Mapping Air Pollution with Google Street View Cars: Efficient Approaches with Mobile Monitoring and Land Use Regression

Spatial and spatiotemporal modelling of intra-urban ultrafine particles: A comparison of linear, nonlinear, regularized, and machine learning methods

BACKGROUND

Machine learning methods are proposed to improve the predictions of ambient air pollution, yet few studies have compared ultrafine particles (UFP) models across a broad range of statistical and machine learning approaches, and only one compared spatiotemporal models. Most reported marginal differences between methods. This limits our ability to draw conclusions about the best methods to model ambient UFPs.

OBJECTIVE

To compare the performance and predictions of statistical and machine learning methods used to model spatial and spatiotemporal ambient UFPs.

METHODS

Daily and annual models were developed from UFP measurements from a year-long mobile monitoring campaign in Quebec City, Canada, combined with 262 geospatial and six meteorological predictors. Various road segment lengths were considered (100/300/500 m) for UFP data aggregation. Four statistical methods included linear, non-linear, and regularized regressions, whereas eight machine learning regressions utilized tree-based, neural networks, support vector, and kernel ridge algorithms. Nested cross-validation was used for model training, hyperparameter tuning and performance evaluation.

RESULTS

Mean annual UFP concentrations was 13,335 particles/cm3. Machine learning outperformed statistical methods in predicting UFPs. Tree-based methods performed best across temporal scales and segment lengths, with XGBoost producing the overall best performing models (annual R2 = 0.78-0.86, RMSE = 2163-2169 particles/cm3; daily R2 = 0.47-0.48, RMSE = 8651-11,422 particles/cm3). With 100 m segments, other annual models performed similarly well, but their prediction surfaces of annual mean UFP concentrations showed signs of overfitting. Spatial aggregation of monitoring data significantly impacted model performance. Longer segments yielded lower RMSE in all daily models and for annual statistical models, but not for annual machine learning models.

CONCLUSIONS

The use of tree-based methods significantly improved spatiotemporal predictions of UFP concentrations, and to a lesser extent annual concentrations. Segment length and hyperparameter tuning had notable impacts on model performance and should be considered in future studies.

Electric buses as an air pollution and meteorological observation network: Methodology and preliminary results

Many local agencies in the United States and other countries are tasked to install air pollution monitoring systems of highly accurate sensors that have high acquisition, operating, and maintenance costs. The need for expanded coverage of air quality measurements across Salt Lake County (SLCO), Utah is being met by mounting air quality and temperature sensors on an expanding fleet of battery electric buses (BEBs). Monitoring air quality from a mobile sensor network provides real-time insights into air pollution patterns at high temporal and spatial resolution. Mobile measurements contribute to assessing residents' exposure to air pollution, facilitating the implementation of cost-effective public health policies and highlighting disparities. The Electric Bus Air Quality Observation Project was launched in SLCO during July 2021 and has collected millions of observations to date. A BEB traveling at typical traffic speeds (~10 m s-1) can provide multiple measurements along city block lengths of up to ~200 m. With careful analysis that factors in the time response of the differing sensors, variability from block-to-block may be attributed to fine-scale factors (e.g., pollution and heat sources, tree shading and urban vegetation, etc.). Preliminary findings showcase the value of increased coverage and resolution. During an extreme heat event in July 2023, both the morning and afternoon temperature readings showed differences of over 6.5 °C (12 °F), primarily as an east-west gradient with similar gradients in ozone. We conclude that temperature and pollutant concentration readings, at fine spatial and temporal resolutions, will facilitate future health studies and equitable policy and mitigation strategies. Our study demonstrates that our partnerships established with governmental, non-profit, and transit agencies facilitate the successful transfer of research and development to operational real-time mobile air quality monitoring.

Neighborhood-Level Nitrogen Dioxide Inequalities Contribute to Surface Ozone Variability in Houston, Texas

In Houston, Texas, nitrogen dioxide (NO2) air pollution disproportionately affects Black, Latinx, and Asian communities, and high ozone (O3) days are frequent. There is limited knowledge of how NO2 inequalities vary in urban air quality contexts, in part from the lack of time-varying neighborhood-level NO2 measurements. First, we demonstrate that daily TROPOspheric Monitoring Instrument (TROPOMI) NO2 tropospheric vertical column densities (TVCDs) resolve a major portion of census tract-scale NO2 inequalities in Houston, comparing NO2 inequalities based on TROPOMI TVCDs and spatiotemporally coincident airborne remote sensing (250 m × 560 m) from the NASA TRacking Aerosol Convection ExpeRiment-Air Quality (TRACER-AQ). We further evaluate the application of daily TROPOMI TVCDs to census tract-scale NO2 inequalities (May 2018-November 2022). This includes explaining differences between mean daily NO2 inequalities and those based on TVCDs oversampled to 0.01° × 0.01° and showing daily NO2 column-surface relationships weaken as a function of observation separation distance. Second, census tract-scale NO2 inequalities, city-wide high O3, and mesoscale airflows are found to covary using principal component and cluster analysis. A generalized additive model of O3 mixing ratios versus NO2 inequalities reproduces established nonlinear relationships between O3 production and NO2 concentrations, providing observational evidence that neighborhood-level NO2 inequalities and O3 are coupled. Consequently, emissions controls specifically in Black, Latinx, and Asian communities will have co-benefits, reducing both NO2 disparities and high O3 days city wide.

A review of geospatial exposure models and approaches for health data integration

BACKGROUND

Geospatial methods are common in environmental exposure assessments and increasingly integrated with health data to generate comprehensive models of environmental impacts on public health.

OBJECTIVE

Our objective is to review geospatial exposure models and approaches for health data integration in environmental health applications.

METHODS

We conduct a literature review and synthesis.

RESULTS

First, we discuss key concepts and terminology for geospatial exposure data and models. Second, we provide an overview of workflows in geospatial exposure model development and health data integration. Third, we review modeling approaches, including proximity-based, statistical, and mechanistic approaches, across diverse exposure types, such as air quality, water quality, climate, and socioeconomic factors. For each model type, we provide descriptions, general equations, and example applications for environmental exposure assessment. Fourth, we discuss the approaches used to integrate geospatial exposure data and health data, such as methods to link data sources with disparate spatial and temporal scales. Fifth, we describe the landscape of open-source tools supporting these workflows.

Local exposure misclassification in national models: relationships with urban infrastructure and demographics

BACKGROUND

National-scale linear regression-based modeling may mischaracterize localized patterns, including hyperlocal peaks and neighborhood- to regional-scale gradients. For studies focused on within-city differences, this mischaracterization poses a risk of exposure misclassification, affecting epidemiological and environmental justice conclusions.

OBJECTIVE

Characterize the difference between intraurban pollution patterns predicted by national-scale land use regression modeling and observation-based estimates within a localized domain and examine the relationship between that difference and urban infrastructure and demographics.

METHODS

We compare highly resolved (0.01 km2) observations of NO2 mixing ratio and ultrafine particle (UFP) count obtained via mobile monitoring with national model predictions in thirteen neighborhoods in the San Francisco Bay Area. Grid cell-level divergence between modeled and observed concentrations is termed "localized difference." We use a flexible machine learning modeling technique, Bayesian Additive Regression Trees, to investigate potentially nonlinear relationships between discrepancy between localized difference and known local emission sources as well as census block group racial/ethnic composition.

RESULTS

We find that observed local pollution extremes are not represented by land use regression predictions and that observed UFP count significantly exceeds regression predictions. Machine learning models show significant nonlinear relationships among localized differences between predictions and observations and the density of several types of pollution-related infrastructure (roadways, commercial and industrial operations). In addition, localized difference was greater in areas with higher population density and a lower share of white non-Hispanic residents, indicating that exposure misclassification by national models differs among subpopulations.

IMPACT

Comparing national-scale pollution predictions with hyperlocal observations in the San Francisco Bay Area, we find greater discrepancies near major roadways and food service locations and systematic underestimation of concentrations in neighborhoods with a lower share of non-Hispanic white residents. These findings carry implications for using national-scale models in intraurban epidemiological and environmental justice applications and establish the potential utility of supplementing large-scale estimates with publicly available urban infrastructure and pollution source information.

Portable Sensors for Dynamic Exposure Assessments in Urban Environments: State of the Science

This study presents a fit-for-purpose lab and field evaluation of commercially available portable sensor systems for PM, NO2, and/or BC. The main aim of the study is to identify portable sensor systems that are capable of reliably quantifying dynamic exposure gradients in urban environments. After an initial literature and market study resulting in 39 sensor systems, 10 sensor systems were ultimately purchased and benchmarked under laboratory and real-word conditions. We evaluated the comparability to reference analyzers, sensor precision, and sensitivity towards environmental confounders (temperature, humidity, and O3). Moreover, we evaluated if the sensor accuracy can be improved by applying a lab or field calibration. Because the targeted application of the sensor systems under evaluation is mobile monitoring, we conducted a mobile field test in an urban environment to evaluate the GPS accuracy and potential impacts from vibrations on the resulting sensor signals. Results of the considered sensor systems indicate that out-of-the-box performance is relatively good for PM (R2 = 0.68-0.9, Uexp = 16-66%, BSU = 0.1-0.7 µg/m3) and BC (R2 = 0.82-0.83), but maturity of the tested NO2 sensors is still low (R2 = 0.38-0.55, Uexp = 111-614%) and additional efforts are needed in terms of signal noise and calibration, as proven by the performance after multilinear calibration (R2 = 0.75-0.83, Uexp = 37-44%)). The horizontal accuracy of the built-in GPS was generally good, achieving <10 m accuracy for all sensor systems. More accurate and dynamic exposure assessments in contemporary urban environments are crucial to study real-world exposure of individuals and the resulting impacts on potential health endpoints. A greater availability of mobile monitoring systems capable of quantifying urban pollutant gradients will further boost this line of research.

Hyperlocal Air Pollution Mapping: A Scalable Transfer Learning LUR Approach for Mobile Monitoring

Addressing the challenge of mapping hyperlocal air pollution in areas without local monitoring, we evaluated unsupervised transfer learning-based land-use regression (LUR) models developed using mobile monitoring data from other cities: CORrelation ALignment (Coral) and its inverse distance-weighted modification (IDW_Coral). These models mitigated domain shifts and transferred patterns learned from mobile air quality monitoring campaigns in Copenhagen and Rotterdam to estimate annual average air pollution levels in Amsterdam (50m road segments) without involving any Amsterdam measurements in model development. For nitrogen dioxide (NO2), IDW_Coral outperformed Copenhagen and Rotterdam LUR models directly applied to Amsterdam, achieving MAE (4.47 μg/m3) and RMSE (5.36 μg/m3) comparable to a locally fitted LUR model (AMS_SLR) developed using Amsterdam mobile measurements collected for 160 days. IDW_Coral yielded an R2 of 0.35, similar to that of the AMS_SLR based on 20 collection days, suggesting a minimum requirement of 20-day mobile monitoring to capture city-specific insights. For ultrafine particles (UFP), IDW_Coral's citywide predictions strongly correlated with previously published mixed-effect models fitted with 160-day Amsterdam measurements (Pearson correlation of 0.71 for UFP and 0.72 for NO2). IDW_Coral demands no direct measurements in the target area, showcasing its potential for large-scale applications and offering significant economic efficiencies in executing mobile monitoring campaigns.

Capturing Exposure Disparities with Chemical Transport Models: Evaluating the Suitability of Downscaling Using Land Use Regression

High resolution exposure surfaces are essential to capture disparities in exposure to traffic-related air pollution in urban areas. In this study, we develop an approach to downscale Chemical Transport Model (CTM) simulations to a hyperlocal level (∼100m) in the Greater Toronto Area (GTA) under three scenarios where emissions from cars, trucks and buses are zeroed out, thus capturing the burden of each transportation mode. This proposed approach statistically fuses CTMs with Land-Use Regression using machine learning techniques. With this proposed downscaling approach, changes in air pollutant concentrations under different scenarios are appropriately captured by downscaling factors that are trained to reflect the spatial distribution of emission reductions. Our validation analysis shows that high-resolution models resulted in better performance than coarse models when compared with observations at reference stations. We used this downscaling approach to assess disparities in exposure to nitrogen dioxide (NO2) for populations composed of renters, low-income households, recent immigrants, and visible minorities. Individuals in all four categories were disproportionately exposed to the burden of cars, trucks, and buses. We conducted this analysis at spatial resolutions of 12, 4, 1 km, and 100 m and observed that disparities were significantly underestimated when using coarse spatial resolutions. This reinforces the need for high-spatial resolution exposure surfaces for environmental justice analyses.

Estimating the short-term effect of PM2.5 on the mortality of cardiovascular diseases based on instrumental variables

BACKGROUND

PM2.5 can induce and aggravate the occurrence and development of cardiovascular diseases (CVDs). The objective of our study is to estimate the causal effect of PM2.5 on mortality rates associated with CVDs using the instrumental variables (IVs) method.

METHODS

We extracted daily meteorological, PM2.5 and CVDs death data from 2016 to 2020 in Binzhou. Subsequently, we employed the general additive model (GAM), two-stage predictor substitution (2SPS), and control function (CFN) to analyze the association between PM2.5 and daily CVDs mortality.

RESULTS

The 2SPS estimated the association between PM2.5 and daily CVDs mortality as 1.14% (95% CI: 1.04%, 1.14%) for every 10 µg/m3 increase in PM2.5. Meanwhile, the CFN estimated this association to be 1.05% (95% CI: 1.02%, 1.10%). The GAM estimated it as 0.85% (95% CI: 0.77%, 1.05%). PM2.5 also exhibited a statistically significant effect on the mortality rate of patients with ischaemic heart disease, myocardial infarction, or cerebrovascular accidents (P < 0.05). However, no significant association was observed between PM2.5 and hypertension.

CONCLUSION

PM2.5 was significantly associated with daily CVDs deaths (excluding hypertension). The estimates from the IVs method were slightly higher than those from the GAM. Previous studies based on GAM may have underestimated the impact of PM2.5 on CVDs.

High-resolution urban air pollution mapping

Variation in urban air pollution arises because of complex spatial, temporal, and chemical processes, which profoundly affect population exposure, human health, and environmental justice. This Review highlights insights from two popular in situ measurement methods-mobile monitoring and dense sensor networks-that have distinct but complementary strengths in characterizing the dynamics and impacts of the multidimensional urban air quality system. Mobile monitoring can measure many pollutants at fine spatial scales, thereby informing about processes and control strategies. Sensor networks excel at providing temporal resolution at many locations. Increasingly sophisticated studies leveraging both methods can vividly identify spatial and temporal patterns that affect exposures and disparities and offer mechanistic insight toward effective interventions. This Review summarizes the strengths and limitations of these methods and discusses their implications for understanding fine-scale processes and impacts.

Integrating Mobile and Fixed-Site Black Carbon Measurements to Bridge Spatiotemporal Gaps in Urban Air Quality

Urban air pollution can vary sharply in space and time. However, few monitoring strategies can concurrently resolve spatial and temporal variation at fine scales. Here, we present a new measurement-driven spatiotemporal modeling approach that transcends the individual limitations of two complementary sampling paradigms: mobile monitoring and fixed-site sensor networks. We develop, validate, and apply this model to predict black carbon (BC) using data from an intensive, 100-day field study in West Oakland, CA. Our spatiotemporal model exploits coherent spatial patterns derived from a multipollutant mobile monitoring campaign to fill spatial gaps in time-complete BC data from a low-cost sensor network. Our model performs well in reconstructing patterns at fine spatial and temporal resolution (30 m, 15 min), demonstrating strong out-of-sample correlations for both mobile (Pearson's R ∼ 0.77) and fixed-site measurements (R ∼ 0.95) while revealing features that are not effectively captured by a single monitoring approach in isolation. The model reveals sharp concentration gradients near major emission sources while capturing their temporal variability, offering valuable insights into pollution sources and dynamics.

High-resolution spatial and spatiotemporal modelling of air pollution using fixed site and mobile monitoring in a Canadian city

The development of high-resolution spatial and spatiotemporal models of air pollutants is essential for exposure science and epidemiological applications. While fixed-site sampling has conventionally provided input data for statistical predictive models, the evolving mobile monitoring method offers improved spatial resolution, ideal for measuring pollutants with high spatial variability such as ultrafine particles (UFP). The Quebec Air Pollution Exposure and Epidemiology (QAPEE) study measured and modelled the spatial and spatiotemporal distributions of understudied pollutants, such as UFPs, black carbon (BC), and brown carbon (BrC), along with fine particulate matter (PM2.5), nitrogen dioxide (NO2), and ozone (O3) in Quebec City, Canada. We conducted a combined fixed-site (NO2 and O3) and mobile monitoring (PM2.5, BC, BrC, and UFPs) campaign over 10-months. Mobile monitoring routes were monitored on a weekly basis between 8am-10am and designed using location/allocation modelling. Seasonal fixed-site sampling campaigns captured continuous 24-h measurements over two-week periods. Generalized Additive Models (GAMs), which combined data on pollution concentrations with spatial, temporal, and spatiotemporal predictor variables were used to model and predict concentration surfaces. Annual models for PM2.5, NO2, O3 as well as seven of the smallest size fractions in the UFP range, had high out of sample predictive accuracy (range r2: 0.54-0.86). Varying spatial patterns were observed across UFP size ranges measured as Particle Number Counts (PNC). The monthly spatiotemporal models for PM2.5 (r2 = 0.49), BC (r2 = 0.27), BrC (r2 = 0.29), and PNC (r2 = 0.49) had moderate or moderate-low out of sample predictive accuracy. We conducted a sensitivity analysis and found that the minimum number of 'n visits' (mobile monitoring sessions) required to model annually representative air pollution concentrations was between 24 and 32 visits dependent on the pollutant. This study provides a single source of exposure models for a comprehensive set of air pollutants in Quebec City, Canada. These exposure models will feed into epidemiological research on the health impacts of ambient UFPs and other pollutants.

Mobile air quality monitoring and comparison to fixed monitoring sites for instrument performance assessment

Air pollution monitoring using mobile ground-based measurement platforms can provide high quality spatiotemporal air pollution information. As mobile air quality monitoring campaigns extend to entire fleets of vehicles and integrate smaller scale air quality sensors, it is important to address the need for assessing these measurements in a scalable manner. We explore collocation-based evaluation of air quality measurements in a mobile platform using fixed regulatory sites as a reference. We compare two approaches - a standard collocation assessment technique where the mobile platform is parked near the fixed regulatory site for a period of time and an expanded approach using measurements while the mobile platform is in motion in the general vicinity of the fixed regulatory site. Based on the availability of fixed reference site data, we focus on three pollutants (ozone, nitrogen dioxide, and nitric oxide) with distinct atmospheric lifetimes and behaviors. We compare measurements from a mobile laboratory with regulatory site measurements in Denver, Colorado, USA and in the San Francisco Bay Area, California, USA. Our one-month Denver dataset includes both parked collocation periods near the fixed regulatory sites as well as general driving patterns around the sites, allowing a direct comparison of the parked and mobile collocation techniques on the same dataset. We show that the mobile collocation approach produces similar performance statistics, including coefficients of determination and mean bias errors, as the standard parked collocation technique. This is particularly true when the comparisons are restricted to specific road types, with residential streets showing the closest agreement and highways showing the largest differences. We extend our analysis to a larger (year-long) dataset in California, where we explore the relationships between the mobile measurements and the fixed reference sites on a larger scale. We show that using a 40-hour running median converges to within ±4 ppbv of the fixed reference site for nitrogen dioxide and ozone and up to about 8 ppbv for nitric oxide. We propose that this agreement can be leveraged to assess instrument performance over time during large-scale mobile monitoring campaigns. We demonstrate an example of how such relationships can be used during large-scale monitoring campaigns using small sensors to identify potential measurement biases.

LUR modeling of long-term average hourly concentrations of NO2 using hyperlocal mobile monitoring data

Mobile monitoring campaigns have effectively captured spatial hyperlocal variations in long-term average concentrations of regulated and unregulated air pollutants. However, their application in estimating spatiotemporally varying maps has rarely been investigated. Tackling this gap, we investigated whether mobile measurements can assess long-term average nitrogen dioxide (NO2) concentrations for each hour of the day. Using mobile NO2 data monitored for 10 months in Amsterdam, we examined the performance of two spatiotemporal land use regression (LUR) methods, Spatiotemporal-Kriging and GTWR (Geographical and Temporal Weighted Regression), alongside two classical spatial LUR models developed separately for each hour. We found that mobile measurements follow the general pattern of fixed-site measurements, but with considerable deviations (indicating collection uncertainty). Leveraging heterogeneous spatiotemporal autocorrelations, GTWR smoothed these deviations and achieved an overall performance of an R2 of 0.49 and a Mean Absolute Error of 6.33 μg/m3, validated by long-term fixed-site measurements (out-of-sample). The other models tested were more affected by the collection uncertainty. We highlighted that the spatiotemporal variations captured in mobile measurements can be used to reconstruct long-term average hourly air pollution maps. These maps facilitate dynamic exposure assessments considering spatiotemporal human activity patterns.

Multi-season mobile monitoring campaign of on-road air pollution in Bengaluru, India: High-resolution mapping and estimation of quasi-emission factors

Mobile monitoring can supplement regulatory measurements, particularly in low-income countries where stationary monitoring is sparse. Here, we report results from a ~ year-long mobile monitoring campaign of on-road concentrations of black carbon (BC), ultrafine particles (UFP), and carbon dioxide (CO2) in Bengaluru, India. The study route included 150 unique kms (average: ~22 repeat measurements per monitored road segment). After cleaning the data for known instrument artifacts and sensitivities, we generated 30 m high-resolution stable 'data only' spatial maps of BC, UFP, and CO2 for the study route. For the urban residential areas, the mean BC levels for residential roads, arterials, and highways were ~ 10, 22, and 56 μg m-3, respectively. A similar pattern (highways being characterized by highest pollution levels) was also observed for UFP and CO2. Using the data from repeat measurements, we carried out a Monte Carlo subsampling analysis to understand the minimum number of repeat measures to generate stable maps of pollution in the city. Leveraging the simultaneous nature of the measurements, we also mapped the quasi-emission factors (QEF) of the pollutants under investigation. The current study is the first multi-season mobile monitoring exercise conducted in a low or middle -income country (LMIC) urban setting that oversampled the study route and investigated the optimum number of repeat rides required to achieve representative pollution spatial patterns characterized with high precision and low bias. Finally, the results are discussed in the context of technical aspects of the campaign, limitations, and their policy relevance for our study location and for other locations. Given the day-to-day variability in the pollution levels, the presence of dynamic and unorganized sources, and active government pollution mitigation policies, multi-year mobile measurement campaigns would help test the long-term representativeness of the current results.

High-Precision Microscale Particulate Matter Prediction in Diverse Environments Using a Long Short-Term Memory Neural Network and Street View Imagery

In this study, we propose a novel long short-term memory (LSTM) neural network model that leverages color features (HSV: hue, saturation, value) extracted from street images to estimate air quality with particulate matter (PM) in four typical European environments: urban, suburban, villages, and the harbor. To evaluate its performance, we utilize concentration data for eight parameters of ambient PM (PM1.0, PM2.5, and PM10, particle number concentration, lung-deposited surface area, equivalent mass concentrations of ultraviolet PM, black carbon, and brown carbon) collected from a mobile monitoring platform during the nonheating season in downtown Augsburg, Germany, along with synchronized street view images. Experimental comparisons were conducted between the LSTM model and other deep learning models (recurrent neural network and gated recurrent unit). The results clearly demonstrate a better performance of the LSTM model compared with other statistically based models. The LSTM-HSV model achieved impressive interpretability rates above 80%, for the eight PM metrics mentioned above, indicating the expected performance of the proposed model. Moreover, the successful application of the LSTM-HSV model in other seasons of Augsburg city and various environments (suburbs, villages, and harbor cities) demonstrates its satisfactory generalization capabilities in both temporal and spatial dimensions. The successful application of the LSTM-HSV model underscores its potential as a versatile tool for the estimation of air pollution after presampling of the studied area, with broad implications for urban planning and public health initiatives.

A comprehensive review of the development of land use regression approaches for modeling spatiotemporal variations of ambient air pollution: A perspective from 2011 to 2023

Land use regression (LUR) models are widely used in epidemiological and environmental studies to estimate humans' exposure to air pollution within urban areas. However, the early models, developed using linear regressions and data from fixed monitoring stations and passive sampling, were primarily designed to model traditional and criteria air pollutants and had limitations in capturing high-resolution spatiotemporal variations of air pollution. Over the past decade, there has been a notable development of multi-source observations from low-cost monitors, mobile monitoring, and satellites, in conjunction with the integration of advanced statistical methods and spatially and temporally dynamic predictors, which have facilitated significant expansion and advancement of LUR approaches. This paper reviews and synthesizes the recent advances in LUR approaches from the perspectives of the changes in air quality data acquisition, novel predictor variables, advances in model-developing approaches, improvements in validation methods, model transferability, and modeling software as reported in 155 LUR studies published between 2011 and 2023. We demonstrate that these developments have enabled LUR models to be developed for larger study areas and encompass a wider range of criteria and unregulated air pollutants. LUR models in the conventional spatial structure have been complemented by more complex spatiotemporal structures. Compared with linear models, advanced statistical methods yield better predictions when handling data with complex relationships and interactions. Finally, this study explores new developments, identifies potential pathways for further breakthroughs in LUR methodologies, and proposes future research directions. In this context, LUR approaches have the potential to make a significant contribution to future efforts to model the patterns of long- and short-term exposure of urban populations to air pollution.

Mobile monitoring of air pollutants; performance evaluation of a mixed-model land use regression framework in relation to the number of drive days

We used black carbon data from a mobile monitoring campaign in Oakland, USA measuring street segments up to 40 times and compared a data-only, LUR model and mixed-model approach with a long-term average, represented by the average concentration based on 40 drive days on that street segment. The mixed model outperformed the data-only and LUR model estimates, with 80% explained variance after 5 drive days and 90% after 14 drive days. The data-only approach needed 8 and 15 to achieve an explained variance of 80% and 90%, respectively, The LUR model never achieved an explained variance higher than 70%. The mixed model is a scalable approach, as it can be used before all street segments in a domain are measured by developing a LUR model and adds information with increasing repeats per street segment.

Data Insights for Sustainable Cities: Associations between Google Street View-Derived Urban Greenspace and Google Air View-Derived Pollution Levels

Unprecedented levels of urbanization have escalated urban environmental health issues, including increased air pollution in cities globally. Strategies for mitigating air pollution, including green urban planning, are essential for sustainable and healthy cities. State-of-the-art research investigating urban greenspace and pollution metrics has accelerated through the use of vast digital data sets and new analytical tools. In this study, we examined associations between Google Street View-derived urban greenspace levels and Google Air View-derived air quality, where both have been resolved in extremely high resolution, accuracy, and scale along the entire road network of Dublin City. Particulate matter of size fraction less than 2.5 μm (PM2.5), nitrogen dioxide, nitric oxide, carbon monoxide, and carbon dioxide were quantified using 5,030,143 Google Air View measurements, and greenspace was quantified using 403,409 Google Street View images. Significant (p < 0.001) negative associations between urban greenspace and pollution were observed. For example, an interquartile range increase in the Green View Index was associated with a 7.4% [95% confidence interval: -13.1%, -1.3%] decrease in NO2 at the point location spatial resolution. We provide insights into how large-scale digital data can be harnessed to elucidate urban environmental interactions that will have important planning and policy implications for sustainable future cities.

Hyperlocal environmental data with a mobile platform in urban environments

Environmental data with a high spatio-temporal resolution is vital in informing actions toward tackling urban sustainability challenges. Yet, access to hyperlocal environmental data sources is limited due to the lack of monitoring infrastructure, consistent data quality, and data availability to the public. This paper reports environmental data (PM, NO2, temperature, and relative humidity) collected from 2020 to 2022 and calibrated in four deployments in three global cities. Each data collection campaign targeted a specific urban environmental problem related to air quality, such as tree diversity, community exposure disparities, and excess fossil fuel usage. Firstly, we introduce the mobile platform design and its deployment in Boston (US), NYC (US), and Beirut (Lebanon). Secondly, we present the data cleaning and validation process, for the air quality data. Lastly, we explain the data format and how hyperlocal environmental datasets can be used standalone and with other data to assist evidence-based decision-making. Our mobile environmental sensing datasets include cities of varying scales, aiming to address data scarcity in developing regions and support evidence-based environmental policymaking.

Predicting spatial variations in annual average outdoor ultrafine particle concentrations in Montreal and Toronto, Canada: Integrating land use regression and deep learning models

BACKGROUND

Concentrations of outdoor ultrafine particles (UFP; <0.1 µm) and black carbon (BC) can vary greatly within cities and long-term exposures to these pollutants have been associated with a variety of adverse health outcomes.

OBJECTIVE

This study integrated multiple approaches to develop new models to estimate within-city spatial variations in annual median (i.e. average) outdoor UFP and BC concentrations as well as mean UFP size in Canada's two largest cities, Montreal and Toronto.

METHODS

We conducted year-long mobile monitoring campaigns in each city that included evenings and weekends. We developed generalized additive models trained on land use parameters and deep Convolutional Neural Network (CNN) models trained on satellite-view images. Using predictions from these models, we developed final combined models.

RESULTS

In Toronto, the median observed UFP concentration, UFP size, and BC concentration values were 16,172pt/cm3, 33.7 nm, and 1225 ng/m3, respectively. In Montreal, the median observed UFP concentration, UFP size, and BC concentration values were 14,702pt/cm3, 29.7 nm, and 1060 ng/m3, respectively. For all pollutants in both cities, the proportion of spatial variation explained (i.e., R2) was slightly greater (1-2 percentage points) for the combined models than the generalized additive models and a greater (approximately 10 percentage points) than the deep CNN models. The Toronto combined model R2 values in the test set were 0.73, 0.55, and 0.61 for UFP concentrations, UFP size, and BC concentration, respectively. The Montreal combined model R2 values were 0.60, 0.49, and 0.60 for UFP concentration, UFP size, and BC concentration models respectively. For each pollutant, predictions from the combined, deep CNN, and generalized additive models were highly correlated with each other and differences between models were explored in sensitivity analyses.

CONCLUSION

Predictions from these models are available to support future epidemiological research examining long-term health impacts of outdoor UFPs and BC.

Integrating large-scale stationary and local mobile measurements to estimate hyperlocal long-term air pollution using transfer learning methods

Mobile air quality measurements are collected typically for several seconds per road segment and in specific timeslots (e.g., working hours). These short-term and on-road characteristics of mobile measurements become the ubiquitous shortcomings of applying land use regression (LUR) models to estimate long-term concentrations at residential addresses. This issue was previously found to be mitigated by transferring LUR models to the long-term residential domain using routine long-term measurements in the studied region as the transfer target (local scale). However, long-term measurements are generally sparse in individual cities. For this scenario, we propose an alternative by taking long-term measurements collected over a larger geographical area (global scale) as the transfer target and local mobile measurements as the source (Global2Local model). We empirically tested national, airshed countries (i.e., national plus neighboring countries) and Europe as the global scale in developing Global2Local models to map nitrogen dioxide (NO₂) concentrations in Amsterdam. The airshed countries scale provided the lowest absolute errors, and the Europe-wide scale had the highest R². Compared to a "global" LUR model (trained exclusively with European-wide long-term measurements), and a local mobile LUR model (using mobile data from Amsterdam only), the Global2Local model significantly reduced the absolute error of the local mobile LUR model (root-mean-square error, 6.9 vs 12.6 μg/m³) and improved the percentage explained variances compared to the global model (R², 0.43 vs 0.28, assessed by independent long-term NO₂ measurements in Amsterdam, n = 90). The Global2Local method improves the generalizability of mobile measurements in mapping long-term residential concentrations with a fine spatial resolution, which is preferred in environmental epidemiological studies.

Exposure Disparities by Income, Race and Ethnicity, and Historic Redlining Grade in the Greater Seattle Area for Ultrafine Particles and Other Air Pollutants

BACKGROUND

Growing evidence shows ultrafine particles (UFPs) are detrimental to cardiovascular, cerebrovascular, and respiratory health. Historically, racialized and low-income communities are exposed to higher concentrations of air pollution.

OBJECTIVES

Our aim was to conduct a descriptive analysis of present-day air pollution exposure disparities in the greater Seattle, Washington, area by income, race, ethnicity, and historical redlining grade. We focused on UFPs (particle number count) and compared with black carbon, nitrogen dioxide, and fine particulate matter (PM 2.5 ) levels.

METHODS

We obtained race and ethnicity data from the 2010 U.S. Census, median household income data from the 2006-2010 American Community Survey, and Home Owners' Loan Corporation (HOLC) redlining data from the University of Richmond's Mapping Inequality. We predicted pollutant concentrations at block centroids from 2019 mobile monitoring data. The study region encompassed much of urban Seattle, with redlining analyses restricted to a smaller region. To analyze disparities, we calculated population-weighted mean exposures and regression analyses using a generalized estimating equation model to account for spatial correlation.

RESULTS

Pollutant concentrations and disparities were largest for blocks with median household income of < $ 20,000 , Black residents, HOLC Grade D, and ungraded industrial areas. UFP concentrations were 4% lower than average for non-Hispanic White residents and higher than average for racialized groups (Asian, 3%; Black, 15%; Hispanic, 6%; Native American, 8%; Pacific Islander, 11%). For blocks with median household incomes of < $ 20,000 , UFP concentrations were 40% higher than average, whereas blocks with incomes of > $ 110,000 had UFP concentrations 16% lower than average. UFP concentrations were 28% higher for Grade D and 49% higher for ungraded industrial areas compared with Grade A. Disparities were highest for UFPs and lowest for PM 2.5 exposure levels.

DISCUSSION

Our study is one of the first to highlight large disparities with UFP exposures compared with multiple pollutants. Higher exposures to multiple air pollutants and their cumulative effects disproportionately impact historically marginalized groups. https://doi.org/10.1289/EHP11662.

Design and evaluation of short-term monitoring campaigns for long-term air pollution exposure assessment

BACKGROUND

Short-term mobile monitoring campaigns to estimate long-term air pollution levels are becoming increasingly common. Still, many campaigns have not conducted temporally-balanced sampling, and few have looked at the implications of such study designs for epidemiologic exposure assessment.

OBJECTIVE

We carried out a simulation study using fixed-site air quality monitors to better understand how different short-term monitoring designs impact the resulting exposure surfaces.

METHODS

We used Monte Carlo resampling to simulate three archetypal short-term monitoring sampling designs using oxides of nitrogen (NOx) monitoring data from 69 regulatory sites in California: a year-around Balanced Design that sampled during all seasons of the year, days of the week, and all or various hours of the day; a temporally reduced Rush Hours Design; and a temporally reduced Business Hours Design. We evaluated the performance of each design's land use regression prediction model.

RESULTS

The Balanced Design consistently yielded the most accurate annual averages; while the reduced Rush Hours and Business Hours Designs generally produced more biased results.

SIGNIFICANCE

A temporally-balanced sampling design is crucial for short-term campaigns such as mobile monitoring aiming to assess long-term exposure in epidemiologic cohorts.

IMPACT STATEMENT

Short-term monitoring campaigns to assess long-term air pollution trends are increasingly common, though they rarely conduct temporally balanced sampling. We show that this approach produces biased annual average exposure estimates that can be improved by collecting temporally-balanced samples.

Exposure assessment for air pollution epidemiology: A scoping review of emerging monitoring platforms and designs

BACKGROUND

Both exposure monitoring and exposure prediction have played key roles in assessing individual-level long-term exposure to air pollutants and their associations with human health. While there have been notable advances in exposure prediction methods, improvements in monitoring designs are also necessary, particularly given new monitoring paradigms leveraging low-cost sensors and mobile platforms.

OBJECTIVES

We aim to provide a conceptual summary of novel monitoring designs for air pollution cohort studies that leverage new paradigms and technologies, to investigate their characteristics in real-world examples, and to offer practical guidance to future studies.

METHODS

We propose a conceptual summary that focuses on two overarching types of monitoring designs, mobile and non-mobile, as well as their subtypes. We define mobile designs as monitoring from a moving platform, and non-mobile designs as stationary monitoring from permanent or temporary locations. We only consider non-mobile studies with cost-effective sampling devices. Then we discuss similarities and differences across previous studies with respect to spatial and temporal representation, data comparability between design classes, and the data leveraged for model development. Finally, we provide specific suggestions for future monitoring designs.

RESULTS

Most mobile and non-mobile monitoring studies selected monitoring sites based on land use instead of residential locations, and deployed monitors over limited time periods. Some studies applied multiple design and/or sub-design classes to the same area, time period, or instrumentation, to allow comparison. Even fewer studies leveraged monitoring data from different designs to improve exposure assessment by capitalizing on different strengths. In order to maximize the benefit of new monitoring technologies, future studies should adopt monitoring designs that prioritize residence-based site selection with comprehensive temporal coverage and leverage data from different designs for model development in the presence of good data compatibility.

DISCUSSION

Our conceptual overview provides practical guidance on novel exposure assessment monitoring for epidemiological applications.

Design, calibration, and testing of a mobile sensor system for air pollution and built environment data collection: The urban scanner platform

This paper describes a mobile air pollution sampling system, the Urban Scanner, which aims at gathering dense spatiotemporal air quality data to support urban air quality and exposure science. Urban Scanner comprises custom vehicle-mounted sensors for air pollution, meteorology, and built environment data collection (low-cost sensors, wind anemometer, 360 deg camera, LIDAR, GPS) as well as a server to store, process, and map all gathered geo-referenced sensory information. Two levels of sensor calibration were implemented, both in a chamber and in the field, against reference instrumentation. Chamber tests and a set of mathematical tools were developed to correct for sensor noise (wavelet denoising), misalignment (linear and nonlinear), and hysteresis removal. Models based on chamber testing were further refined based on field co-location. While field co-location captures natural changes in air pollution and meteorology, chamber tests allow for simulating fast transitions in these variables, like the transitions experienced by a mobile sensor in an urban environment. The best suite of models achieved an R² higher than 0.9 between sensor output and reference station observations and an RMSE of 2.88 ppb for nitrogen dioxide and 4.03 ppb for ozone. A mobile sampling campaign was conducted in the city of Toronto, Canada, to further test Urban Scanner. We observe that the platform adequately captures spatial and temporal variability in urban air pollution, leading to the development of land-use regression models with high explanatory power.

Impact of Mobile Monitoring Network Design on Air Pollution Exposure Assessment Models

Short-term mobile monitoring campaigns are increasingly used to assess long-term air pollution exposure in epidemiology. Little is known about how monitoring network design features, including the number of stops and sampling temporality, impacts exposure assessment models. We address this gap by leveraging an extensive mobile monitoring campaign conducted in the greater Seattle area over the course of a year during all days of the week and most hours. The campaign measured total particle number concentration (PNC; sheds light on ultrafine particulate (UFP) number concentration), black carbon (BC), nitrogen dioxide (NO2), fine particulate matter (PM2.5), and carbon dioxide (CO2). In Monte Carlo sampling of 7327 total stops (278 sites × 26 visits each), we restricted the number of sites and visits used to estimate annual averages. Predictions from the all-data campaign performed well, with cross-validated R2s of 0.51-0.77. We found similar model performances (85% of the all-data campaign R2) with ∼1000 to 3000 randomly selected stops for NO2, PNC, and BC, and ∼4000 to 5000 stops for PM2.5 and CO2. Campaigns with additional temporal restrictions (e.g., business hours, rush hours, weekdays, or fewer seasons) had reduced model performances and different spatial surfaces. Mobile monitoring campaigns wanting to assess long-term exposure should carefully consider their monitoring designs.

Identifying Patterns and Sources of Fine and Ultrafine Particulate Matter in London Using Mobile Measurements of Lung-Deposited Surface Area

We performed more than a year of mobile, 1 Hz measurements of lung-deposited surface area (LDSA, the surface area of 20-400 nm diameter particles, deposited in alveolar regions of lungs) and optically assessed fine particulate matter (PM_2.5), black carbon (BC), and nitrogen dioxide (NO₂) in central London. We spatially correlated these pollutants to two urban emission sources: major roadways and restaurants. We show that optical PM_2.5 is an ineffective indicator of tailpipe emissions on major roadways, where we do observe statistically higher LDSA, BC, and NO₂. Additionally, we find pollutant hot spots in commercial neighborhoods with more restaurants. A low LDSA (15 μm² cm^-3) occurs in areas with fewer major roadways and restaurants, while the highest LDSA (25 μm² cm^-3) occurs in areas with more of both sources. By isolating areas that are higher in one source than the other, we demonstrate the comparable impacts of traffic and restaurants on LDSA. Ratios of hyperlocal enhancements (ΔLDSA:ΔBC and ΔLDSA:ΔNO₂) are higher in commercial neighborhoods than on major roadways, further demonstrating the influence of restaurant emissions on LDSA. We demonstrate the added value of using particle surface in identifying hyperlocal patterns of health-relevant PM components, especially in areas with strong vehicular emissions where the high LDSA does not translate to high PM_2.5.

Hyperlocal variation of nitrogen dioxide, black carbon, and ultrafine particles measured with Google Street View cars in Amsterdam and Copenhagen

Hyperlocal air quality maps are becoming increasingly common, as they provide useful insights into the spatial variation and sources of air pollutants. In this study, we produced several high-resolution concentration maps to assess the spatial differences of three traffic-related pollutants, Nitrogen dioxide (NO₂), Black Carbon (BC) and Ultrafine Particles (UFP), in Amsterdam, the Netherlands, and Copenhagen, Denmark. All maps were based on a mixed-effect model approach by using state-of-the-art mobile measurements conducted by Google Street View (GSV) cars, during October 2018 - March 2020, and Land-use Regression (LUR) models based on several land-use and traffic predictor variables. We then explored the concentration ratio between the different normalised pollutants to understand possible contributing sources to the observed hyperlocal variations. The maps developed in this work reflect, (i) expected elevated pollution concentrations along busy roads, and (ii) similar concentration patterns on specific road types, e.g., motorways, for both cities. In the ratio maps, we observed a clear pattern of elevated concentrations of UFP near the airport in both cities, compared to BC and NO₂. This is the first study to produce hyperlocal maps for BC and UFP using high-quality mobile measurements. These maps are important for policymakers and health-effect studies, trying to disentangle individual effects of key air pollutants of interest (e.g., UFP).

National Exposure Models for Source-Specific Primary Particulate Matter Concentrations Using Aerosol Mass Spectrometry Data

This paper investigates the feasibility of developing national empirical models to predict ambient concentrations of sparsely monitored air pollutants at high spatial resolution. We used a data set of cooking organic aerosol (COA) and hydrocarbon-like organic aerosol (HOA; traffic primary organic PM) measured using aerosol mass spectrometry across the continental United States. The monitoring locations were selected to span the national distribution of land-use and source-activity variables commonly used for land-use regression modeling (e.g., road length, restaurant count, etc.). The models explain about 60% of the spatial variability of the measured data (R² 0.63 for the COA model and 0.62 for the HOA model). Extensive cross-validation suggests that the models are robust with reasonable transferability. The models predict large urban-rural and intra-urban variability with hotspots in urban areas and along the road corridors. The predicted national concentration surfaces show reasonable spatial correlation with source-specific national chemical transport model (CTM) simulations (R²: 0.45 for COA, 0.4 for HOA). Our measured data, empirical models, and CTM predictions all show that COA concentrations are about two times higher than HOA. Since COA and HOA are important contributors to the intra-urban spatial variability of the total PM_2.5, our results highlight the potential importance of controlling commercial cooking emissions for air quality management in the United States.

A Knowledge Transfer Approach to Map Long-Term Concentrations of Hyperlocal Air Pollution from Short-Term Mobile Measurements

Mobile measurements are increasingly used to develop spatially explicit (hyperlocal) air quality maps using land-use regression (LUR) models. The prevailing design of mobile monitoring campaigns results in the collection of short-term, on-road air pollution measurements during daytime on weekdays. We hypothesize that LUR models trained with such mobile measurements are not optimized for estimating long-term average residential air pollution concentrations. To bridge the knowledge gaps in space (on-road versus near-road) and time (short- versus long-term), we propose transfer-learning techniques to adapt LUR models by transferring the mobile knowledge into long-term near-road knowledge in an end-to-end manner. We trained two transfer-learning LUR models by incorporating mobile measurements of nitrogen dioxide (NO2) and ultrafine particles (UFP) collected by Google Street View cars with long-term near-road measurements from regular monitoring networks in Amsterdam. We found that transfer-learning LUR models performed 55.2% better in predicting long-term near-road concentrations than the LUR model trained only with mobile measurements for NO2 and 26.9% for UFP, evaluated by normalized mean absolute errors. This improvement in model accuracy suggests that transfer-learning models provide a solution for narrowing the knowledge gaps and can improve the accuracy of mapping long-term near-road air pollution concentrations using short-term on-road mobile monitoring data.

Optimized environmental justice calculations for air pollution disparities in Southern California

An Environmental Justice (EJ) analysis was carried out using full Chemical Transport Models (CTMs) over Los Angeles, California, to determine how the combination of domain size and spatial resolution affects predicted air pollution disparities in present day and future simulations when data support from measurements is not available. One set of simulations used the Weather Research and Forecasting (WRF) model coupled with Chemistry (WRF/Chem) with spatial resolution ranging from 250 m to 36 km, comparable to census tract sizes, over domains ranging in size from 320 km² to 10,000 km². A second set of simulations used the UCD/CIT CTM with spatial resolution ranging from 4 km to 24 km over domains ranging in size from 98,000 km² to 1,000,000 km². Overall WRF/Chem model accuracy improved approximately 9% as spatial resolution increased from 4 km to 250 m in present-day simulations, with similar results expected for future simulations. Exposure disparity results are consistent with previous findings: the average Non-Hispanic White person in the study domain experiences PM_2.5 mass concentrations 6-14% lower than the average resident, while the average Black and African American person experiences PM_2.5 mass concentrations that are 3-22% higher than the average resident. Predicted exposure disparities were a function of the model configuration. Increasing the spatial resolution finer than approximately 1 km produced diminishing returns because the increased spatial resolution came at the expense of reduced domain size in order to maintain reasonable computational burden. Increasing domain size to capture regional trends, such as wealthier populations living in coastal areas, identified larger exposure disparities but the benefits were limited. CTM configurations that use spatial resolution/domain size of 1 km/10³ km² and 4 km/10⁴ km² over Los Angeles can detect a 0.5 μg m^-3 exposure difference with statistical power greater than 90%. These configurations represent a balanced approach between statistical power, sensitivity across socio-economic groups, and computational burden when predicting current and future air pollution exposure disparities in Los Angeles.

National Land Use Regression Model for NO2 Using Street View Imagery and Satellite Observations

Land use regression (LUR) models are widely applied to estimate intra-urban air pollution concentrations. National-scale LURs typically employ predictors from multiple curated geodatabases at neighborhood scales. In this study, we instead developed national NO₂ models relying on innovative street-level predictors extracted from Google Street View [GSV] imagery. Using machine learning (random forest), we developed two types of models: (1) GSV-only models, which use only GSV features, and (2) GSV + OMI models, which also include satellite observations of NO₂. Our results suggest that street view imagery alone may provide sufficient information to explain NO₂ variation. Satellite observations can improve model performance, but the contribution decreases as more images are available. Random 10-fold cross-validation R² of our best models were 0.88 (GSV-only) and 0.91 (GSV + OMI)─a performance that is comparable to traditional LUR approaches. Importantly, our models show that street-level features might have the potential to better capture intra-urban variation of NO₂ pollution than traditional LUR. Collectively, our findings indicate that street view image-based modeling has great potential for building large-scale air quality models under a unified framework. Toward that goal, we describe a cost-effective image sampling strategy for future studies based on a systematic evaluation of image availability and model performance.

Prediction of Short-Term Ultrafine Particle Exposures Using Real-Time Street-Level Images Paired with Air Quality Measurements

Within-city ultrafine particle (UFP) concentrations vary sharply since they are influenced by various factors. We developed prediction models for short-term UFP exposures using street-level images collected by a camera installed on a vehicle rooftop, paired with air quality measurements conducted during a large-scale mobile monitoring campaign in Toronto, Canada. Convolutional neural network models were trained to extract traffic and built environment features from images. These features, along with regional air quality and meteorology data were used to predict short-term UFP concentration as a continuous and categorical variable. A gradient boost model for UFP as a continuous variable achieved R² = 0.66 and RMSE = 9391.8#/cm³ (mean values for 10-fold cross-validation). The model predicting categorical UFP achieved accuracies for "Low" and "High" UFP of 77 and 70%, respectively. The presence of trucks and other traffic parameters were associated with higher UFPs, and the spatial distribution of elevated short-term UFP followed the distribution of single-unit trucks. This study demonstrates that pictures captured on urban streets, associated with regional air quality and meteorology, can adequately predict short-term UFP exposure. Capturing the spatial distribution of high-frequency short-term UFP spikes in urban areas provides crucial information for the management of near-road air pollution hot spots.

Characterization of Annual Average Traffic-Related Air Pollution Concentrations in the Greater Seattle Area from a Year-Long Mobile Monitoring Campaign

Growing evidence links traffic-related air pollution (TRAP) to adverse health effects. We designed an innovative and extensive mobile monitoring campaign to characterize TRAP exposure levels for the Adult Changes in Thought (ACT) study, a Seattle-based cohort. The campaign measured particle number concentration (PNC) to capture ultrafine particles (UFP), black carbon (BC), nitrogen dioxide (NO2), fine particulate matter (PM2.5), and carbon dioxide (CO2) at 309 roadside sites within a large, 1200 land km2 (463 mi2) area representative of the cohort. We collected about 29 two-minute measurements at each site during all seasons, days of the week, and most times of the day over a 1-year period. Validation showed good agreement between our BC, NO2, and PM2.5 measurements and monitoring agency sites (R2 = 0.68-0.73). Universal kriging-partial least squares models of annual average pollutant concentrations had cross-validated mean square error-based R2 (and root mean square error) values of 0.77 (1177 pt/cm3) for PNC, 0.60 (102 ng/m3) for BC, 0.77 (1.3 ppb) for NO2, 0.70 (0.3 μg/m3) for PM2.5, and 0.51 (4.2 ppm) for CO2. Overall, we found that the design of this extensive campaign captured the spatial pollutant variations well and these were explained by sensible land use features, including those related to traffic.

Assessing and Validating the Ability of Machine Learning to Handle Unrefined Particle Air Pollution Mobile Monitoring Data Randomly, Spatially, and Spatiotemporally

Many epidemiological studies have evaluated the accuracy of machine learning models in predicting levels of particulate number (PN) and black carbon (BC) pollutant concentrations. However, few studies have investigated the ability of machine learning to predict the pollutant concentration with using unrefined mobile measurement data and explore the reliability of the prediction models. Additionally, researchers are moving away from using fixed-site data in favor of using mobile monitoring data in a variety of locations to develop hourly empirical models of particulate air pollution. This study compared the differences between long-term (daily average) and short-term (hourly average and 1 s unrefined data) model performance in three different classes of cross validation: randomly, spatially, and spatially temporally. This study used secondary data describing BC and PN pollutant levels in the rural location of Blacksburg (VA). Our results show that the model based on unrefined data was able to detect the pollutant hot spot areas with similar accuracy compared to the aggregated model. Moreover, the performance was found to improve when temporal data added to the model: the 10-fold MAE for the BC and PN were 0.44 μg/m³ and 3391 pt/cm³, respectively, for the unrefined data (one second data) model. The findings detailed here will add to the literature on the correlation between data (pre)processing and the efficacy of machine learning models in predicting pollution levels while also enhancing our understanding of more reliable validation strategies.

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

Assessing exposure to fine particulate matter (PM2.5) 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 PM2.5 concentrations from June 2021 to December 2021. We identified the spatial and temporal patterns of PM2.5 measurements as well as the relationship between the total PM2.5 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 PM2.5 concentrations. The average PM2.5 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.

What you see is what you breathe? Estimating air pollution spatial variation using street level imagery

High spatial resolution information on urban air pollution levels is unavailable in many areas globally, partially due to high input data needs of existing estimation approaches. Here we introduce a computer vision method to estimate annual means for air pollution levels from street level images. We used annual mean estimates of NO2 and PM2.5 concentrations from locally calibrated models as labels from London, New York, and Vancouver to allow for compilation of a sufficiently large dataset (~250k images for each city). Our experimental setup is designed to quantify intra and intercity transferability of image-based model estimates. Performances were high and comparable to traditional land-use regression (LUR) and dispersion models when training and testing on images from the same city (R2 values between 0.51 and 0.95 when validated on data from ground monitoring stations). Like LUR models, transferability of models between cities in different geographies is more difficult. Specifically, transferability between the three cities i.e., London, New York, and Vancouver, which have similar pollution source profiles were moderately successful (R2 values between zero and 0.67). Comparatively, performances when transferring models trained on these cities with very different source profiles i.e., Accra in Ghana and Hong Kong were lower (R2 between zero and 0.21) suggesting the need for local calibration with local calibration using additional measurement data from cities that share similar source profiles.

Three-dimensional building morphology impacts on PM2.5 distribution in urban landscape settings in Zhejiang, China

Three-dimensional (3D) urban landscape patterns and building morphology are crucial for urban planning and essential for urban landscape functions. In this study, fixed and mobile monitoring sites were used to determine the spatial distribution of PM_2.5 concentrations in Hangzhou. Six 3D metrics were selected to analyze the response of PM_2.5 pollution to landscape patterns and building morphology, while their two-dimensional (2D) counterparts' metrics were also analyzed to contrast the differences. A variance partitioning analysis (VPA) was performed to measure the combined and relative contribution of 3D and 2D metrics to the changes in PM_2.5 concentrations. The results showed that: (1) on the 3D scale, forming a building pattern with a combination of different building heights can eliminate the accumulation of PM_2.5; (2) on the 2D scale, fragmentation and decentralization of landscapes and building patches alleviate PM_2.5 pollution; and (3) 3D building morphology indicators have the highest explanatory power (40.94%) for the changes of PM_2.5 concentrations. It turns out that the explanatory power of 3D metrics for PM_2.5 concentrations changes is much greater than that of 2D metrics. In addition, when compared to building morphology indicators from a single dimension, the combination of 2D and 3D metrics is better able to reflect urban PM_2.5 pollution. The results of this study expand our understanding of how PM_2.5 pollution responds to 2D and 3D metrics and provide useful information for urban planning.

Mixed-Effects Modeling Framework for Amsterdam and Copenhagen for Outdoor NO2 Concentrations Using Measurements Sampled with Google Street View Cars

High-resolution air quality (AQ) maps based on street-by-street measurements have become possible through large-scale mobile measurement campaigns. Such campaigns have produced data-only maps and have been used to produce empirical models [i.e., land use regression (LUR) models]. Assuming that all road segments are measured, we developed a mixed model framework that predicts concentrations by an LUR model, while allowing road segments to deviate from the LUR prediction based on between-segment variation as a random effect. We used Google Street View cars, equipped with high-quality AQ instruments, and measured the concentration of NO₂ on every street in Amsterdam (n = 46.664) and Copenhagen (n = 28.499) on average seven times over the course of 9 and 16 months, respectively. We compared the data-only mapping, LUR, and mixed model estimates with measurements from passive samplers (n = 82) and predictions from dispersion models in the same time window as mobile monitoring. In Amsterdam, mixed model estimates correlated r_s (Spearman correlation) = 0.85 with external measurements, whereas the data-only approach and LUR model estimates correlated r_s = 0.74 and 0.75, respectively. Mixed model estimates also correlated higher r_s = 0.65 with the deterministic model predictions compared to the data-only (r_s = 0.50) and LUR model (r_s = 0.61). In Copenhagen, mixed model estimates correlated r_s = 0.51 with external model predictions compared to r_s = 0.45 and r_s = 0.50 for data-only and LUR model, respectively. Correlation increased for 97 locations (r_s = 0.65) with more detailed traffic information. This means that the mixed model approach is able to combine the strength of data-only mapping (to show hyperlocal variation) and LUR models by shrinking uncertain concentrations toward the model output.

Insights from Application of a Hierarchical Spatio-Temporal Model to an Intensive Urban Black Carbon Monitoring Dataset

Existing regulatory pollutant monitoring networks rely on a small number of centrally located measurement sites that are purposefully sited away from major emission sources. While informative of general air quality trends regionally, these networks often do not fully capture the local variability of air pollution exposure within a community. Recent technological advancements have reduced the cost of sensors, allowing air quality monitoring campaigns with high spatial resolution. The 100×100 black carbon (BC) monitoring network deployed 100 low-cost BC sensors across the 15 km² West Oakland, CA community for 100 days in the summer of 2017, producing a nearly continuous site-specific time series of BC concentrations which we aggregated to one-hour averages. Leveraging this dataset, we employed a hierarchical spatio-temporal model to accurately predict local spatio-temporal concentration patterns throughout West Oakland, at locations without monitors (average cross-validated hourly temporal R ²=0.60). Using our model, we identified spatially varying temporal pollution patterns associated with small-scale geographic features and proximity to local sources. In a sub-sampling analysis, we demonstrated that fine scale predictions of nearly comparable accuracy can be obtained with our modeling approach by using ~30% of the 100×100 BC network supplemented by a shorter-term high-density campaign.

Ambient Air Pollution Exposure Assessments in Fertility Studies: a Systematic Review and Guide for Reproductive Epidemiologists

Purpose of Review

We reviewed the exposure assessments of ambient air pollution used in studies of fertility, fecundability, and pregnancy loss.

Recent Findings

Comprehensive literature searches were performed in the PUBMED, Web of Science, and Scopus databases. Of 168 total studies, 45 met the eligibility criteria and were included in the review. We find that 69% of fertility and pregnancy loss studies have used one-dimensional proximity models or surface monitor data, while only 35% have used the improved models, such as land-use regression models (4%), dispersion/chemical transport models (11%), or fusion models (20%). No published studies have used personal air monitors.

Summary

While air pollution exposure models have vastly improved over the past decade from a simple, one-dimensional distance or air monitor data to models that incorporate physiochemical properties leading to better predictive accuracy, precision, and increased spatiotemporal variability and resolution, the fertility literature has yet to fully incorporate these new methods. We provide descriptions of each of these air pollution exposure models and assess the strengths and limitations of each model, while summarizing the findings of the literature on ambient air pollution and fertility that apply each method.

Selecting Data Analytic and Modeling Methods to Support Air Pollution and Environmental Justice Investigations: A Critical Review and Guidance Framework

Given the serious adverse health effects associated with many pollutants, and the inequitable distribution of these effects between socioeconomic groups, air pollution is often a focus of environmental justice (EJ) research. However, EJ analyses that aim to illuminate whether and how air pollution hazards are inequitably distributed may present a unique set of requirements for estimating pollutant concentrations compared to other air quality applications. Here, we perform a scoping review of the range of data analytic and modeling methods applied in past studies of air pollution and environmental injustice and develop a guidance framework for selecting between them given the purpose of analysis, users, and resources available. We include proxy, monitor-based, statistical, and process-based methods. Upon critically synthesizing the literature, we identify four main dimensions to inform method selection: accuracy, interpretability, spatiotemporal features of the method, and usability of the method. We illustrate the guidance framework with case studies from the literature. Future research in this area includes an exploration of increasing data availability, advanced statistical methods, and the importance of science-based policy.

Hyperlocalized Measures of Air Pollution and Preeclampsia in Oakland, California

Exposure to nitrogen dioxide (NO₂), black carbon (BC), and ultrafine particles (UFPs) during pregnancy may increase the risk of preeclampsia, but previous studies have not assessed hyperlocalized differences in pollutant levels, which may cause exposure misclassification. We used data from Google Street View cars with mobile air monitors that repeatedly sampled NO₂, BC, and UFPs every 30 m in Downtown and West Oakland neighborhoods during 2015-2017. Data were linked to electronic health records of pregnant women in the 2014-2016 Sutter Health population, who resided within 120 m of monitoring data (N = 1095), to identify preeclampsia cases. We used G-computation with log-binomial regression to estimate risk differences (RDs) associated with a hypothetical intervention reducing pollutant levels to the 25th percentile observed in our sample on preeclampsia risk, overall and stratified by race/ethnicity. Prevalence of preeclampsia was 6.8%. Median (interquartile range) levels of NO₂, BC, and UFPs were 10.8 ppb (9.0, 13.0), 0.34 μg/m³ (0.27, 0.42), and 29.2 # × 10³/cm³ (26.6, 32.6), respectively. Changes in the risk of preeclampsia achievable by limiting each pollutant to the 25th percentile were NO₂ RD = -1.5 per 100 women (95% confidence interval (CI): -2.5, -0.5); BC RD = -1.0 (95% CI: -2.2, 0.02); and UFP RD = -0.5 (95% CI: -1.8, 0.7). Estimated effects were the largest for non-Latina Black mothers: NO₂ RD = -2.8 (95% CI: -5.2, -0.3) and BC RD = -3.0 (95% CI: -6.4, 0.4).

Improving emissions inputs via mobile measurements to estimate fine-scale Black Carbon monthly concentrations through geostatistical space-time data fusion

Isolating air pollution sources in a complex transportation environment to quantify their contribution is challenging, particularly with sparse stationary measurements. Mobile measurements can add finer spatial resolution to support source apportionment, but they exhibit limitations when characterizing long term concentrations. Dispersion models can help overcome these limitations. However, they are only as reliable as their input emissions inventories. Herein, we developed an innovative method to revise emissions through inverse modeling and improve dispersion modeling predictions using stationary/mobile measurements. One specific revision estimated an adjustment factor of ~306 for warehouse emissions, indicating a significant underestimation of our initial estimates. This revised emission rate scaled up nationally would correspond to ~3.5% of the total Black Carbon emissions in the U.S. Nevertheless, domain-specific revisions only contribute to a 4% increase of area source emissions while improving R² from monthly estimates at fixed sites by 38%. After revising emissions through inverse dispersion modeling, we combine this model with stationary/mobile measurements through Bayesian Maximum Entropy (I-DISP BME) to produce temporally coarse yet spatially fine data fusion. We compare this novel data fusion approach to BME using only measurements (Flat BME). A 10-fold conventional cross-validation (representative of months with mobile measurements) shows that all BME methods have R² values that range from 0.787 to 0.798. A 2-fold cross-validation (representative of months with no mobile measurements) shows that the R² for I-DISP BME increases by a factor 90 when compared to Flat BME. Furthermore, not only is our novel I-DISP BME method more accurate than the classic Flat BME method, but the area it detects as highly exposed can be up to 5 times larger than that detected by the less accurate Flat BME method.

Estimating Intra-Urban Inequities in PM2.5-Attributable Health Impacts: A Case Study for Washington, DC

Air pollution levels are uneven within cities, contributing to persistent health disparities between neighborhoods and population sub-groups. Highly spatially resolved information on pollution levels and disease rates is necessary to characterize inequities in air pollution exposure and related health risks. We leverage recent advances in deriving surface pollution levels from satellite remote sensing and granular data in disease rates for one city, Washington, DC, to assess intra-urban heterogeneity in fine particulate matter (PM2.5)- attributable mortality and morbidity. We estimate PM2.5-attributable cases of all-cause mortality, chronic obstructive pulmonary disease, ischemic heart disease, lung cancer, stroke, and asthma emergency department (ED) visits using epidemiologically derived health impact functions. Data inputs include satellite-derived annual mean surface PM2.5 concentrations; age-resolved population estimates; and statistical neighborhood-, zip code- and ward-scale disease counts. We find that PM2.5 concentrations and associated health burdens have decreased in DC between 2000 and 2018, from approximately 240 to 120 cause-specific deaths and from 40 to 30 asthma ED visits per year (between 2014 and 2018). However, remaining PM2.5-attributable health risks are unevenly and inequitably distributed across the District. Higher PM2.5-attributable disease burdens were found in neighborhoods with larger proportions of people of color, lower household income, and lower educational attainment. Our study adds to the growing body of literature documenting the inequity in air pollution exposure levels and pollution health risks between population sub-groups, and highlights the need for both high-resolution disease rates and concentration estimates for understanding intra-urban disparities in air pollution-related health risks.

Assessing the intra-urban variability of nitrogen oxides and ozone across a highly heterogeneous urban area

High-resolution air quality maps are critical towards assessing and understanding exposures to elevated air pollution in dense urban areas. However, these surfaces are rarely available in low- and middle-income countries that suffer from some of the highest air pollution levels worldwide. In this study, we make use of land use regressions (LURs) to generate annual and seasonal, high-resolution nitrogen dioxide (NO₂), nitrogen oxides (NO_x), and ozone (O₃) exposure surfaces for the Greater Beirut Area (GBA) in Lebanon. NO₂, NO_x and O₃ concentrations were monitored using passive samplers that were deployed at 55 pre-defined monitoring locations. The average annual concentrations of NO₂, NO_x, and O₃ across the GBA were 36.0, 89.7, and 26.9 ppb, respectively. Overall, the performance of the generated models was appropriate, with low biases, high model robustness, and acceptable R² values that ranged between 0.66 and 0.73 for NO₂, 0.56 and 0.60 for NO_x, and 0.54 and 0.65 for O₃. Traffic-related emissions as well as the operation of a fossil-fuel power plant were found to be the main contributors to the measured NO₂ and NO_x levels in the GBA, whereas they acted as sinks for O₃ concentrations. No seasonally significant differences were found for the NO₂ and NO_x pollution surfaces; as their seasonal and annual models were largely similar (Pearson's r > 0.85 for both pollutants). On the other hand, seasonal O₃ pollution surfaces were significantly different. The model results showed that around 99% of the population of the GBA were exposed to NO₂ levels that exceeded the World Health Organization defined annual standard.

Local- and regional-scale racial and ethnic disparities in air pollution determined by long-term mobile monitoring

Disparity in air pollution exposure arises from variation at multiple spatial scales: along urban-to-rural gradients, between individual cities within a metropolitan region, within individual neighborhoods, and between city blocks. Here, we improve on existing capabilities to systematically compare urban variation at several scales, from hyperlocal (<100 m) to regional (>10 km), and to assess consequences for outdoor air pollution experienced by residents of different races and ethnicities, by creating a set of uniquely extensive and high-resolution observations of spatially variable pollutants: NO, NO2, black carbon (BC), and ultrafine particles (UFP). We conducted full-coverage monitoring of a wide sample of urban and suburban neighborhoods (93 km2 and 450,000 residents) in four counties of the San Francisco Bay Area using Google Street View cars equipped with the Aclima mobile platform. Comparing scales of variation across the sampled population, greater differences arise from localized pollution gradients for BC and NO (pollutants dominated by primary sources) and from regional gradients for UFP and NO2 (pollutants dominated by secondary contributions). Median concentrations of UFP, NO, and NO2 are, for Hispanic and Black populations, 8 to 30% higher than the population average; for White populations, average exposures to these pollutants are 9 to 14% lower than the population average. Systematic racial/ethnic disparities are influenced by regional concentration gradients due to sharp contrasts in demographic composition among cities and urban districts, while within-group extremes arise from local peaks. Our results illustrate how detailed and extensive fine-scale pollution observations can add new insights about differences and disparities in air pollution exposures at the population scale.

Mobile monitoring and spatial prediction of black carbon in Cairo, Egypt

This study harnesses the power of mobile data in developing a spatial model for predicting black carbon (BC) concentrations within one of the most heavily populated regions in the Middle East and North Africa MENA region, Greater Cairo Region (GCR) in Egypt. A mobile data collection campaign was conducted in GCR to collect BC measurements along specific travel routes. In total, 3,300 km were travelled across a widespread 525 km of routes. Reported average BC values were around 20 µg/m³, announcing an alarming order of magnitude value when compared to the maximum reported values in similar studies. A bi-directional stepwise land use regression (LUR) model was developed to select the best combination of explanatory variables and generate an exposure surface for BC, in addition to a number of machine learning models (random forest gradient boost, light gradient boost model (LightGBM), Keras neural network (NN)). Data from 7 air quality (AQ) stations were compared-in terms of mean square error (MSE) and mean absolute error (MAE)-with predictions from the LUR and the NN model. The NN model estimated higher BC concentrations in the downtown areas, while lower concentrations are estimated for the peripheral area at the east side of the city. Such results shed light on the credibility of the LUR models in generating a general spatial trend of BC concentrations while the superiority of NN in BC accuracy estimation (0.023 vs 0.241 in terms of MSE and 0.12 vs 0.389 in terms of MAE; of NN vs LUR respectively).

High-Spatial-Resolution Estimates of Ultrafine Particle Concentrations across the Continental United States

There is growing evidence that ultrafine particles (UFP; particles smaller than 100 nm) are likely more toxic than larger particles. However, the health effects of UFP remain uncertain due in part to the lack of large-scale population-based exposure assessment. We develop a national-scale empirical model of particle number concentration (PNC; a measure of UFP) using data from mobile monitoring and fixed sites across the United States and a land-use regression (LUR) modeling framework. Traffic, commercial land use, and urbanicity-related variables explain much of the spatial variability of PNC (base model R² = 0.77, RMSE = 2400 cm^-3). Model predictions are robust across a diverse set of evaluations [random 10-fold holdout cross-validation (HCV): R² = 0.72, RMSE = 2700 cm^-3; spatially defined HCV: R² = 0.66, RMSE = 3000 cm^-3; evaluation against an independent data set: R² = 0.54, RMSE = 2600 cm^-3]. We apply our model to predict PNC at ∼6 million residential census blocks in the contiguous United States. Our estimates are annual average concentrations for 2016-2017. The predicted national census-block-level mean PNC ranges between 1800 and 26 600 cm^-3 (population-weighted average: 6500 cm^-3), with hotspots in cities and near highways. Our national PNC model predicts large urban-rural, intra-, and inter-city contrasts. PNC and PM_2.5 are moderately correlated at the city scale, but uncorrelated at the regional/national scale. Our high-spatial-resolution national PNC estimates are useful for analyzing population exposure (socioeconomic disparity, epidemiological health impact) and environmental policy and regulation.