When the time lag was five days, the annual average of PM10, PM2.5, SO2, NO2, and O3 increased by 10%, and the risk of hospitalization for the respiratory system increased by 0.29%, 0.23%, 0.22%, 0.25%, and 0.22%, respectively. All the pollutants except CO impact the respiratory system's hospitalization in a short period, and PM10 has the most significant impact. The results are helpful for pollution control from a public health perspective.

Are Environmentally Friendly Fireworks Really "Green" for Air Quality? A Study from the 2019 National Day Fireworks Display in Shenzhen.

Fireworks are widely used around the world and can cause severe air pollution over a short period of time. Many efforts have been carried out worldwide to reduce the level of firework-generated air pollution, such as limiting the use of fireworks and developing environmentally friendly fireworks. Research has suggested that the use of environmentally friendly charges in fireworks can reduce emissions, although their impact on ambient air quality has not been quantified. Here, we used a chemical transport model to study the benefits of environmentally friendly fireworks in reducing ambient PM2.5 based on a detailed estimation of emissions from fireworks and dense observations available for simulation validation. Our results showed that environmentally friendly fireworks can reduce ambient PM2.5 by ∼50% (in the range of 15-65% with a "central" value of 35% considering uncertainties) compared with traditional fireworks. However, due to a large number of fireworks used, the air quality still significantly deteriorated, and the effect of using twice the amount of environmentally friendly fireworks on air quality would be comparable to the use of traditional fireworks. Our results indicate that environmentally friendly fireworks are not actually "green". To make them green, the total number of fireworks used at one time must be strictly restricted.

[Characteristics and Meteorological Factors of Complex Nonattainment Pollution of Atmospheric Photochemical Oxidant (Ox) and PM2.5 in the Pearl River Delta Region, China].

Based on the atmospheric pollutant data from twelve monitoring sites in the Guangdong-Hong Kong-Macao Pearl River Delta Regional Air Quality Monitoring Network, the mass concentration trends of atmospheric photochemical oxidants (Ox, NO2+O3) and PM2.5 during 2013-2017 were studied. The complex nonattainment pollution of Ox and PM2.5 is defined as the daily average mass concentration of NO2 and PM2.5 and daily maximum 8 h average (O3 MDA8) mass concentration of O3 simultaneously that exceeds the Chinese grade Ⅱ national air quality standard. The characteristics and meteorological factors that influence the complex nonattainment pollution of Ox and PM2.5 at different types of areas were analyzed. The results indicate that from 2013 to 2017, the annual average mass concentration of PM2.5 in the Pearl River Delta (PRD) region decreased from (44±7) µg·m-3 to (32±4) µg·m-3, which met the annual standard for three consecutive years. The annual average mass concentration of Ox decreased from (127±14) µg·m-3 in 2013 to (114±12) µg·m-3 in 2016 and then showed a general rebound trend to (129±13) µg·m-3 in 2017 when O3 concentrations increased significantly (10 µg·m-3). The proportion of pollution processes with O3 as the primary pollutant increased from 33% in 2013 to 78% in 2017, and the regional characteristics of simultaneous pollution in multiple cities have been highlighted. The complex nonattainment pollution of Ox and PM2.5 occurred 60 times during the study period, primarily in urban sites (78%) and suburban sites (22%). The largest number of days of complex nonattainment pollution occurred in autumn (52%) because of strong solar radiation that was conducive to ozone formation, and consequently, the high oxidization of the atmosphere promoted the secondary generation of PM2.5. The weather conditions that caused the complex nonattainment pollution in the PRD mainly include outflow-high-pressures (43%), subtropical-high-pressures(30%), and tropical-depressions (27%). In terms of specific meteorological conditions, when the temperature was in the range of 20-25℃ and relative humidity was in the range of 60%-75%, the proportion of complex nonattainment pollution was the highest (22%). When O3 pollution was substantial, the high relative humidity and low wind speed during the nighttime caused the concentration of NO2 and PM2.5 to rise significantly, and then the high temperatures during the day aggravated the complex nonattainment pollution.