Quantifying source contributions to ambient NH3 using Geo-AI with time lag and parcel tracking functions.

Ambient ammonia (NH3) plays an important compound in forming particulate matters (PMs), and therefore, it is crucial to comprehend NH3's properties in order to better reduce PMs. However, it is not easy to achieve this goal due to the limited range/real-time NH3 data monitored by the air quality stations. While there were other studies to predict NH3 and its source apportionment, this manuscript provides a novel method (i.e., GEO-AI)) to look into NH3 predictions and their contribution sources. This study represents a pioneering effort in the application of a novel geospatial-artificial intelligence (Geo-AI) base model with parcel tracking functions. This innovative approach seamlessly integrates various machine learning algorithms and geographic predictor variables to estimate NH3 concentrations, marking the first instance of such a comprehensive methodology. The Shapley additive explanation (SHAP) was used to further analyze source contribution of NH3 with domain knowledge. From 2016 to 2018, Taichung's hourly average NH3 values were predicted with total variance up to 96%. SHAP values revealed that waterbody, traffic and agriculture emissions were the most significant factors to affect NH3 concentrations in Taichung among all the characteristics. Our methodology is a vital first step for shaping future policies and regulations and is adaptable to regions with limited monitoring sites.

A machine learning-based ensemble model for estimating diurnal variations of nitrogen oxide concentrations in Taiwan.

Air pollution is inextricable from human activity patterns. This is especially true for nitrogen oxide (NOx), a pollutant that exists naturally and also as a result of anthropogenic factors. Assessing exposure by considering diurnal variation is a challenge that has not been widely studied. Incorporating 27 years of data, we attempted to estimate diurnal variations in NOx across Taiwan. We developed a machine learning-based ensemble model that integrated hybrid kriging-LUR, machine-learning, and an ensemble learning approach. Hybrid kriging-LUR was performed to select the most influential predictors, and machine-learning algorithms were applied to improve model performance. The three best machine-learning algorithms were suited and reassessed to develop ensemble learning that was designed to improve model performance. Our ensemble model resulted in estimates of daytime, nighttime, and daily NOx with high explanatory powers (Adj-R2) of 0.93, 0.98, and 0.94, respectively. These explanatory powers increased from the initial model that used only hybrid kriging-LUR. Additionally, the results depicted the temporal variation of NOx, with concentrations higher during the daytime than the nighttime. Regarding spatial variation, the highest NOx concentrations were identified in northern and western Taiwan. Model evaluations confirmed the reliability of the models. This study could serve as a reference for regional planning supporting emission control for environmental and human health.

Estimating morning and evening commute period O3 concentration in Taiwan using a fine spatial-temporal resolution ensemble mixed spatial model with Geo-AI technology.

Elevated levels of ground-level ozone (O3) can have harmful effects on health. While previous studies have focused mainly on daily averages and daytime patterns, it's crucial to consider the effects of air pollution during daily commutes, as this can significantly contribute to overall exposure. This study is also the first to employ an ensemble mixed spatial model (EMSM) that integrates multiple machine learning algorithms and predictor variables selected using Shapley Additive exExplanations (SHAP) values to predict spatial-temporal fluctuations in O3 concentrations across the entire island of Taiwan. We utilized geospatial-artificial intelligence (Geo-AI), incorporating kriging, land use regression (LUR), machine learning (random forest (RF), categorical boosting (CatBoost), gradient boosting (GBM), extreme gradient boosting (XGBoost), and light gradient boosting (LightGBM)), and ensemble learning techniques to develop ensemble mixed spatial models (EMSMs) for morning and evening commute periods. The EMSMs were used to estimate long-term spatiotemporal variations of O3 levels, accounting for in-situ measurements, meteorological factors, geospatial predictors, and social and seasonal influences over a 26-year period. Compared to conventional LUR-based approaches, the EMSMs improved performance by 58% for both commute periods, with high explanatory power and an adjusted R2 of 0.91. Internal and external validation procedures and verification of O3 concentrations at the upper percentile ranges (in 1%, 5%, 10%, 15%, 20%, and 25%) and other conditions (including rain, no rain, weekday, weekend, festival, and no festival) have demonstrated that the models are stable and free from overfitting issues. Estimation maps were generated to examine changes in O3 levels before and during the implementation of COVID-19 restrictions. These findings provide accurate variations of O3 levels in commute period with high spatiotemporal resolution of daily and 50m * 50m grid, which can support control pollution efforts and aid in epidemiological studies.

Evaluating long-term and high spatiotemporal resolution of wet-bulb globe temperature through land-use based machine learning model.

BACKGROUND: The increase in global temperature and urban warming has led to the exacerbation of heatwaves, which negatively affect human health and cause long-term loss of work productivity. Therefore, a global assessment in temperature variation is essential. OBJECTIVE: This paper is the first of its kind to propose land-use based spatial machine learning (LBSM) models for predicting highly spatial-temporal variations of wet-bulb globe temperature (WBGT), which is a heat stress indicator used to assess thermal comfort in indoor and outdoor environments, specifically for the main island of Taiwan. METHODS: To develop spatiotemporal prediction models for both the working period and noon period, we calculated the WBGT of each weather station from 2001 to 2019 using temperature, humidity, and solar radiation data. These WBGT estimations were then used as the dependent variable for developing the spatiotemporal prediction models. To enhance model performance, we used innovative approaches that combined SHapley Additive exPlanations (SHAP) values for the selection of non-linear variables, along with machine learning algorithms for model development. RESULTS: When incorporating temperature along with other land-use/land cover predictor variables, the performance of LBSM models was excellent, with an R2 value of up to 0.99. The LBSM models explained 98% and 99% of the spatial-temporal variations in WBGT for the working and noon periods, respectively, within the complete models. In the temperature-excluded models, the explained variances were 94% and 96% for the working and noon periods, respectively. IMPACT: WBGT is a common method used by many organizations to access the impact of heat stress on human beings. However, limited studies have mentioned the association between WBGT and health impacts due to the absence of spatiotemporal databases. This study develops a new approach using land-use-based spatial machine learning (LBSM) models to better predict the fine spatial-temporal WBGT levels, with a 50-m × 50-m grid resolution for both working time and noontime. Our proposed methodology could be used in future studies aimed at evaluating the potential long-term loss of work productivity due to the effects of global warming or urban heat island.

Characterization of the sources and health risks of polycyclic aromatic hydrocarbons in PM2.5 and their relationship with black carbon: A case study in northern Taiwan.

Polycyclic aromatic hydrocarbons (PAHs) and black carbon (BC) often coexist in PM2.5 because both form during the incomplete combustion of organic matter. These compounds are regarded as hazardous air pollutants with potential health effects, including respiratory and cardiovascular effects. In this study, to evaluate the health risks of PAHs and BC at an urban site in northern Taiwan, 16 priority PAHs and BC, identified by the United States Environmental Protection Agency, were analyzed and quantified in PM2.5 to determine their concentrations, their relationship with each other, and their likely sources. The results indicated that the mean concentrations of total PAHs and BC were 0.91 ng m-3 and 0.97 µg m-3, respectively, with a significant positive correlation between them, indicating the same emission sources. The results also indicated that fossil fuel combustion and traffic emissions were primary contributors to PAHs, with wood and biomass combustion playing a less prominent role. Among these 16 priority PAHs, benzo[a]pyrene, dibenz[a,h]anthracene, benzo[b]fluoranthene, and indeno[1,2,3-cd]pyrene served as major carcinogenic compounds, accounting for 89.0% of the total carcinogenic toxicity. Thus, the lifetime excess cancer risk resulting from PAH exposure was estimated as 8.03 × 10-6, indicating a potential carcinogenic risk to human health at the sampling site. Overall, this study highlights the need for future mitigation policies for traffic emissions and fossil fuel combustion for reducing the local emissions of BC and co-produced PAHs in northern Taiwan.

Spatial distributions of PM10-bound metal elements in the central part of western Taiwan and their potential emission sources and the carcinogenic health risks.

This study aimed to investigate the spatial distribution of metal elements in PM10 and their potential sources and associated health risks over a period of two years in eight locations in the central part of western Taiwan. The study revealed that the mass concentration of PM10 and the total mass concentration of 20 metal elements in PM10 were 39.0 µg m-3 and 4.74 µg m-3, respectively, with total metal elements accounting for approximately 13.0% of PM10. Of the total metal elements, 95.6% were crustal elements (Al, Ca, Fe, K, Mg, and Na), with trace elements (As, Ba, Cd, Cr, Co, Cu, Ga, Mn, Ni, Pb, Sb, Se, V, and Zn) contributing only 4.4%. Spatially, the inland areas exhibited higher PM10 concentrations due to lee-side topography and low wind speeds. In contrast, the coastal regions exhibited higher total metal concentrations because of the dominance of crustal elements from sea salt and crustal soil. Four primary sources of metal elements in PM10 were identified as sea salt (58%), re-suspended dust (32%), vehicle emissions and waste incineration (8%), and industrial emissions and power plants (2%). The positive matrix factorization (PMF) analysis results indicated that natural sources like sea salt and road dust contributed up to 90% of the total metal elements in PM10, while only 10% was attributed to human activities. The excess cancer risks (ECRs) associated with As, Co, and Cr(VI) were greater than 1 × 10-6, and the total ECR was 6.42 × 10-5. Although only 10% of total metal elements in PM10 came from human activities, they contributed to 82% of the total ECR.

Estimating the daily average concentration variations of PCDD/Fs in Taiwan using a novel Geo-AI based ensemble mixed spatial model.

It is generally established that PCDD/Fs is harmful to human health and therefore extensive field research is necessary. This study is the first to use a novel geospatial-artificial intelligence (Geo-AI) based ensemble mixed spatial model (EMSM) that integrates multiple machine learning algorithms and geographic predictor variables selected using SHapley Additive exPlanations (SHAP) values to predict spatial-temporal fluctuations in PCDD/Fs concentrations across the entire island of Taiwan. Daily PCDD/F I-TEQ levels from 2006 to 2016 were used for model construction, while external data was used for validating model dependability. We utilized Geo-AI, incorporating kriging, five machine learning, and ensemble methods (combinations of the aforementioned five models) to develop EMSMs. The EMSMs were used to estimate long-term spatiotemporal variations in PCDD/F I-TEQ levels, considering in-situ measurements, meteorological factors, geospatial predictors, social and seasonal influences over a 10-year period. The findings demonstrated that the EMSM was superior to all other models, with an increase in explanatory power reaching 87 %. The results of spatial-temporal resolution show that the temporal fluctuation of PCDD/F concentrations can be a result of weather circumstances, while geographical variance can be the result of urbanization and industrialization. These results provide accurate estimates that support pollution control measures and epidemiological studies.

Structured Cluster Detection from Local Feature Learning for Text Region Extraction.

The detection of regions of interest is commonly considered as an early stage of information extraction from images. It is used to provide the contents meaningful to human perception for machine vision applications. In this work, a new technique for structured region detection based on the distillation of local image features with clustering analysis is proposed. Different from the existing methods, our approach takes the application-specific reference images for feature learning and extraction. It is able to identify text clusters under the sparsity of feature points derived from the characters. For the localization of structured regions, the cluster with high feature density is calculated and serves as a candidate for region expansion. An iterative adjustment is then performed to enlarge the ROI for complete text coverage. The experiments carried out for text region detection of invoice and banknote demonstrate the effectiveness of the proposed technique.

Using cluster algorithms with a machine learning technique and PMF models to quantify local-specific origins of PM2.5 and associated metals in Taiwan.

The influence of long-range transport (LRT) of air pollutants on neighboring regions and countries has been documented. The magnitude of LRT aerosols and related constituents can misdirect control strategies for local air quality management. In this study, we aimed to quantify PM2.5 (diameter less than 2.5 µm, PM2.5) and associated metals derived from local sources and LRT in different geographic locations in Taiwan using advanced receptor models. We collected daily PM2.5 samples (n = âˆ¼1000) and analyzed 28 metals every three days from 2016 to 2018 in the northern, central-south, eastern, and southern areas of Taiwan. We first used a machine learning technique with a cluster algorithm coupled with a backward trajectory to classify local, regional, and LRT-related aerosols. We then quantified the source contributions with a positive matrix factorization (PMF) model for Taiwan weighted by region-specific populations. The northern and eastern regions were found to be more vulnerable to LRT-related PM2.5 and metals than the central-south and southern regions in Taiwan. The LRT increased Pb and As concentrations by 90-200% and ∼40% in the northern and central-south regions. Ambient PM2.5-metals mainly originated from local traffic-related emissions in the northern, central-south, and southern regions, whereas oil combustion was the primary source of PM2.5-metals in the eastern region. By subtracting the influence from the LRT, the contributions of domestic emission sources to ambient PM2.5 metals in Taiwan were 35% from traffic-related emission, 17% from non-ferrous metallurgy, 13% from iron ore and steel factories, 12% from coal combustion, 12% from oil combustion, 10% from incinerator emissions, and <1% from cement manufacturing emissions. This study proposed an advanced method for refining local source contributions to ambient PM2.5 metals in Taiwan, which provides useful information on regional control strategies.

How a winding-down oil refinery park impacts air quality nearby?

It is always difficult to compare, let alone estimate, the difference of air pollutant concentrations before and after closure of a major source because the pollutants cannot be traced or predicted after entering the ambient. Indeed, we are not aware of any studies specifically related to the air pollutants impacted by a winding-down source. In this work, we applied nine years (2010-2018) online measurement of air pollutants (including PM10, PM2.5, NO2, SO2, O3 and VOCs) to investigate (i) the temporal behavior of air pollutants before and after closure of an oil refinery park by using pair-wise statistics and correlations between wind speed and direction, and (ii) the source impacts on O3 concentrations using PMF coupled with multiple linear regression (MLR) analysis (PMF-MLR). Example applications are presented at two monitoring sites (A and B) close to the Kaohsiung Oil Refinery (KOR), located in the southern industrial city of Taiwan. The results show that the KOR shutdown changed air pollutant concentrations to a certain extent in these study areas. We also conclude that, instead of using propylene-equivalent and ozone formation potential (OFP) concentrations, it is better to estimate the formation of O3 based on PMF-MLR analysis as developed in this study. The PMF analysis has identified various VOCs sources at both sites including solvent usage, petrochemical industrial sources, industrial emissions, vehicle-related sources, vegetation emissions and aged air-masses. Also, the MLR model shows that both the background sources and petrochemical industrial sources may significantly change O3 concentrations.

A mixed spatial prediction model in estimating spatiotemporal variations in benzene concentrations in Taiwan.

It is well known benzene negatively impacts human health. This study is the first to predict spatial-temporal variations in benzene concentrations for the entirety of Taiwan by using a mixed spatial prediction model integrating multiple machine learning algorithms and predictor variables selected by Land-use Regression (LUR). Monthly benzene concentrations from 2003 to 2019 were utilized for model development, and monthly benzene concentration data from 2020, as well as mobile monitoring vehicle data from 2009 to 2019, served as external data for verifying model reliability. Benzene concentrations were estimated by running six LUR-based machine learning algorithms; these algorithms, which include random forest (RF), deep neural network (DNN), gradient boosting (GBoost), light gradient boosting (LightGBM), CatBoost, extreme gradient boosting (XGBoost), and ensemble algorithms (a combination of the three best performing models), can capture how nonlinear observations and predictions are related. The results indicated conventional LUR captured 79% of the variability in benzene concentrations. Notably, the LUR with ensemble algorithm (GBoost, CatBoost, and XGBoost) surpassed all other integrated methods, increasing the explanatory power to 92%. This study establishes the value of the proposed ensemble-based model for estimating spatiotemporal variation in benzene exposure.

Living proximity to petrochemical industries and the risk of attention-deficit/hyperactivity disorder in children.

Evidence regarding the negative neurodevelopmental effects of compound exposure to petrochemicals remains limited. We aimed to evaluate the association between exposure to petrochemical facilities and generated emissions during early life and the risk of attention-deficit/hyperactivity disorder (ADHD) development in children. We conducted a population-based birth cohort study using the 2004 to 2014 Taiwanese Birth Certificate Database and verified diagnoses of ADHD using the National Health Insurance Database. The level of petrochemical exposure in each participant's residential township was evaluated using the following 3 measurements: distance to the nearest petrochemical industrial plant (PIP), petrochemical exposure probability (accounting for monthly prevailing wind measurements), and monthly benzene concentrations estimated using kriging-based land-use regression models. We applied Cox proportional hazard models to evaluate the association. During the study period, 48,854 out of 1,863,963 children were diagnosed as having ADHD. The results revealed that residents of townships in close proximity to PIPs (hazard ratio [HR] = 1.20, 95% confidence interval [CI]: 1.16-1.23, <3 vs. ≥10 km), highly affected by petrochemical-containing prevailing winds (HR = 1.12, 95% CI: 1.08-1.16, ≥40% vs. <10%), and with high benzene concentrations (HR = 1.26, 95% CI: 1.23-1.29, ≥0.75 vs. <0.55 ppb) were consistently associated with the increased risk of ADHD development in children. The findings of the sensitivity analysis remained robust, particularly for the 2004 to 2009 birth cohort and for models accounting for a longer duration of postnatal exposure. This work provided clear evidence that living near petrochemical plants increases the risk of ADHD development in children. Further studies are warranted to confirm our findings.

A hybrid methodology to quantitatively identify inorganic aerosol of PM2.5 source contribution.

It is difficult to identify inorganic aerosol (IA) (primary and secondary), the main component of PM2.5, without the significant tracers for sources. We are not aware of any studies specifically related to the IA's local contribution to PM2.5. To effectively reduce the IA load, however, the contribution of local IA sources needs to be identified. In this work, we developed a hybrid methodology and applied online measurement of PM2.5 and the associated compounds to (1) classify local and long-range transport PM2.5, (2) identify sources of local PM2.5 using PMF model, and (3) quantify local source contribution to IA in PM2.5 using regression analysis. Coal combustion and iron ore and steel industry contributed the most amount of IA (~42.7%) in the study area (City of Taichung), followed by 32.9% contribution from oil combustion, 8.9% from traffic-related emission, 4.6% from the interactions between agrochemical applications and combustion sources (traffic-related emissions and biomass burning), and 2.3% from biomass burning. The methodology developed in this study is an important preliminary step for setting up future control policies and regulations, which can also be applied to any other places with serious local air pollution.

Proximity to petrochemical industrial parks and risk of chronic glomerulonephritis.

This study determined whether individuals residing near petrochemical industrial parks (PIPs) have a higher risk of chronic glomerulonephritis (CGN). We performed population-based 1:4 case-control study by using Taiwan's National Health Insurance Research Database from 2000 to 2016. The subjects were aged 20-65 years, residing in western Taiwan, and did not have a history of any renal or urinary system disease in 2000. The case cohort included those who had at least three outpatient visits or one hospitalization between 2001 and 2016 with codes for CGN as per International Classification of Diseases (ICD)-Ninth and Tenth Revisions. Controls were randomly sampled age-, sex-, and urbanization-matched individuals without renal and urinary system diseases. Petrochemical exposure was evaluated by the distance to the nearest PIP of the residential township, and petrochemical exposure probability was examined considering the monthly prevailing wind direction. Conditional logistic regression was used to determine the association between petrochemical exposure and CGN risk. A total of 320,935 subjects were included in the final analysis (64,187 cases and 256,748 controls). After adjustment for potential confounders, living in townships within a 3-km radius of PIPs was associated with a higher risk of CGN (adjusted odds ratio [aOR] = 1.32, 95% confidence interval [CI] = 1.28-1.37). Compared with townships more than 20 km away from PIPs, those within 10 km of PIPs were associated with significantly increased risks of CGN in a dose-dependent manner. When prevailing wind was considered, townships with high exposure probability were associated with a significantly increased risk of CGN. We found that those residing near PIPs or with high petrochemical exposure probability had a higher risk of CGN. These findings highlight the need for monitoring environmental nephrotoxic substances and the renal health of residents living near PIPs.

An integrated strategy by using long-term monitoring data to identify volatile organic compounds of high concern near petrochemical industrial parks.

Exposure to ambient volatile organic compounds (VOCs) is associated with a risk of cancer in the residents living near petrochemical facilities. However, research on the contribution of different VOCs to the lifetime cancer risk remains inconclusive. The variability in source emissions, geographical locations, seasons, and meteorological conditions can be assessed through long-term measurement of ambient VOCs with a wide spatial distribution, thus reducing the uncertainty of health risk assessment from source emissions. This study analyzed comprehensive measurement data of 109 VOCs at 17 monitoring stations around petrochemical industrial parks, collected once every six days during 2015-2018 by the Taiwan Environmental Protection Agency. We calculated the annual mean concentration of selected VOCs and then integrated the probability risk assessment (PRA) and positive matrix factorization (PMF) models to identify the sources of VOCs of high concern. First, we prioritized 12 out of 23 carcinogenic VOCs based on the PRA results. Further, the results obtained from the PMF model revealed that petrochemical industrial parks contributed to more than 50% of the emissions of six VOCs, namely 1,3-butadiene, benzene, 1,2-dichloroethane, chloroform, vinyl chloride, and acrylonitrile, measured at a few monitoring stations. This integrated approach can help regulatory agencies to efficiently propose control strategies on the emissions of VOCs of high concern, thereby reducing the population's health risk.

Effectiveness of palonosetron versus granisetron in preventing chemotherapy-induced nausea and vomiting: a systematic review and meta-analysis.

PURPOSE: Chemotherapy-induced nausea and vomiting (CINV) commonly occurs after chemotherapy, adversely affecting patients' quality of life. Recently, studies have shown inconsistent antiemetic effects of two common 5-hydroxytryptamine 3 receptor antagonists, namely, palonosetron and granisetron. Therefore, we conducted a meta-analysis to evaluate the effectiveness of palonosetron versus granisetron in preventing CINV. METHODS: Relevant studies were obtained from PubMed, Embase, and Cochrane databases. The primary outcome was the complete response (CR) rate. Secondary outcomes were headache and constipation events. RESULTS: In total, 12 randomized controlled trials and five retrospective studies were reviewed. Palonosetron was consistently statistically superior to granisetron in all phases in terms of the CR rate (acute phases: odds ratio [OR] = 1.28, 95% confidence interval [CI] = 1.06-1.54; delayed phases: OR = 1.38, 95% CI = 1.13-1.69; and overall phases: OR = 1.37, 95% CI = 1.17-1.60). Moreover, a non-significant difference was found between the two groups in terms of the headache event, but the occurrence of the constipation event was lower in the granisetron group than in the palonosetron group. CONCLUSION: Palonosetron showed a higher protective efficacy in all phases of CINV prevention, especially in delayed phases, and no relatively severe adverse effects were observed.

Integrated analysis of source-specific risks for PM2.5-bound metals in urban, suburban, rural, and industrial areas.

The levels and characteristics of atmospheric metals vary in time and location, can result in various health impacts, which increases the challenge of air quality management. We aimed to investigate PM2.5-bound metals in multiple locations and propose a methodology for comparing metal elements across study regions and prioritizing source contributions through integrated health risk assessments. PM2.5-bound metals were collected in the urban, suburban, rural, and industrial regions of Taiwan between 2016 and 2018. We incorporated the positive matrix factorization (PMF) with health risk assessments (considering estimates of the margin of exposure (MOE) and excess cancer risk (ECR)) to prioritize sources for control. We found that the concentrations of Fe, Zn, V, Cu, and Mn (industry-related metals) were higher at the industrial site (Kaohsiung) and Ba, Cr, Ni, Mo, and Co (traffic-related metals) were higher at the urban site (Taipei). The rural site (Hualian) had good air quality, with low PM2.5 and metal concentrations. Most metal concentrations were higher during the cold season for all study sites, except for the rural. Ambient concentrations of Mn, Cr, and Pb obtained from all study sites presents a higher health risk of concern. In Kaohsiung, south Taiwan, PM2.5-bound metals from the iron ore and steel factory is suggested as the first target for control based on the calculated health risks (MOE < 1 and ECR > 10-6). Overall, we proposed an integrated strategy for initiating the source management prioritization of PM2.5-bound metals, which can aid an effort for policymaking.

Maternal proximity to petrochemical industrial parks and risk of premature rupture of membranes.

BACKGROUND: Living near petrochemical industries has been reported to increase the risks of adverse birth outcomes, such as low birth weight and preterm delivery. However, evidence regarding the role of petrochemical exposure in pregnancy complications remains limited. This study evaluated the association between maternal proximity to petrochemical industrial parks (PIPs) during pregnancy and the occurrence of premature rupture of membranes (PROM). METHODS: We performed a population-based 1:3 case-control study by using the 2004-2014 Taiwanese Birth Certificate Database. Birth records reported as stillbirth or bearing congenital anomalies were excluded. Cases were newborns reported to have PROM, whereas controls were randomly sampled from those without any pregnancy complications by matching birth year and urbanization index of the residential township. The proximity to PIPs was evaluated by calculating the distance to the nearest PIP of the maternal residential township during pregnancy. Furthermore, petrochemical exposure opportunity, accounting for monthly prevailing wind direction, was quantified during the entire gestational period. We applied conditional logistic regression models to evaluate the associations. RESULTS: In total, 29371 PROM cases were reported during the study period, with a corresponding 88113 healthy controls sampled. The results revealed that living within a 3-km radius of PIPs during pregnancy would increase the risk of PROM (odds ratio [OR] = 1.76, 95% CI: 1.66-1.87). Furthermore, compared with the lowest exposed group, those with high petrochemical exposure opportunity had a significantly increased risk of PROM occurrence (OR = 1.69-1.75). The adverse effects remained robust in the subgroup analysis for both term- and preterm-PROM. CONCLUSIONS: The results of the present work provide evidence that living near PIPs during pregnancy would increase the risk of PROM, and additional studies are warranted to confirm our findings.

Predicting carbonaceous aerosols and identifying their source contribution with advanced approaches.

Organic carbon (OC) and elemental carbon (EC) play important roles in various atmospheric processes and health effects. Predicting carbonaceous aerosols and identifying source contributions are important steps for further epidemiological study and formulating effective emission control policies. However, we are not aware of any study that examined predictions of OC and EC, and this work is also the first study that attempted to use machine learning and hyperparameter optimization method to predict concentrations of specific aerosol contaminants. This paper describes an investigation of the characteristics and sources of OC and EC in fine particulate matter (PM2.5) from 2005 to 2010 in the City of Taipei. Respective hourly average concentrations of OC and EC were 5.2 µg/m3 and 1.6 µg/m3. We observed obvious seasonal variation in OC but not in EC. Hourly and daily OC and EC concentrations were predicted using generalized additive model and grey wolf optimized multilayer perceptron model, which could explain up to about 80% of the total variation. Subsequent clustering suggests that traffic emission was the major contribution to OC, accounting for about 80% in the spring, 65% in the summer, and 90% in the fall and winter. In the Taipei area, local emissions were the dominant sources of OC and EC in all seasons, and long-range transport had a significant contribution to OC and in PM2.5 in spring.

Comparison of Spatial Modelling Approaches on PM10 and NO2 Concentration Variations: A Case Study in Surabaya City, Indonesia.

Because of fast-paced industrialization, urbanization, and population growth in Indonesia, there are serious health issues in the country resulting from air pollution. This study uses geospatial modelling technologies, namely land-use regression (LUR), geographically weighted regression (GWR), and geographic and temporal weighted regression (GTWR) models, to assess variations in particulate matter (PM10) and nitrogen dioxide (NO2) concentrations in Surabaya City, Indonesia. This is the first study to implement spatiotemporal variability of air pollution concentrations in Surabaya City, Indonesia. To develop the prediction models, air pollution data collected from seven monitoring stations from 2010 to 2018 were used as dependent variables, while land-use/land cover allocations within a 250 m to 5000 m circular buffer range surrounding the monitoring stations were collected as independent variables. A supervised stepwise variable selection procedure was applied to identify the important predictor variables for developing the LUR, GWR, and GTWR models. The developed models of LUR, GWR, and GTWR accounted for 49%, 50%, and 51% of PM10 variations and 46%, 47%, and 48% of NO2 variations, respectively. The GTWR model performed better (R2 = 0.51 for PM10 and 0.48 for NO2) than the other two models (R2 = 0.49-0.50 for PM10 and 0.46-0.47 for NO2), LUR and GWR. In the PM10 model four predictor variables, public facility, industry and warehousing, paddy field, and normalized difference vegetation index (NDVI), were selected during the variable selection procedure. Meanwhile, paddy field, residential area, rainfall, and temperature played important roles in explaining NO2 variations. Because of biomass burning issues in South Asia, the paddy field, which has a positive correlation with PM10 and NO2, was selected as a predictor. By using long-term monitoring data to establish prediction models, this model may better depict PM10 and NO2 concentration variations within areas across Asia.