Air Meteorological Data Research Articles

Differential health and economic impacts from the COVID-19 lockdown between the developed and developing countries: Perspective on air pollution

It is enlightening to determine the discrepancies and potential reasons for the degree of impact from the COVID-19 control measures on air quality as well as the associated health and economic impacts. Analysis of air quality, socio-economic factors, and meteorological data from 447 cities in 46 countries indicated that the COVID-19 control measures had significant impacts on the PM2.5 (particulate matter with an aerodynamic diameter less than 2.5 μm) concentrations in 20 (reduced PM2.5 concentrations of −7.4–29.1 μg m−3) of the selected 46 countries. In these 20 countries, the robustly distinguished changes in the PM2.5 concentrations caused by the control measures differed between the developed (95% confidence interval (CI): −2.7–5.5 μg m−3) and developing countries (95% CI: 8.3–23.2 μg m−3). As a result, the COVID-19 lockdown reduced death and hospital admissions change from the decreased PM2.5 concentrations by 7909 and 82,025 cases in the 12 developing countries, and by 78 and 1214 cases in the eight developed countries. The COVID-19 lockdown reduced the economic cost from the PM2.5 related health burden by 54.0 million dollars in the 12 developing countries and by 8.3 million dollars in the eight developed countries. The disparity was related to the different chemical compositions of PM2.5. In particular, the concentrations of primary PM2.5 (e.g., BC) in cities of developing countries were 3–45 times higher than those in developed countries, so the mass concentration of PM2.5 was more sensitive to the reduced local emissions in developing countries during the COVID-19 control period. The mass fractions of secondary PM2.5 in developed countries were generally higher than those in developing countries. As a result, these countries were more sensitive to the secondary atmospheric processing that may have been enhanced due to reduced local emissions.

Air quality impact of slash pile burns: Simulated geo-spatial impact assessment for Washington State

In the Western U.S., the prescribed burning of woody biomass in forests, mainly harvest slash, is the prevailing practice for in-woods fuel reduction and wildfire mitigation. Though these prescribed burns play an essential role in mitigating the wildfire risks, the resultant emission is a major air pollutants source that adversely affects air quality, negatively impacting human health. With an increased need for fire hazard reduction thinning, coupled with shrinking regional demand for lower quality biomass (pulpwood, hog-fuel, etc.), the volumes of unused biomass left on the forest floor as ‘waste’ will continue to grow. Reducing prescribed burns by utilizing this ‘waste’ biomass for alternate bio-based solutions (like bio-energy or bio-char) will enhance the economic feasibility of much-needed thinning operations and reduce uncontrolled emissions and related environmental and local health impacts.In this study, we simulate the increase in air pollutants due to additional prescribed fires in the Southwestern part of Washington State. Using the ‘BlueSky smoke modeling system,’ the study estimated the emissions associated with burning additional 726,000 dry t of residual biomass, which corresponds to a 30% increment from 2011. The burn was simulated over 29 days of the fall quarter and subsequently incorporated into the AIRPACT pollution transportation modeling system using the 2011 air quality and meteorological data as the baseline. The results showed that the ambient PM2.5 concentrations, due to the simulated pile burns, exceeded EPA's air quality standards on multiple days and in various locations across the Western part of the state, with two days reaching “very unhealthy” levels and one day reaching “hazardous” levels. By layering the census data on top of the pollution concentration data, the model estimated that, over the 29-day burn period, approximately 440,000 additional human days would be affected by higher than the EPA air-quality standards for ambient PM2.5 levels.

Interactive Effects of the Influencing Factors on the Changes of O3 Concentrations Based on GAMs Model in Chengdu

To explore the influence characteristics of the interaction effects between meteorological factors on ozone(O3) concentration in Chengdu, daily air pollutants and meteorological data from 2014 to 2019 were collected. Generalized additive models(GAMs) were adopted to explore the effects of different factors on O3 concentration. The results showed that the relationship between O3 and maximum temperature, sunshine hours, relative humidity, wind speed, precipitation, maximum mixed depth(MMD), and ventilation coefficient(VC) was non-linear. Specifically, the maximum temperature, sunshine hours, MMD, and relative humidity had a significant influence on O3 concentration throughout the year. It is worth noting that the influence of relative humidity and precipitation on O3 concentration during summer was more significant than that for the whole year. In the multi-meteorological factors GAMs of O3 concentration, the meteorological factors mentioned above, except average wind, had significant impacts on O3 concentration change. For the whole year, the judgment coefficient(R2) was 0.849 and the variance explanation rate was 85.1%. The maximum temperature was the most important influencing factor on O3 concentration throughout the year. During summer, corresponding R2 was 0.811 and the explanation rate of variance was 81.3%; however, maximum temperature and MMD were the dominant meteorological factors. In the interaction GAMs, for the whole year, the interaction between maximum temperature and sunshine hours, relative humidity, and precipitation, and the interaction between sunshine hours and MMD had a significant impact on O3 concentrations. The interaction between maximum temperature and sunshine hours played a leading role in changes of O3 concentration. The high temperature+strong radiation+MMD(about 2000 m) +no precipitation were conducive to the formation of O3 concentration, but in summer, only the maximum temperature, sunshine hours, and VC had the most significant effect on the O3 concentration, and strong high temperatures+strong radiation+the little horizontal wind in summer were conducive to the formation of O3 concentration near the surface. In summary, GAMs model can not only be used to identify the dominant influencing factors of O3 pollution, but also quantitatively analyze the influence of single effects and interaction of influencing factors on O3 concentration, which has great significance for the prevention and control of O3 pollution.

The Relationship Between Ambient Air Pollution and Hospitalizations for Gout in a Humid Subtropical Region of China.

ObjectiveGout is a chronic disease caused by the deposition of sodium urate (MSU) crystals. Available data on the association between environmental hazards and gout are scarce. The present study was present to investigate the relationship between short-term exposure to air pollution and hospitalizations for acute gout from 2016 to 2020 in Anqing City, China.MethodsDaily records of hospital admissions for acute gout in Anqing from 1 January 2016 to 31 December 2020 were retrieved from the tertiary first-class hospitals in Anqing. Air pollutants and meteorological data were obtained from the China Environmental Monitoring Station and China Meteorological Data Service Center respectively. We used a time-series analysis to explore the association between air pollution (NO2, O3, and CO) and hospitalizations for acute gout, and conducted stratified analyses by gender, age and season.ResultsWe observed an association between NO2 and hospitalizations for gout (lag 0, relative risk (RR):1.022, 95% confidence interval (CI):1.004–1.041). For every 1 mg/m3 increase in CO concentration, hospitalizations for gout increased by 3.9% (lag 11 days, RR=1.039, 95% CI: 1.004–1.076). Intriguingly, there was a negative association between O3 and hospitalizations for gout (lag0, RR=0.986, 95% CI: 0.976–0.996). Stratified analyses showed that exposure to high levels of NO2 was considered to be more vulnerable to gout in cold season.ConclusionOur study showed that short-term exposure to NO2 and CO has a significant effect on hospitalizations for acute gout.

Prediction of PM2.5 Concentration Based on the LSTM-TSLightGBM Variable Weight Combination Model

PM2.5 is one of the main pollutants that cause air pollution, and high concentrations of PM2.5 seriously threaten human health. Therefore, an accurate prediction of PM2.5 concentration has great practical significance for air quality detection, air pollution restoration, and human health. This paper uses the historical air quality concentration data and meteorological data of the Beijing Olympic Sports Center as the research object. This paper establishes a long short-term memory (LSTM) model with a time window size of 12, establishes a T-shape light gradient boosting machine (TSLightGBM) model that uses all information in the time window as the next period of prediction input, and establishes a LSTM-TSLightGBM model pair based on an optimal weighted combination method. PM2.5 hourly concentration is predicted. The prediction results on the test set show that the mean squared error (MAE), root mean squared error (RMSE), and symmetric mean absolute percentage error (SMAPE) of the LSTM-TSLightGBM model are 11.873, 22.516, and 19.540%, respectively. Compared with LSTM, TSLightGBM, the recurrent neural network (RNN), and other models, the LSTM-TSLightGBM model has a lower MAE, RMSE, and SMAPE, and higher prediction accuracy for PM2.5 and better goodness-of-fit.

Incorporation of Shipping Activity Data in Recurrent Neural Networks and Long Short-Term Memory Models to Improve Air Quality Predictions around Busan Port

Air pollution sources and the hazards of high particulate matter 2.5 (PM2.5) concentrations among air pollutants have been well documented. Shipping emissions have been identified as a source of air pollution; therefore, it is necessary to predict air pollutant concentrations to manage seaport air quality. However, air pollution prediction models rarely consider shipping emissions. Here, the PM2.5 concentrations of the Busan North and Busan New Ports were predicted using a recurrent neural network and long short-term memory model by employing the shipping activity data of Busan Port. In contrast to previous studies that employed only air quality and meteorological data as input data, our model considered shipping activity data as an emission source. The model was trained from 1 January 2019 to 31 January 2020 and predictions and verifications were performed from 1–28 February 2020. Verifications revealed an index of agreements (IOA) of 0.975 and 0.970 and root mean square errors of 4.88 and 5.87 µg/m3 for Busan North Port and Busan New Port, respectively. Regarding the results based on the activity data, a previous study reported an IOA of 0.62–0.84, with a higher predictive power of 0.970–0.975. Thus, the extended approach offers a useful strategy to prevent PM2.5 air pollutant-induced damage in seaports.

DESIGN AND RESULTS OF AN AI-BASED FORECASTING OF AIR POLLUTANTS FOR SMART CITIES

Abstract. This paper presents the design and the results of a novel approach to predict air pollutants in urban environments. The objective is to create an artificial intelligence (AI)-based system to support planning actors in taking effective and adequate short-term measures against unfavourable air quality situations. In general, air quality in European cities has improved over the past decades. Nevertheless, reductions of the air pollutants particulate matter (PM), nitrogen dioxide (NO2) and ground-level ozone (O3), in particular, are essential to ensure the quality of life and a healthy life in cities. To forecast these air pollutants for the next 48 hours, a sequence-to-sequence encoder-decoder model with a recurrent neural network (RNN) was implemented. The model was trained with historic in situ air pollutant measurements, traffic and meteorological data. An evaluation of the prediction results against historical data shows high accordance with in situ measurements and implicate the system’s applicability and its great potential for high quality forecasts of air pollutants in urban environments by including real time weather forecast data.

Long- and short-term air pollution exposure shortens telomere length in a population of hypersusceptible subjects

BACKGROUND AND AIM: Reduction in telomere length (TL) has been documented in subjects affected by age-related diseases (e.g., cancer, cardiovascular diseases) and has been associated to oxidative stress and systemic inflammation, claimed also as potential mechanisms underlying health effects of air pollution exposure, especially particulate matter (PM). We aim to determine the effects of both short- and long-term exposure to PM ≤10µm (PM10) on TL in a well-characterized population (SPHERE project). METHODS: About 1,800 subjects with overweight/obesity were recruited in Milan (Italy) in 2010-2015, completed a questionnaire and donated a 15 mL blood sample. TL was measured (as T/S ratio) by real-time PCR. Each subject was assigned air pollution and meteorological daily data based on his/her residential address. Multivariate mixed-effects linear models with a random intercept on PCR plate were applied. RESULTS:We observed a -2.8% change in TL [95% confidence interval (CI): -5.3; -0.8) per 10 µg/m3 increase in PM10 at the day of blood sampling (lag0). A similar pattern was apparent up to 12 days before recruitment (lag12), with the highest reduction observed at lag6 (-4.3, 95%CI: -6.9; -1.7). When considering moving averages of exposure levels in days preceding recruitment, we observed percent changes in TL ranging from -2.1 (lag0-1) to -8.5 (lag0-12). Long-term PM10 exposure was associated to a -14.9% TL reduction (95%CI: -29.4; -0.5) per 10 µg/m3 increase in annual average PM10 levels. The association between short-term exposure and TL remained practically unchanged when we additionally adjusted for long-term exposure (-6.2%, 95%CI: -11.2; -1.3 at lag0-14). CONCLUSIONS:Our results consistently show that both long- and short-term air pollution exposure shortens TL in a population of hypersusceptible subjects, thus shedding light on the potential mechanisms responsible for the excess of age-related diseases that is known to be associated with air pollution exposure. KEYWORDS: air pollution, particulate matter (PM), telomere length (TL), overweight, obesity, hypersusceptible

Long- and Short-Term Exposures to PM10 Can Shorten Telomere Length in Individuals Affected by Overweight and Obesity.

Reduced telomere length (TL) has been associated with increased risk of age-related diseases, most likely through oxidative stress and inflammation, which have also been claimed as mechanisms underlying health effects of air pollution exposure. We aimed to verify whether exposure to particulate matter with diameter ≤10 µm (PM10) affects TL. We recruited 1792 participants with overweight/obesity in Milan (Italy) in 2010–2015 who completed a structured questionnaire on sociodemographic data, gave a blood sample for TL measurement by real-time PCR, and were assigned air pollution and meteorological data of their residential address. In multivariate mixed-effects linear models (with a random intercept on PCR plate), we observed a −0.51% change in TL (95% confidence interval (CI): −0.98; −0.05)) per 10 µg/m3 increase in PM10 at the day of recruitment. A similar decreasing trend in TL was observed up to two weeks before withdrawal, with percentage changes as low as −1.53% (average exposure of the 12 days before recruitment). Mean annual exposure to PM10 was associated with −2.57% TL reduction (95%CI: −5.06; −0.08). By showing consistent associations between short- and long-term PM10 exposures and reduced TL, our findings shed light on the potential mechanisms responsible for the excess of age-related diseases associated with air pollution exposure.

PM2.5 Concentration Prediction Based on CNN-BiLSTM and Attention Mechanism

The concentration of PM2.5 is an important index to measure the degree of air pollution. When it exceeds the standard value, it is considered to cause pollution and lower the air quality, which is harmful to human health and can cause a variety of diseases, i.e., asthma, chronic bronchitis, etc. Therefore, the prediction of PM2.5 concentration is helpful to reduce its harm. In this paper, a hybrid model called CNN-BiLSTM-Attention is proposed to predict the PM2.5 concentration over the next two days. First, we select the PM2.5 concentration data in hours from January 2013 to February 2017 of Shunyi District, Beijing. The auxiliary data includes air quality data and meteorological data. We use the sliding window method for preprocessing and dividing the corresponding data into a training set, a validation set, and a test set. Second, CNN-BiLSTM-Attention is composed of the convolutional neural network, bidirectional long short-term memory neural network, and attention mechanism. The parameters of this network structure are determined by the minimum error in the training process, including the size of the convolution kernel, activation function, batch size, dropout rate, learning rate, etc. We determine the feature size of the input and output by evaluating the performance of the model, finding out the best output for the next 48 h. Third, in the experimental part, we use the test set to check the performance of the proposed CNN-BiLSTM-Attention on PM2.5 prediction, which is compared by other comparison models, i.e., lasso regression, ridge regression, XGBOOST, SVR, CNN-LSTM, and CNN-BiLSTM. We conduct short-term prediction (48 h) and long-term prediction (72 h, 96 h, 120 h, 144 h), respectively. The results demonstrate that even the predictions of the next 144 h with CNN-BiLSTM-Attention is better than the predictions of the next 48 h with the comparison models in terms of mean absolute error (MAE), root mean square error (RMSE), and coefficient of determination (R2).

Analysis of Complex Pollution and Control of Atmospheric PM2.5 and Ozone in Qinhuangdao

This paper used the air pollutant monitoring data and meteorological observation data to analayse the compound pollution process of PM2.5 and ozone that appeared in Qinhuangdao City from October 8th-11th, 2020. The causes of pollution were analyse from high-altitude situation, meteorological conditions, pollutant conversion and zone transformation. The results showed that this pollution was affected by the high humidity, static stability and regional transmission. The gaseous pollutants were transformed in the strong oxidizing air which further pushed up the concentration of particles.

Spatiotemporal causal convolutional network for forecasting hourly PM2.5 concentrations in Beijing, China

Air pollution in Northeastern Asia is a serious environmental problem, especially in China where PM2.5 levels are quite high. Accurate PM2.5 predictions are significant to environmental management and human health. Recently, deep learning has received increasing attention from relevant researchers. In this work, a spatiotemporal causal convolutional neural network (ST-CausalConvNet) for short-term PM2.5 prediction is proposed. The distinguishing characteristics of the proposed model is that the convolutions in the model architecture are causal, where an output at a certain time step is convolved only with elements from the same or earlier time steps in the previous layer. Accordingly, no information leakage is induced from the future to the past in this model. The spatial dependence between multiple monitoring stations was also considered in the model. Spatiotemporal correlation analysis was performed to select relevant information from monitoring stations that have a high relationship with the target station. The information from the target and related stations were then employed as the inputs and fed into the model. A case study from May 1, 2014 to April 30, 2015 in Beijing, China was conducted. The next hour PM2.5 concentration was predicted by the proposed model by using historical air quality and meteorological data from 36 monitoring stations. Experimental results show that the trends of the predicted PM2.5 concentrations and the observed values were consistent. The proposed method achieved a better prediction performance than the other three comparative models, namely artificial neural network (ANN), gated recurrent unit (GRU), and long short-term memory (LSTM). Furthermore, the effects of the important parameters and the model transferability were also conducted. We conclude that the proposed ST-CausalConvNet is a potential effective model for air pollution forecasting.

GIS-based geostatistical approaches study on spatial-temporal distribution of ozone and its sources in hot, arid climates

Ambient ozone (O3) is a critical atmospheric pollutant with significant potential threats to human health and the environment. Geographic information systems (GIS) techniques have opened up a wide range of methods for the assessment of health risks associated with pollutant exposure in urban environments. Accordingly, this study aimed to identify the sources and spatial-temporal distribution of O3 in regions under hot, arid climates. GIS-based geostatistical interpolation approaches were applied to analyze and locate the sources and spatial-temporal distribution of O3 in the state of Kuwait, which was taken as a case study. The spatial distribution of O3 in Kuwait was mapped using GIS functions. Hourly observation data for O3 concentration along with air pollutants and meteorological condition data for five years were collected from four air-monitoring stations representing open, residential, industrial, and commercial areas. To evaluate the accuracy of several spatial interpolation approaches, O3 concentration was estimated using the inverse distance weighted (IDW) and kriging approaches. Both attribute and geographic data were analyzed and mapped along with meteorological data to investigate the sources and the spatial-temporal distribution of O3. The results showed the O3 and NO2 concentrations during the four seasons were less than that in the regional and international limits. Seasonal spatial variability showed that the opposite trend of variations between O3 and NO2 recorded high concentrations in the summer and spring seasons for O3, while it was in the winter and autumn seasons for NO2. A high correlation was found between O3 pollutants and meteorological parameters. The highest O3 concentration was recorded in the summer season, followed by spring. The minimum O3 concentration was during the winter season. The concentrations of NO during the summer and spring seasons were lower than during the winter and autumn seasons. The strongest correlation was found between O3 and NO2 during the summer and autumn in the four regions.

Effect of Air Quality on the Risk of Emergency Room Visits in Patients With Atrial Fibrillation.

Background: We investigated the effect of particulate matter with aerodynamic diameter <2.5 μm (PM2.5) and meteorological conditions on the risk of emergency room visits in patients with atrial fibrillation (AF) in Beijing, which is considered as a monsoon climate region.Methods: In this case-crossover design study, medical records from patients with AF who visited the Critical Care Center in the Emergency Department of Anzhen Hospital from January 2011 through December 2014 and air quality and meteorological data of Beijing during the same period were collected and analyzed using Cox regression and time-series autocorrelation analyses.Results: A total of 8,241 patients were included. When the average PM2.5 concentration was >430 μg/m3, the risk of emergency room visits for patients with uncomplicated AF, AF combined with cardiac insufficiency, and AF combined with rheumatic heart disease increased by 12, 12, and 40%, respectively. When the average PM2.5 concentration was >420 μg/m3, patients with AF combined with diabetes mellitus had a 75% increased risk of emergency room visits, which was the largest increase in risk among all types of patients with AF. When the average PM2.5 concentration was >390 μg/m3, patients with AF combined with acute coronary syndrome had an approximately 30% increased risk of emergency room visits, which was the highest and fastest increase in risk among all types of patients with AF. The risk of emergency room visits for patients with AF was positively correlated with air quality as the time lag proceeded, with an autocorrelation coefficient of 0.223 between the risk of emergency room visits and air quality in patients with AF on day 6 of the time lag.Conclusion: Exposure to certain concentrations of PM2.5 in a monsoon climate region significantly increased the risk of emergency room visits in patients with AF.

Providing an accurate global model for monthly solar radiation forecasting using artificial intelligence based on air quality index and meteorological data of different cities worldwide.

This study aims to present an exact model for predicting solar radiation worldwide through a general model. In this study, mean monthly global solar radiation would have been predicted by applying artificial intelligence methods including artificial neural network, adaptive neuro-fuzzy inference system and hybrid genetic algorithm for different cities worldwide. Investigating different models under various situations showed that the adaptive neuro-fuzzy inference system created the most accurate and precise model for predicting solar radiation. Statistics indexes, such as the determination coefficient, mean absolute percentage error, root mean square error and mean bias error, for the best model selected are 0.999, 5.50E-04, 5.90E-05 and 0.425, respectively. It can be claimed that according to the amount of the statistical indexes, which was mentioned above, the provided model has approximately more formidable accuracy and credibility in comparison with other models, which other researchers did.

Changes in air pollutants during the COVID-19 lockdown in Beijing: Insights from a machine-learning technique and implications for future control policy

The COVID-19 lockdowns led to abrupt reductions in human-related emissions worldwide and had an unintended impact on air quality improvement. However, quantifying this impact is difficult as meteorological conditions may mask the real effect of changes in emissions on the observed concentrations of pollutants. Based on the air quality and meteorological data at 35 sites in Beijing from 2015 to 2020, a machine learning technique was applied to decouple the impacts of meteorology and emissions on the concentrations of air pollutants. The results showed that the real (“deweathered”) concentrations of air pollutants (expect for O3) dropped significantly due to lockdown measures. Compared with the scenario without lockdowns (predicted concentrations), the observed values of PM2.5, PM10, SO2, NO2, and CO during lockdowns decreased by 39.4%, 50.1%, 51.8%, 43.1%, and 35.1%, respectively. In addition, a significant decline for NO2 and CO was found at the background sites (51% and 37.8%) rather than the traffic sites (37.1% and 35.5%), which is different from the common belief. While the primary emissions reduced during the lockdown period, episodic haze events still occurred due to unfavorable meteorological conditions. Thus, developing an optimized strategy to tackle air pollution in Beijing is essential in the future.摘要基于2015–2020年北京35个环境空气站和20个气象站观测资料, 应用机器学习方法 (随机森林算法) 分离了气象条件和源排放对大气污染物浓度的影响. 结果发现, 为应对疫情采取的隔离措施使北京2020年春节期间大气污染物浓度降低了35.1%–51.8%; 其中, 背景站氮氧化物和一氧化碳浓度的降幅最大, 超过了以往报道较多的交通站点. 同时, 2020年春节期间的气象条件不利于污染物扩散, 导致多次霾污染事件发生.为进一步改善北京空气质量, 未来需要优化减排策略.

Analysis of temporal spatial distribution characteristics of PM2.5 pollution and the influential meteorological factors using Big Data in Harbin, China

ABSTRACT Based on the monitoring data of atmospheric pollutants and the meteorological data in Harbin in 2017, the temporal spatial distribution characteristics of PM2.5 pollution and the relationships between PM2.5 concentration and meteorological factors in this region were analyzed. The PM2.5 concentration data and the meteorological data in 2017 were comprehensively analyzed by using ArcGIS and R. The results show that spatially, the PM2.5 concentration in the central districts of Harbin are high in the southeast and low in the northwest; temporally, PM2.5 pollution is most serious in autumn and winter, with multiple spells of heavy pollution and an obvious “weekend effect”, while the air quality is better in spring and summer; overall, relative humidity is positively correlated to PM2.5 concentration, while temperature, wind direction, and wind speed are negatively correlated to PM2.5 mass concentration, and low wind speed and high relative humidity are major contributors to increase of PM2.5 concentration. Implications: Highlight: The use of big data to deal with the data of air pollution and meteorology. Key points: The air pollution data of Harbin in autumn and winter is more serious than that in spring and summer, and is closely related to meteorological factors. Attraction: Big data is used to process air pollution data and meteorological data, and R language is used to describe the relationship between them.

Modeling of atmospheric particulate matters via artificial intelligence methods.

Nowadays, pollutants continue to be released into the atmosphere in increasing amounts with each passing day. Some of them may turn into more harmful forms by accumulating in different layers of the atmosphere at different times and can be transported to other regions with atmospheric events. Particulate matter (PM) is one of the most important air pollutants in the atmosphere, and it can be released into the atmosphere by natural and anthropogenic processes or can be formed in the atmosphere as a result of chemical reactions. In this study, it was aimed to predict PM10 and PM2.5 components measured in an industrial zone selected by adaptive neuro-fuzzy inference system (ANFIS), support vector regression (SVR), classification and regression trees (CART), random forest (RF), k-nearest neighbor (KNN), and extreme learning machine (ELM) methods. To this end, in the first stage of the study, the dataset consisting of air pollutants and meteorological data was created, the temporal and qualitative evaluation of these data was performed, and the PM (PM10 and PM2.5) components were modeled using the "R" software environment by artificial intelligence methods. The ANFIS model was more successful in predicting the PM10 (R2 = 0.95, RMSE = 5.87, MAE = 4.75) and PM2.5 (R2 = 0.97, RMSE = 3.05, MAE = 2.18) values in comparison with other methods. As a result of the study, it was clearly observed that the ANFIS model could be used in the prediction of air pollutants.

The Association between Preterm Birth and Ambient Air Pollution Exposure in Shiyan, China, 2015-2017.

Shortening of the gestational duration has been found associated with ambient air pollution exposure. However, the critical exposure windows of ambient air pollution for gestational duration remain inconsistent, and the association between ambient air pollution and early term births (ETB, 37 to 38 weeks) has rarely been studied relative to preterm births (PTB, 28–37 weeks). A time-series study was conducted in Shiyan, a medium-sized city in China. Birth information was collected from the Shiyan Maternity and Child Health Hospital, and 13,111 pregnant women who gave birth between 2015 and 2017 were included. Data of the concentrations of air pollutants, including PM10, PM2.5, NO2, and SO2 and meteorological data, were collected in the corresponding gestational period. The Cox regression analysis was performed to estimate the relationship between ambient air pollution exposure and the risk of preterm birth after controlling the confounders, including maternal age, education, Gravidity, parity, fetal gender, and delivery mode. Very preterm birth (VPTB, 28–32 weeks) as a subtype of PTB was also incorporated in this study. The risk of VPTB and ETB was positively associated with maternal ambient air pollution exposure, and the correlation of gaseous pollutants was stronger than particulate matter. With respect to exposure windows, the critical trimester of air pollutants for different adverse pregnancy outcomes was different. The exposure windows of PM10, PM2.5, and SO2 for ETB were found in the third trimester, with HRs (hazard ratios) of 1.06 (95%CI: 1.04, 1.09), 1.07 (95%CI: 1.04, 1.11), and 1.28 (95%CI: 1.20, 1.35), respectively. However, for NO2, the second and third trimesters exhibited similar results, the HRs reaching 1.10 (95%CI: 1.03, 6.17) and 1.09 (95%CI: 1.03,1.15), respectively. This study extends and strengthen the evidence for a significant correlation between the ambient air pollution exposure during pregnancy and the risk of not only PTB but, also, ETB. Moreover, our findings suggest that the exposure windows during pregnancy vary with different air pollutants and pregnancy outcomes.

Considering Condensable Particulate Matter Emissions Improves the Accuracy of Air Quality Modeling for Environmental Impact Assessment

This study examines environmental impact assessment considering filterable particulate matter (FPM) and condensable particulate matter (CPM) to improve the accuracy of the air quality model. Air pollutants and meteorological data were acquired from Korea’s national monitoring station near a residential development area in the target district and background site. Seasonal emissions of PM2.5, including CPM, were estimated using the California puff (CALPUFF) model, based on Korea’s national emissions inventory. These results were compared with the traditional environmental impact assessment results. For the residential development area, the seasonal PM2.5 concentration was predicted by considering FPM and CPM emissions in the target area as well as the surrounding areas. In winter and spring, air quality standards were not breached because only FPM was considered. However, when CPM was included in the analysis, the results exceeded the air quality standards. Furthermore, it was predicted that air quality standards would not be breached in summer and autumn, even when CPM is included. In other words, conducting an environmental impact assessment on air pollution including CPM affects the final environmental decision. Therefore, it is concluded that PM2.5 should include CPM for greater accuracy of the CALPUFF model for environmental impact assessment.