Land Use Regression models for 60 volatile organic compounds: Comparing Google Point of Interest (POI) and city permit data

High-resolution mapping of regional VOCs using the enhanced space-time extreme gradient boosting machine (XGBoost) in Shanghai

The accurate estimation of highly spatiotemporal volatile organic compounds (VOCs) is of great significance to establish advanced early warning systems and regulate air pollution control. However, the estimation of high spatiotemporal VOCs remains incomplete. Here, the space-time extreme gradient boost model (STXGB) was enhanced by integrating spatiotemporal information to obtain the spatial resolution and overall accuracy of VOCs. To this end, meteorological, topographical and pollutant emissions, was input to the STXGB model, and regional hourly 300 m VOCs maps for 2020 in Shanghai were produced. Our results show that the STXGB model achieve good hourly VOCs estimations performance (R2 = 0.73). A further analysis of SHapley Additive exPlanation (SHAP) regression indicate that local interpretations of the STXGB models demonstrate the strong contribution of emissions on mapping VOCs estimations, while acknowledging the important contribution of space and time term. The proposed approach outperforms many traditional machine learning models with a lower computational burden in terms of speed and memory.

Spatial modeling of ambient concentrations of volatile organic compounds in Montreal, Canada

Volatile organic compounds (VOCs) are components of the complex mixture of air pollutants within cities and can cause various adverse health effects. Therefore, it is necessary to understand their spatial distribution for exposure assessment in epidemiological studies.

Integrating Multiscale Geospatial Environmental Data into Large Population Health Studies: Challenges and Opportunities

Quantifying the exposome is key to understanding how the environment impacts human health and disease. However, accurately, and cost-effectively quantifying exposure in large population health studies remains a major challenge. Geospatial technologies offer one mechanism to integrate high-dimensional environmental data into epidemiology studies, but can present several challenges. In June 2021, the National Institute of Environmental Health Sciences (NIEHS) held a workshop bringing together experts in exposure science, geospatial technologies, data science and population health to address the need for integrating multiscale geospatial environmental data into large population health studies. The primary objectives of the workshop were to highlight recent applications of geospatial technologies to examine the relationships between environmental exposures and health outcomes; identify research gaps and discuss future directions for exposure modeling, data integration and data analysis strategies; and facilitate communications and collaborations across geospatial and population health experts. This commentary provides a high-level overview of the scientific topics covered by the workshop and themes that emerged as areas for future work, including reducing measurement errors and uncertainty in exposure estimates, and improving data accessibility, data interoperability, and computational approaches for more effective multiscale and multi-source data integration, along with potential solutions.

Leveraging Citizen Science and Low-Cost Sensors to Characterize Air Pollution Exposure of Disadvantaged Communities in Southern California

Assessing exposure to fine particulate matter (PM_2.5) across disadvantaged communities is understudied, and the air monitoring network is inadequate. We leveraged emerging low-cost sensors (PurpleAir) and engaged community residents to develop a community-based monitoring program across disadvantaged communities (high proportions of low-income and minority populations) in Southern California. We recruited 22 households from 8 communities to measure residential outdoor PM_2.5 concentrations from June 2021 to December 2021. We identified the spatial and temporal patterns of PM_2.5 measurements as well as the relationship between the total PM_2.5 measurements and diesel PM emissions. We found that communities with a higher percentage of Hispanic and African American population and higher rates of unemployment, poverty, and housing burden were exposed to higher PM_2.5 concentrations. The average PM_2.5 concentrations in winter (25.8 µg/m³) were much higher compared with the summer concentrations (12.4 µg/m³). We also identified valuable hour-of-day and day-of-week patterns among disadvantaged communities. Our results suggest that the built environment can be targeted to reduce the exposure disparity. Integrating low-cost sensors into a citizen-science-based air monitoring program has promising applications to resolve monitoring disparity and capture “hotspots” to inform emission control and urban planning policies, thus improving exposure assessment and promoting environmental justice.

Spatiotemporal estimation of the PM2.5 concentration and human health risks combining the three-dimensional landscape pattern index and machine learning methods to optimize land use regression modeling in Shaanxi, China

PM_2.5 pollution endangers human health and urban sustainable development. Land use regression (LUR) is one of the most important methods to reveal the temporal and spatial heterogeneity of PM_2.5, and the introduction of characteristic variables of geographical factors and the improvement of model construction methods are important research directions for its optimization. However, the complex non-linear correlation between PM_2.5 and influencing indicators is always unrecognized by the traditional regression model. The two-dimensional landscape pattern index is difficult to reflect the real information of the surface, and the research accuracy cannot meet the requirements. As such, a novel integrated three-dimensional landscape pattern index (TDLPI) and machine learning extreme gradient boosting (XGBOOST) improved LUR model (LTX) are developed to estimate the spatiotemporal heterogeneity in the fine particle concentration in Shaanxi, China, and health risks of exposure and inhalation of PM_2.5 were explored. The LTX model performed well with R² = 0.88, RMSE of 8.73 μg/m³ and MAE of 5.85 μg/m³. Our findings suggest that integrated three-dimensional landscape pattern information and XGBOOST approaches can accurately estimate annual and seasonal variations of PM_2.5 pollution The Guanzhong Plain and northern Shaanxi always feature high PM_2.5 values, which exhibit similar distribution trends to those of the observed PM_2.5 pollution. This study demonstrated the outstanding performance of the LTX model, which outperforms most models in past researches. On the whole, LTX approach is reliable and can improve the accuracy of pollutant concentration prediction. The health risks of human exposure to fine particles are relatively high in winter. Central part is a high health risk area, while northern area is low. Our study provides a new method for atmospheric pollutants assessing, which is important for LUR model optimization, high-precision PM_2.5 pollution prediction and landscape pattern planning. These results can also contribute to human health exposure risks and future epidemiological studies of air pollution.

Spatial and Temporal Analysis of Impacts of Hurricane Florence on Criteria Air Pollutants and Air Toxics in Eastern North Carolina

Natural and anthropogenic disasters are associated with air quality concerns due to the potential redistribution of pollutants in the environment. Our objective was to conduct a spatiotemporal analysis of air concentrations of benzene, toluene, ethylbenzne, and xylene (BTEX) and criteria air pollutants in North Carolina during and after Hurricane Florence. Three sampling campaigns were carried out immediately after the storm (September 2018) and at four-month intervals. BTEX were measured along major roads. Concurrent criteria air pollutant concentrations were predicted from modeling. Correlation between air pollutants and possible point sources was conducted using spatial regression. Exceedances of ambient air criteria were observed for benzene (in all sampling periods) and PM2.5 (mostly immediately after Florence). For both, there was an association between higher concentrations and fueling stations, particularly immediately after Florence. For other pollutants, concentrations were generally below levels of regulatory concern. Through characterization of air quality under both disaster and "normal" conditions, this study demonstrates spatial and temporal variation in air pollutants. We found that only benzene and PM2.5 were present at levels of potential concern, and there were localized increases immediately after the hurricane. These substances warrant particular attention in future disaster response research (DR2) investigations.

Estimating PM2.5 concentration using the machine learning GA-SVM method to improve the land use regression model in Shaanxi, China

With rapid economic growth, urbanization and industrialization, fine particulate matter with aerodynamic diameters ≤ 2.5 µm (PM_2.5) has become a major pollutant and shows adverse effects on both human health and the atmospheric environment. Many studies on estimating PM_2.5 concentrations have been performed using statistical regression models and satellite remote sensing. However, the accuracy of PM_2.5 concentration estimates is limited by traditional regression models; machine learning methods have high predictive power, but fewer studies have been performed on the complementary advantages of different approaches. This study estimates PM_2.5 concentrations from satellite remote sensing-derived aerosol optical depth (AOD) products, meteorological data, terrain data and other predictors in 2015 in Shaanxi, China, using a combined genetic algorithm-support vector machine (GA-SVM) method, after which the spatial clustering pattern was explored at the season and year levels. The results indicated that temperature (r = -0.684), precipitation (r = -0.602) and normalized difference vegetation index (NDVI) (r = -0.523) were significantly negatively correlated with the PM_2.5 concentration, while AOD (r = 0.337) was significantly positively correlated with the PM_2.5 concentration. Compared to conventional land use regression (LUR) and SVM models and previous related studies, the GA-SVM method demonstrated a significantly better prediction accuracy of PM_2.5 concentration, with a higher 10-fold cross-validation coefficient of determination (R²) of 0.84 and lower root mean square error (RMSE) and mean absolute error (MAE) of 12.1 μg/m³ and 10.07 μg/m³, respectively. Y-scrambling test shows that the models have no chance correlation. The central and southern parts of Shaanxi have high PM_2.5 concentrations, which are mainly due to the pollutant emissions and meteorological and topographical conditions in those areas. There was a positive spatial agglomeration characteristic of regional PM_2.5 pollution, and the spatial spillover effect of PM_2.5 pollution for seasonal and annual variations does exist. In general, the GA-SVM method is robust and accurately estimates PM_2.5 concentrations via a novel modeling framework application and high-quality spatiotemporal information. It also has great significance for the exploration of PM_2.5 pollution estimation and high-precision mapping methods, especially early warning in high-risk areas. Finally, the prevention and control of atmospheric pollution should take pollution control measures from major cities and surrounding cities, and focus on the joint pollution control measures for plain cities.

National Empirical Models of Air Pollution Using Microscale Measures of the Urban Environment

National-scale empirical models of air pollution (e.g., Land Use Regression) rely on predictor variables (e.g., population density, land cover) at different geographic scales. These models typically lack microscale variables (e.g., street level), which may improve prediction with fine-spatial gradients. We developed microscale variables of the urban environment including Point of Interest (POI) data, Google Street View (GSV) imagery, and satellite-based measures of urban form. We developed United States national models for six criteria pollutants (NO₂, PM_2.5, O₃, CO, PM₁₀, SO₂) using various modeling approaches: Stepwise Regression + kriging (SW-K), Partial Least Squares + kriging (PLS-K), and Machine Learning + kriging (ML-K). We compared predictor variables (e.g., traditional vs microscale) and emerging modeling approaches (ML-K) to well-established approaches (i.e., traditional variables in a PLS-K or SW-K framework). We found that combined predictor variables (traditional + microscale) in the ML-K models outperformed the well-established approaches (10-fold spatial cross-validation (CV) R² increased 0.02-0.42 [average: 0.19] among six criteria pollutants). Comparing all model types using microscale variables to models with traditional variables, the performance is similar (average difference of 10-fold spatial CV R² = 0.05) suggesting microscale variables are a suitable substitute for traditional variables. ML-K and microscale variables show promise for improving national empirical models.

High Temporal Resolution Land Use Regression Models with POI Characteristics of the PM2.5 Distribution in Beijing, China

PM2.5 is one of the primary components of air pollutants, and it has wide impacts on human health. Land use regression models have the typical disadvantage of low temporal resolution. In this study, various point of interests (POIs) variables are added to the usual predictive variables of the general land use regression (LUR) model to improve the temporal resolution. Hourly PM2.5 concentration data from 35 monitoring stations in Beijing, China, were used. Twelve LUR models were developed for working days and non-working days of the heating season and non-heating season, respectively. The results showed that these models achieved good fitness in winter and summer, and the highest R2 of the winter and summer models were 0.951 and 0.628, respectively. Meteorological factors, POIs, and roads factors were the most critical predictive variables in the models. This study also showed that POIs had time characteristics, and different types of POIs showed different explanations ranging from 5.5% to 41.2% of the models on working days or non-working days, respectively. Therefore, this study confirmed that POIs can greatly improve the temporal resolution of LUR models, which is significant for high precision exposure studies.

Predicting outdoor ultrafine particle number concentrations, particle size, and noise using street-level images and audio data

Outdoor ultrafine particles (UFPs) (<0.1 µm) may have an important impact on public health but exposure assessment remains a challenge in epidemiological studies. We developed a novel method of estimating spatiotemporal variations in outdoor UFP number concentrations and particle diameters using street-level images and audio data in Montreal, Canada. As a secondary aim, we also developed models for noise. Convolutional neural networks were first trained to predict 10-second average UFP/noise parameters using a large database of images and audio spectrogram data paired with measurements collected between April 2019 and February 2020. Final multivariable linear regression and generalized additive models were developed to predict 5-minute average UFP/noise parameters including covariates from deep learning models based on image and audio data along with outdoor temperature and wind speed. The best performing final models had mean cross-validation R² values of 0.677 and 0.523 for UFP number concentrations and 0.825 and 0.735 for UFP size using two different test sets. Audio predictions from deep learning models were stronger predictors of spatiotemporal variations in UFP parameters than predictions based on street-level images; this was not explained only by noise levels captured in the audio signal. All final noise models had R² values above 0.90. Collectively, our findings suggest that street-level images and audio data can be used to estimate spatiotemporal variations in outdoor UFPs and noise. This approach may be useful in developing exposure models over broad spatial scales and such models can be regularly updated to expand generalizability as more measurements become available.

Applying Real-Time Travel Times to Estimate Fire Service Coverage Rate for High-Rise Buildings

Frequent high-rise building fires have posed serious threats to urban public safety. In this study, real-time travel times extracted from online maps were applied to estimate fire service coverage rates for high-rise buildings. Firstly, the minimum fire apparatus requirement for high-rise building “at least 1 water fire truck and 1 aerial fire truck should arrive at the fire scene of high-rise building within 240 s” was proposed. Then, a dynamic estimation model of fire service coverage rate for high-rise buildings was established. To validate the model, 5146 high-rise buildings, 61 water fire trucks, and 56 aerial fire trucks in Changsha were selected as case studies. The results show that the total effective coverage rate and total average travel time in Changsha are 20.43% and 421.95 s, respectively. There are 10,840 water fire trucks and 6192 aerial fire trucks in China. Based on the average number of water fire trucks and aerial fire trucks per high-rise building, it can be estimated that the total effective coverage rate in China may not exceed 60.00%. Due to limited fire resources and frequent traffic congestion, only partial high-rise buildings can be effectively covered by fire services, whether in Changsha or China.