ACS Publications. Most Trusted. Most Cited. Most Read
My Activity
CONTENT TYPES

Figure 1Loading Img
RETURN TO ISSUEPREVAnthropogenic Impact...Anthropogenic Impacts on the AtmosphereNEXT

Development of Europe-Wide Models for Particle Elemental Composition Using Supervised Linear Regression and Random Forest

  • Jie Chen*
    Jie Chen
    Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The Netherlands
    *Email: [email protected]
    More by Jie Chen
  • Kees de Hoogh
    Kees de Hoogh
    Swiss Tropical and Public Health Institute, Socinstrasse 57, 4051 Basel, Switzerland
    University of Basel, Petersplatz 1, Postfach 4001 Basel, Switzerland
  • John Gulliver
    John Gulliver
    Centre for Environmental Health and Sustainability, School of Geography, Geology and the Environment, University of Leicester, University Road, LE1 7RH Leicester, U.K.
  • Barbara Hoffmann
    Barbara Hoffmann
    Institute for Occupational, Social and Environmental Medicine, Centre for Health and Society, Medical Faculty, Heinrich Heine University Düsseldorf, Universitätsstraße 1, 40225 Düsseldorf, Germany
  • Ole Hertel
    Ole Hertel
    Department of Environmental Science, Aarhus University, P.O. Box 358, Frederiksborgvej 399, 4000 Roskilde, Denmark
    More by Ole Hertel
  • Matthias Ketzel
    Matthias Ketzel
    Department of Environmental Science, Aarhus University, P.O. Box 358, Frederiksborgvej 399, 4000 Roskilde, Denmark
    Global Centre for Clean Air Research (GCARE), Department of Civil and Environmental Engineering, University of Surrey, GU2 7XH Guildford, U.K.
  • Gudrun Weinmayr
    Gudrun Weinmayr
    Institute of Epidemiology and Medical Biometry, Ulm University, Helmholtzstr. 22, 89081 Ulm, Germany
  • Mariska Bauwelinck
    Mariska Bauwelinck
    Interface Demography—Department of Sociology, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium
  • Aaron van Donkelaar
    Aaron van Donkelaar
    Department of Physics and Atmospheric Science, Dalhousie University, B3H 4R2 Halifax, Nova Scotia, Canada
    Department of Energy, Environmental & Chemical Engineering, Washington University in St. Louis, 63130 St. Louis, Missouri, United States
  • Ulla A. Hvidtfeldt
    Ulla A. Hvidtfeldt
    Danish Cancer Society Research Center, Strandboulevarden 49, 2100 Copenhagen, Denmark
  • Richard Atkinson
    Richard Atkinson
    St George’s University of London, SW17 0RE London, U.K.
  • Nicole A. H. Janssen
    Nicole A. H. Janssen
    National Institute for Public Health and the Environment (RIVM), P.O. Box 1, 3720 BA Bilthoven, The Netherlands
  • Randall V. Martin
    Randall V. Martin
    Danish Cancer Society Research Center, Strandboulevarden 49, 2100 Copenhagen, Denmark
    Department of Physics and Atmospheric Science, Dalhousie University, B3H 4R2 Halifax, Nova Scotia, Canada
    Atomic and Molecular Physics Division, Harvard-Smithsonian Center for Astrophysics, Cambridge, 60 Garden Street, 02138 Cambridge, Massachusetts, United States
  • Evangelia Samoli
    Evangelia Samoli
    Department of Hygiene, Epidemiology and Medical Statistics, Medical School, National and Kapodistrian University of Athens, 75 Mikras Asias Str, 115 27 Athens, Greece
  • Zorana J. Andersen
    Zorana J. Andersen
    University of Copenhagen, 1165 Copenhagen, Denmark
  • Bente M. Oftedal
    Bente M. Oftedal
    Department of Environmental Health, Norwegian Institute of Public Health, P.O. Box 4404 Nydalen, N-0403 Oslo, Norway
  • Massimo Stafoggia
    Massimo Stafoggia
    Department of Epidemiology, Lazio Region Health Service/ASL Roma 1, Via Cristoforo Colombo, 112, 00147 Rome, Italy
    Institute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden
  • Tom Bellander
    Tom Bellander
    Institute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden
  • Maciej Strak
    Maciej Strak
    Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The Netherlands
    Atomic and Molecular Physics Division, Harvard-Smithsonian Center for Astrophysics, Cambridge, 60 Garden Street, 02138 Cambridge, Massachusetts, United States
    More by Maciej Strak
  • Kathrin Wolf
    Kathrin Wolf
    Helmholtz Zentrum München, German Research Center for Environmental Health (GmbH), Institute of Epidemiology, Ingolstädter Landstr. 1, D-85764 Neuherberg, Germany
    More by Kathrin Wolf
  • Danielle Vienneau
    Danielle Vienneau
    Swiss Tropical and Public Health Institute, Socinstrasse 57, 4051 Basel, Switzerland
    University of Basel, Petersplatz 1, Postfach 4001 Basel, Switzerland
  • Bert Brunekreef
    Bert Brunekreef
    Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The Netherlands
    Julius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, Netherlands
  • , and 
  • Gerard Hoek
    Gerard Hoek
    Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The Netherlands
    More by Gerard Hoek
Cite this: Environ. Sci. Technol. 2020, 54, 24, 15698–15709
Publication Date (Web):November 25, 2020
https://doi.org/10.1021/acs.est.0c06595

Copyright © 2020 American Chemical Society. This publication is licensed under CC-BY-NC-ND.

  • Open Access

Article Views

3114

Altmetric

-

Citations

LEARN ABOUT THESE METRICS
PDF (6 MB)
Supporting Info (1)»

Abstract

We developed Europe-wide models of long-term exposure to eight elements (copper, iron, potassium, nickel, sulfur, silicon, vanadium, and zinc) in particulate matter with diameter <2.5 μm (PM2.5) using standardized measurements for one-year periods between October 2008 and April 2011 in 19 study areas across Europe, with supervised linear regression (SLR) and random forest (RF) algorithms. Potential predictor variables were obtained from satellites, chemical transport models, land-use, traffic, and industrial point source databases to represent different sources. Overall model performance across Europe was moderate to good for all elements with hold-out-validation R-squared ranging from 0.41 to 0.90. RF consistently outperformed SLR. Models explained within-area variation much less than the overall variation, with similar performance for RF and SLR. Maps proved a useful additional model evaluation tool. Models differed substantially between elements regarding major predictor variables, broadly reflecting known sources. Agreement between the two algorithm predictions was generally high at the overall European level and varied substantially at the national level. Applying the two models in epidemiological studies could lead to different associations with health. If both between- and within-area exposure variability are exploited, RF may be preferred. If only within-area variability is used, both methods should be interpreted equally.

1. Introduction

ARTICLE SECTIONS
Jump To

Exposure to particulate matter (PM) is associated with adverse health outcomes. (1,2) PM is a complex mixture of components that differ spatially and temporally. Identifying which components are main contributors to adverse health effects is important for targeted policymaking. Multiple studies have attempted to associate health effects with PM components including metals, organic compounds, inorganic carbonaceous material, and inorganic secondary aerosols. (3−5) Findings, however, are inconsistent. Epidemiological studies have been limited because of the scarcity of air quality monitors that routinely measure PM composition. In Europe, a PM monitoring campaign was conducted in 20 ESCAPE (European Study of Cohorts for Air Pollution Effects) study areas following a common sampling protocol. (6) Most study areas consisted of a metropolitan area with some small towns around the main city. The PM samples were analyzed for elemental composition. (7) Based on the measurements from 20 sites in each study area, area-specific land use regression (LUR) models were developed to assess long-term exposure to elemental composition. (8) The models were applied to cohorts within the study areas to assess health effects related to particle composition. (9)
The geographical extent of the study-area-specific ESCAPE models is limited and predictions from these models cannot reliably be used for other cohorts, such as large multicenter studies. The models were furthermore developed on 20 sites per area. Methodological studies suggested that more stable models can be developed based on larger number of sites in the model training dataset. (10,11) In addition, the ESCAPE study-area specific models had rather good performance for traffic-related elements such as copper (Cu) and iron (Fe), but had poor performance for elements such as sulfur (S), nickel (Ni), and vanadium (V) for which spatial variation was limited within areas and key predictors were missing. (8) The lack of large-scale European models for particle elemental composition hampers large-area epidemiological studies. Our previous studies showed the possibility to develop European LUR models with good performance using a combined dataset from the ESCAPE study areas for PM with diameter <2.5 μm (PM2.5), black carbon (BC) and nitrogen dioxide (NO2). (12,13)
The supervised linear regression (SLR) algorithm is often used in air pollution modeling, (14,15) and was used to develop ESCAPE models of elemental composition (8) and European models of PM2.5, NO2, and BC. (12) The SLR algorithm shows good predictive ability and interpretability but has strong statistical assumptions such as linearity. SLR models can, however, take into account nonlinear relationships by offering a priori transformed predictor variables (e.g., inverse distance to a source), include only predictor variables following plausible direction of effect (e.g., a positive traffic slope) and add interaction terms. A number of more flexible algorithms including machine-learning algorithms have increasingly been applied in air pollution exposure assessment. (16,17) Random forest (RF) has been widely used in recent years. (18,19) RF is a classification tree analysis. It can model potentially complex relationships including nonlinearity and interactions within data but gives little information regarding the prediction process. (20) A key feature of RF is the “bagging” procedure adopted in both observation and variable selection: this allows even marginally important predictors to contribute, even in the presence of high multicollinearity. A previous study found RF outperformed linear regression in modeling spatial variation of particle elemental composition. (21)
LUR models for multiple particle components are more useful for epidemiological studies if they include more specific predictors. Developments in satellite and chemical transport modeling and availability of industrial point source data have made it possible to develop more specific models.
The aim of this study was to assess the performance of Europe-wide models for particle elemental composition, developed using SLR and RF algorithms. The models have been developed in the “Effects of Low-Level Air Pollution: A Study in Europe” (ELAPSE), a Europe-wide project investigating long-term health effects of low-level air pollution.

2. Materials and Methods

ARTICLE SECTIONS
Jump To

2.1. Air Pollution Data

The PM2.5 elemental composition concentration data originated from the ESCAPE monitoring campaigns conducted in 19 study areas across Europe (Figure S1). PM sampling and analysis methods have been described previously. (6,7) Briefly, measurements were made at 20 sites in each study area (40 in the large Catalunya and Netherlands/Belgium areas) for three 2-week periods in a 1-year period between October 2008 and April 2011. Monitoring sites were selected to represent pollution levels at regional background, urban background, and street locations using a common sampling protocol. PM2.5 samples were collected on Teflon filters using Harvard Impactors and analyzed for elemental composition using energy-dispersive X-ray fluorescence. Annual average concentrations were calculated based on three 14-day average measurements spread over the seasons (warm, cold, and intermediate) with temporal adjustment from a reference background site in each study area. Our measurement campaign was restricted temporally, as previous sampling campaigns used to develop LUR models. (22) While this design does not formally estimate absolute annual average concentrations as in regulatory monitoring, it has been shown to be useful to assess spatial contrast of long-term average concentrations because of specific design elements. (6,22,23) We performed temporal adjustment, using a continuous reference site located at a regional or urban background location (not directly influenced by local sources), where measurements were made for the full 12-month period. Three 14-day average samples were taken in different seasons at all locations, which are less sensitive to the very short-term variations caused by daily variation in weather. Five sites and the reference site were measured simultaneously representing all different site types (regional background, urban background, and street). (6,23)
Eight elements were a priori selected within ESCAPE to represent major pollution sources: Cu, Fe, and Zn representing nontailpipe traffic emissions, S representing long-range transport, Ni and V representing mixed oil burning/industry, silicon (Si) representing crustal material, and potassium (K) representing biomass burning. (7,8)

2.2. Potential Predictor Variables

2.2.1. Traffic, Population, Altitude, and Land Use Variables

We used the same road density, population, and elevation variables as in our previous exposure modeling paper for PM2.5, NO2, ozone (O3), and BC across Europe. (12) In short, road data were extracted from the 1:10,000 EuroStreets digital road network (version 3.1 based on TeleAtlas MultiNet TM, year 2008), classified into “all” and “major” roads, and road density calculated in a 100 × 100 m grid. Population density in 1 × 1 km grid for 2011 were obtained from Eurostat. (24) Elevation was obtained from the SRTM Digital Elevation Database (25) version 4.1 with a resolution of 3 arc second (approximately 90 m) with vertical error of <16 m. X and/or Y coordinates were offered to represent the east–west/north–south gradient.
Land use variables were newly extracted from an updated European CORINE Land Cover surface in 100 × 100 m grid. (26) The initial 44 land cover classes were grouped to six main classes: residential, industry, ports, urban green space, total built up land, and natural land.

2.2.2. Additional Component/Source-Specific Variables

Special attention was taken in obtaining specific potential predictor variables representing different sources of the eight selected elements. We hypothesized that this would allow us to develop better and more specific models, such that the independent associations of the different elements with health could be studied better. For each component, only plausible variables were offered for model development. The restrictions of offering specific potential predictors are specified in Table S1.
Satellite-model (SAT) estimates of 2010 annual average sulfate (SO42–), organic matter (OM), BC, and mineral dust (SOIL) in PM2.5 were extracted from a gridded surface (0.01° × 0.01°, ∼1.11 km) over Europe. These estimates are an application of simulated relative composition to the total PM2.5 estimates produced by the methods described elsewhere, (27) and do not incorporate compositional ground-based measurements over Europe. In brief, PM2.5 mass estimates were produced by relating a combined aerosol optical depth (AOD) retrieval involving multiple satellite products and simulation to near-surface PM2.5 concentrations using the spatiotemporally varying geophysical relationship simulated by the GEOS-Chem chemical transport model (CTM). Ground-based observations of total PM2.5 were then incorporated into these initial values using geographically weighted regression, and the resulting total mass estimates partitioned into chemical composition using their relative contributions according to the GEOS-Chem CTM simulations.
CTM estimates of BC AOD, Sulphate AOD, total column SO2, and sea-salt AOD were obtained from the European Centre for Medium-Range Weather Forecasts. (28) Daily estimates in 2010 were extracted from a gridded surface (0.125° × 0.125°, ∼13.9 km) produced by the MACC-II ENSEMBLE model, (29) and then aggregated to derive the annual average.
In addition to the unspecific industry land-use category, information on major industrial point sources was obtained including facility location, pollutant, and emission amount from the European Pollutant Release and Transfer Register. (30) The industrial facility points were intersected with a 100 m base polygon, and then the number of facility sites and emissions were summed within each 100 × 100 m cell. Density of general industries and industries emitting specific aerosols (metal, Cu, Ni, PM10, SOx, and Zn) were calculated accordingly. Sum of emissions were calculated for PM10, Cu, Ni, SOx, and Zn.
All predictor variables were integrated into a 100 m gridded GIS database covering Europe. For the road density, land use and industrial information, a moving window procedure was used to calculate the sum of values for selected buffers (focal statistics using sum within a circle). The influence of industrial point sources was calculated by inverse distance weighting (1/d). The processing of variable surfaces was done in ArcMap 10.6.

2.3. Model Development

The number of monitoring sites available for particle composition ranged from 400 to 414 because of failed PM composition measurements. (8) We used both SLR and RF algorithms to develop models.
The SLR approach has been described in detail before. (12) Briefly, a univariate linear regression model was applied for each potential predictor to find the predictor that explained the maximum variance in the measurements. At each subsequent step, the significant predictor variable (P < 0.1) that generated the highest increase in the model adjusted coefficient of determination (adjusted R2) was added. Predictors only entered the model if they adhered to the plausible direction of the effect (Table S1). This process was repeated until the model adjusted R2 could not be increased anymore. Predictor variables with variance inflation factor larger than 3 were removed from the model to avoid multicollinearity.
RF is an ensemble machine learning technique based on decision trees. (31) It builds independent trees in parallel, each based on a random sample drawn from the full set of measurements. At each node, a random subset of potential predictors is split. The final predictions are derived by averaging predictions from all decision trees. RF does not perform variable selection. It produces variable importance, calculated as percentage increase in mean squared errors after a random permutation of the values of a variable. We used the R package “randomForest” to develop the RF models.
One-step and two-step modeling processes were used to offer geographical coordinates (X and Y) to the models. Following our previous exposure modeling procedure, (12) for SLR we used a 2-step approach, in which we first developed a SLR model without offering X or Y, then added X and Y only if they increased the model adjusted R2. The rationale for the 2-step procedure is that we preferred spatial variation to be explained first by specific predictor variables and the residual variation to be further explained by the X, Y coordinates added in the second step. In RF, we applied one-step modeling as our primary approach: X and Y were offered together with the other predictor variables. This allowed us to take advantage of the possibilities of RF algorithm to model the potential interactions between coordinates and other predictors. For comparison, we also developed one-step models for SLR and 2-step models for RF: we first developed a RF model without offering X or Y, then developed a second RF model with X, Y coordinates only, explaining variations in the residuals of the step1 RF model. The predictions of these two RF models were later added together. We further performed a sensitivity analysis offering a few nonlinear transformations of the X- and Y-coordinates to the SLR model, including X2, Y2, √X, √Y, and XY, to allow more flexible functions of the coordinates than the linear function. We were not able to perform kriging because of the clustered nature of the monitoring data. (12)

2.4. Model Evaluation and Comparison

For each model, we calculated model r2 (squared Pearson correlation) and root-mean-square error (RMSE) by comparing main model predictions to the measurements.
We performed five-fold hold-out validation (HOV). The full set of measurements were randomly divided into five groups (20% each), stratified by site type (street, rural, and urban background) and region (north, west, central, and south). For each element-model combination, five additional HOV models were built, each based on 80% of the monitoring sites, with the remaining 20% for validation. HOV regression-based r2 and RMSE were computed by comparing the stacked predictions at the five HOV test sets to the corresponding measurements. We also calculated mean square error-based R2 (MSE-R2), defined as
where is the average of the measurements. MSE-R2 can be seen as a rescaling of MSE. It measures fit about the 1:1 line rather than fit about the best fit line in regression-based r2. The HOV r2 and RMSE are relevant for multicity studies that exploit both within and between city variability of air pollution contrasts.
To test how the European models predict within-area variability, we calculated within-area r2 and RMSE by comparing the stacked HOV predictions and measurements within each individual study area. Because the monitors are spatially clustered over Europe and nearby locations might have auto-correlations in their measurements, we additionally performed leave-one-area-out cross-validation (LOAOCV). (32,33) We developed Europe-wide models by excluding all observations from one study area at a time and applied the models to the sites that were left out. Therefore, 19 additional models were developed for each pollutant-algorithm combination. Within-area r2 and RMSE were computed by comparing the predictions and measurements in the area that was excluded from model development. We focus interpretation on the average of the within-area r2s and RMSEs because the performance statistics of the individual study areas may be affected strongly by random error because they were based on only 20 sites in each study area.
For each main model, predictor variables selected in SLR models and the 15 most important variables in RF models were compared.
Each main model was mapped at a 100 × 100 m resolution across the whole study area, allowing for visual comparison between maps. Additionally, we compared predictions from models at 41,936 random locations across Europe used previously. (12) Comparisons of model predictions were made for the entire study area and at the national scale reporting the Pearson correlation coefficient (r) and RMSE. Truncations were performed to deal with unrealistic predictions of the SLR approach: predictions at the high end were truncated to the maximum final two-step modeled value, calculated by fitting the model with the maximum predictor values at monitoring sites for positive slopes (or the minimum predictor values for negative slopes); the negative predictions were set to zeros.

3. Results and Discussion

ARTICLE SECTIONS
Jump To

3.1. Distribution of PM2.5 Component Measurements

Boxplots of the annual mean concentration for PM2.5 components in the full dataset and in individual study areas are shown in Figure S2. For the majority of pollutants, pollution concentrations varied substantially within and between study areas. A positive north–south gradient was observed with higher pollution levels in southern study areas. A more detailed interpretation of the measured concentrations can be found elsewhere. (7)

3.2. Model Performance

Performance of models across Europe is shown in Table 1. Models for most components had moderate to good performance based upon HOV. Model performance was almost the same evaluating by regression-based r2 or MSE-based R2 (Table S2), consistent with the observation that the fitted regression slopes between observed versus predicted values are close to the 1–1 line (Figure S3). Models with the highest HOV r2s were developed for PM2.5 S, having large between-area concentration variability for which large-scale predictor variables from CTM were available to explain the contrast. Sulfate (represented by S) is a secondary pollutant formed by the oxidation of sulfur dioxide for which the ratio of between- and within-area variability is larger than for the other elements. (7) RF models consistently outperformed SLR models for all elements. This agrees with a previous study, which found more accurate exposure assessed for elemental components by RF than SLR, based on 24 monitoring sites. (21) The better performance of RF is different from two previous comparisons, (16,17) where similar performance of spatial models was observed for SLR and RF. One study compared Europe-wide models for PM2.5 and NO2 developed using similar predictor variables as in the current study, (16) the second study compared LUR models for ultrafine particles based upon mobile monitoring. (17) One possible explanation for the difference in findings is that there might be more complex relationships between predictors and elemental composition than with the mass of PM2.5, NO2, and UFP. RF can capture unknown nonlinear relationships and interactions not predefined in SLR, without introducing overfitting of the data. Another important difference is that in the current study, the data were clustered within Europe, whereas in the earlier study on PM2.5 and NO2, models were developed based upon routine monitoring, with a more even distribution of sites across Europe. We hypothesize that the RF model accounted for spatial trends across Europe better than the linear model.
Table 1. Performance of PM2.5 Composition Models over Europea
  componentCuFeKNiSSiVZn
 inclusion of XY coordinatesno. of sites414413414402404400402413
Model Building
SLRone-stepmodel r20.560.550.610.620.790.520.700.48
  model RMSEb3.365.564.60.9146.559.71.711.8
 two-step, step1model r20.520.530.520.560.800.480.660.47
  model RMSE3.467.471.11.0142.261.91.811.9
 two-step, step2model r20.560.530.600.600.820.500.690.48
  model RMSE3.367.465.00.9135.461.11.711.8
RFcone-stepmodel r20.950.950.970.950.980.950.970.95
  model RMSE1.120.816.80.340.219.90.53.5
 two-step, step1model r20.950.950.970.950.980.940.970.96
  model RMSE1.120.917.40.341.820.30.53.4
 two-step, step2model r20.980.980.990.980.990.980.990.99
  model RMSE0.612.49.50.227.012.20.31.8
HOV
SLRone-stepHOV r20.470.480.580.570.760.500.630.41
  HOV RMSE3.670.566.41.0156.460.81.812.5
 two-step, step1HOV r20.440.460.500.510.760.460.600.42
  HOV RMSE3.771.772.61.0154.963.41.912.4
 two-step, step2HOV r20.480.480.590.560.790.460.630.41
  HOV RMSE3.670.566.11.0147.062.91.812.5
RFone-stepHOV r20.600.600.820.740.910.620.850.68
  HOV RMSE3.261.744.10.797.052.91.29.3
 two-step, step1HOV r20.590.590.790.740.900.600.840.68
  HOV RMSE3.262.447.40.7102.154.21.29.2
 two-step, step2HOV r20.590.610.800.760.900.620.860.71
  HOV RMSE3.261.345.80.799.553.11.18.7
a

SLR = supervised linear regression; RF = random forest; r2 = squared Pearson correlation; RMSE = root-mean-square error; HOV = fivefold hold-out validation.

b

Unit of RMSE: ng/m3.

c

Performance of RF on training set cannot be interpreted.

For most components, HOV r2s were similar for the one-step model and the final two-step model and higher than for the first step of the two-step model, documenting that spatial trends account for the residual variance not explained by the available predictors. Offering a priori transformed X- and Y-coordinates did not further improve performance for SLR models. The differences between model r2 and HOV r2 in SLR models were small, suggesting the models do not overfit. The perfect performance on training set (model r2) for RF models is “by design” and basically meaningless. This is because the RF algorithm generally does not prune the individual trees, relying instead on the ensemble of trees to control overfitting. (20)
While the models performed well to explain overall variability across Europe, models performed less well in explaining variation within individual study areas (Table 2). Results are similar by performing fivefold HOV and LOAOCV, suggesting the model performance is stable regardless of CV methods. The better overall performance is explained by a combination of larger variability of concentrations between areas than within areas and the better availability of predictor variables for describing between- compared to within-area variability. Specifically, the addition of large-scale satellite and CTMs has contributed to assess the study-area background. The average within-area r2s were moderate for Cu and Fe and relatively poor for other components. Cu and Fe represent mechanically generated traffic-related particles and thus their particle size distribution within PM2.5 is skewed toward coarse particles. (7,34) Therefore, Cu and Fe do not travel far and may show large within-area variation. The better within-area performance for Cu and Fe is thus possibly because of the combination of higher within-area variation of the concentrations in most areas and the availability of data on traffic networks within individual areas. Within-area r2s were poor for components that have limited within-area variation such as S. S represents secondary inorganic aerosols (sulfates) produced by atmospheric chemistry of precursor gases (sulfur oxides) originating from combustion of sulfur-containing fossil fuels (e.g., in power plants). (35) Much of transported sulfate are in the submicron range and travel far, resulting in fairly uniform spatial variation in the scale of cities. Ni and V are often emitted from coal, oil, or residual oil burning in buildings and ships. The emission height of buildings and ships are relatively low so that within-city variation can be observed. Despite the consistently better performance of RF models than SLR models in overall HOV, the average within-area r2s were similar across models for each element. This further supports our hypothesis that the RF model accounted for spatial trends across Europe better than the SLR model. Within-area r2s varied substantially across study areas and were low in areas with small contrasts in measured concentrations shown by low RMSE (Figure S4).
Table 2. Performance of PM2.5 Composition Models to Assess within-Area Variation: Average within-Area r2a
avg. WA r2inclusion of XY coordinatesevaluation methodCuFeKNiSSiVZn
SLRone-stepfive-fold HOV0.340.350.090.180.140.180.210.20
  LOAOCV0.370.380.090.150.220.210.230.18
 two-step, step1five-fold HOV0.340.340.080.170.140.200.180.21
  LOAOCV0.350.350.090.150.220.200.200.18
 two-step, step2five-fold HOV0.350.360.070.170.140.200.190.19
  LOAOCV0.360.360.090.150.220.200.210.18
RFone-stepfive-fold HOV0.310.310.050.210.210.190.270.24
  LOAOCV0.350.350.120.180.210.170.270.18
 two-step, step1five-fold HOV0.310.300.060.210.220.170.270.24
  LOAOCV0.340.340.070.160.210.160.230.19
 two-step, step2five-fold HOV0.290.290.070.210.230.170.290.25
  LOAOCV0.340.340.070.160.210.160.230.20
a

SLR = supervised linear regression; RF = random forest; r2 = squared Pearson correlation; avg. WA r2 is the average of 19 study area-specific r2s (area-specific r2s evaluated by five-fold HOV are shown in Figure S4); HOV = hold-out validation; LOAOCV = leave-one-area-out cross-validation.

In summary, the generally moderate within-area performance of the developed models is likely related to a combination of limited availability of predictor variables, for example, targeting especially nonexhaust traffic emissions, the clustered nature of the monitoring data and the lack of exposure contrasts within specific areas. Especially predictor variables at the local scale are insufficient.

3.3. Model Structure

Predictor variables selected in SLR models and the 15 most important variables in RF models are shown in Figure 1. For each element, some consistency was found between SLR models and RF models in terms of the variable categories that were included. To some extent, however, different buffer sizes were included. Variables within each algorithm were very similar. X, Y coordinates usually contributed to the models when offered and were considered relatively important variables in the one-step RF.

Figure 1

Figure 1. Regression slopes (shown in red) of predictors selected in SLR and relative variable importance (shown in blue) of the 15 most important predictors in RF.

The major predictors in the models differed substantially between the eight elements, broadly reflecting the different sources.
In Cu and Fe models, traffic-related predictor variables dominated the other source categories in SLR models while they were also considered relatively important in RF models. This is consistent with previous LUR models of Cu and Fe where a large proportion of the variability in the measured concentrations was explained by traffic-related variables. (8,36,37) Some of the industrial point sources were picked up in the SLR models for Cu and Fe, possibly reflecting emission released by metallurgic industries. (35) A previous study suggested that industrial sources were major predictors for Cu and Fe models in PM with diameter <1 μm (PM1). (38)
In Zn models, predictors representing industrial Zn emission and combustion sources contributed a large proportion to the overall r2. This is consistent with LUR models in other studies. (36−38) In ESCAPE modeling, specific industrial predictors were not available. (8) The large contribution of industrial point sources to the Zn models is consistent with results of source apportionment analyses in MESA (Multi-Ethnic Study of Atherosclerosis) showing that Zn-rich features were indicative of incinerators at nearby fixed locations. (34) Previous studies have used Zn as a tracer for metallurgic industries and nonmetallurgic industries for frit production. (35)
In Ni and V models, ports were important predictors, as a proxy for shipping emissions. Density of Ni-emitting industries and more general industrial density predictors were included in the SLR model for Ni and V, consistent with the identification that Ni and V shared the same mixed industrial/fuel-oil combustion source. (39) Large-scale SAT dust showed a large contribution in the Ni and V models, which possibly accounts for the observed north–south trend in the absence of a specific large-scale Ni and V CTM or satellite predictors. We offered SAT dust to all elements as windblown dust can be a source for all components.
In S models, variation in the measured concentrations was predominantly explained by large-scale satellite and CTM estimates and predictors in large buffers. Sulfate from the CTM and SAT dust were virtually equally important in the models. SAT sulfate did not enter the model possibly because sulfate from the CTM was in the model and they are highly correlated. SAT dust likely accounts for the observed north–south trend in concentration. In area-specific ESCAPE models, less well performing models were developed for S mainly because of the small within-study area variability. (8) Predictors representing industrial point sources also contributed to the S models, indicative of the transformation of emissions from combustion. (34)
In K models, SAT estimates for OM explained a large proportion of the variation, indicative of the main source of biomass burning for fine particle K. (35) Small-scale variables contributed little to K models, resulting in limited ability in explaining within-area variability. In our current models, we are still missing fine spatial scale biomass burning source terms because of the lack of reliable predictor variables.
Si models were dominated by SAT dust estimates and the population density, reflecting its crustal dust source. (35) Road length and industry areas from CORINE land cover also contributed to the models. These variables contributed a large fraction also in models for Si in PM1. (38) In a previous study in New York, Si was strongly associated with an indicator for areas of industrial structures. This indicator includes a wide range of industrial, manufacturing, and commercial activities, thus it is difficult to identify the main source. (36)
Values between two algorithms are not quantitatively comparable. Regression slopes in SLR were multiplied by the range of each predictor to allow comparison across predictors. Relative variable importance in RF was calculated as percentage increase in mean squared errors after a random permutation of the values of a variable. SO4 = satellite sulfate, OM = satellite organic matter, SOIL = satellite dust; BC = satellite black carbon; BCAOD = CTM black carbon, SUAOD = CTM sulphate, TCSO2 = CTM SO2, POP = population, ALT = altitude, MJRD = major roads, ALRD = all roads, TBU = total build up, NAT = natural land, IND = industry, POR = ports, UGR = urban green, RES = residential, Cu_emi = Cu emission amount, PM10_emi = PM10 emission amount, SOx_emi = SOx emission amount, Zn_emi = Zn emission amount, industry = number of total industrial sites, Ni = number of industrial sites emitting Ni, X_coord = east–west gradient, and Y_coord = north–south gradient. Number in subscript depicts the buffer size SLR1 = one-step SLR; SLR2.1 = two-step SLR, step one; SLR2.2 = two-step SLR, step two; RF1 = one-step RF; RF2.1 = two-step RF, step one.

3.4. Maps and Prediction at Random Locations

The truncation frequency for prediction at random locations is shown in Table S3. A large number of negative SLR predictions were truncated to zero for some elements—for example, 41.3% of the 41,936 random locations across Europe for Cu in the final two-step SLR model predictions. Most of the negative values were located in the low population density areas of Northern Europe, covered mostly by natural land. When we applied the final two-step SLR models to a large Europe-wide pooled dataset of ESCAPE cohorts with 393,064 subjects (including a Swedish and Danish cohort), truncation frequencies were much smaller: 10.5% for PM2.5 Cu, 0.5% for PM2.5 Fe, 11.3% for PM2.5 Ni, 14.2% for PM2.5 V, and 2.7% for PM2.5 Zn. Therefore, we do not expect this to be a big issue when applying the SLR models to participants in epidemiological studies. No truncation was needed for RF models.
Although we a priori considered one-step RF models as our main RF models, we observed large concentration jumps along horizontal or vertical lines in several maps (Figure S5). This counterintuitive pattern possibly reflects the role of the X, Y coordinates in RF modeling and relative importance attributed to these variables. Using X and Y in RF introduces strong boundary effects because, depending on the value where trees are split, large difference in predictions will be produced below and above that value. The concentration jumps were also observed in the final two-step RF model maps with X, Y coordinates. The RF models without offering X, Y coordinates produced clearly different maps while the HOV r2s were marginally lower than for the RF models with coordinates (Table 1). We, therefore, prefer the first step in the two-step RF and the final two-step SLR (maps in Figure 2), and show maps deriving from the other procedures in the appendix (Figure S5). The maps showing strong boundary effects might require smoothing before application in epidemiological studies. Our results clearly indicate the value in evaluating plausibility of maps as an important last step in air pollution exposure assessment studies. Comparing models solely by HOV statistics is not sufficient. We did not observe sharp gradients in the SLR model maps.

Figure 2

Figure 2. Maps of PM2.5 components developed by our main SLR (two-step, step2) and RF (two-step, step1) models.

There are clear agreements between maps produced by our main SLR and RF for some elements and differences for other elements (Figure 2). In both maps for Cu, high levels of pollution are shown in big cities, and transport networks can be clearly seen in the inset map of the area around Paris. Maps for PM2.5 S are broadly similar with higher pollution levels in the south and east, while quite different patterns were observed for East Germany and Spain. Both maps for Zn show high concentrations close to industrial sites. The same industrial sites were picked up in the area around Paris shown in the inset. Comparing the predictions at a total of 41,936 random locations, agreement was high at all European countries-level and the ELAPSE countries combined-level for PM2.5 Cu, PM2.5 K, PM2.5 S, PM2.5 Zn (r > 0.7), and moderately high for other elements (Table 3). Correlation between all model predictions at the ELAPSE countries combined-level is presented in Figure S6. For most components, correlations were high for predictions derived from the same algorithm, and lower for predictions derived from different algorithms.
Table 3. Correlations between Predictions by Our Main SLR (Two-Step, step2) and RF (Two-Step, step1) Models at 41,936 Random Locationsa
 PM2.5 CuPM2.5 FePM2.5 KPM2.5 NiPM2.5 SPM2.5 SiPM2.5 VPM2.5 Zn 
regionrRMSEbrRMSErRMSErRMSErRMSErRMSErRMSErRMSEN
all European countries0.721.10.6620.50.7551.30.560.50.88162.60.5622.80.641.00.737.141,936
ELAPSE Countries
combined0.791.00.7719.10.7056.10.530.50.89142.00.7512.50.660.80.737.027,411
Austria0.771.10.8016.20.8035.00.280.10.9569.50.089.50.820.20.894.41051
Belgium0.820.90.8911.90.0521.00.830.40.7947.40.718.20.760.80.7011.4355
Switzerland0.801.10.8913.10.7624.10.360.10.4895.00.389.20.490.20.655.8500
Germany0.741.00.8014.90.4330.60.660.30.6760.10.598.20.800.40.586.94233
Denmark0.770.30.779.30.6815.00.210.20.7336.00.457.20.240.30.492.0522
France0.621.10.7514.20.3126.90.390.40.7269.00.489.00.770.60.596.86476
Italy0.721.30.5323.20.6933.60.510.60.83183.00.7019.50.631.30.679.03550
Netherlands0.740.90.8314.20.5517.20.640.40.6045.00.688.90.480.70.6614.2451
Norway0.370.00.615.6–0.68c8.60.430.20.25104.90.034.30.800.30.464.02649
Sweden0.560.20.775.8–0.68c22.60.680.10.8886.70.314.90.730.40.383.64786
United Kingdom0.850.60.8712.0–0.74c25.90.590.30.8672.10.129.60.570.50.684.12838
Non-ELAPSE Countries
Greece0.551.00.5716.80.3828.70.440.80.18123.50.3425.60.461.90.547.01541
Finland0.250.30.587.40.4928.70.480.10.8567.30.284.90.330.30.554.23208
Hungary0.680.90.6111.70.7429.00.340.20.6087.40.578.20.670.30.795.01123
Ireland0.520.30.655.8–0.70c16.90.460.20.4548.5–0.084.80.410.40.261.8844
Lithuania0.630.80.687.00.6525.30.260.10.1652.50.594.70.290.20.891.8783
Luxembourg0.760.80.838.4–0.0816.20.820.10.8226.50.774.90.800.20.832.133
Portugal0.411.60.0121.0–0.0323.50.710.40.7272.90.227.30.800.70.606.61021
Spain0.591.20.3417.20.0632.70.410.60.59102.00.4910.70.591.10.568.05972
a

r = Pearson correlation coefficient; RMSE = root-mean-square error.

b

Unit of RMSE: ng/m3.

c

We do not have clear explanations of these high negative correlations. These values possibly reflect the poor performance of both models at low concentrations. Scatter plots documented the poor agreement between predictions by the two models with lots of scatters.

While correlations between predictions derived from SLR and RF were moderate to high at the European level, they are lower than the very high correlations (r generally >0.9) reported previously for Europe-wide models of PM2.5 and NO2. (16) Agreement between predictions from the two algorithms at the national level varied substantially across countries (Table 3). There was no consistently good agreement between predictions for a specific country. Poor agreement between predictions were observed for area-component combinations that had small contrasts in measured concentrations shown by low RMSE (e.g., most components in Norway and Sweden).
Computation time for mapping differed substantially for RF and SLR—around 40 h for RF and less than 1 h for SLR to map pollution concentrations across Europe on a standard office computer.

3.5. Strengths and Limitations

With the development of Europe-wide models, we are able to assess long-term exposures to PM2.5 components in a large European project, which consists of several nation-wide cohorts and smaller cohorts in which participants were recruited in specific study areas. The use of a single harmonized model allows a standardized exposure assessment in international multicenter studies.
Our Europe-wide models had the advantage of a large training dataset with large contrasts in measured concentrations by combining measurements from individual ESCAPE study areas. In contrast, the previous ESCAPE area-specific models could not be developed for some composition-area combinations because of missing data (e.g., in Lugano), small within-area variability (e.g., S) and poor precision of the measurements in areas with low concentrations (Ni and V). (8) The moderate to good performance of our models across Europe suggests that the models would perform well in multicenter studies that exploit both within and between area variability of air pollution contrasts.
Another strength of our study is that we made efforts in collecting specific large-scale predictors, from satellites and CTMs, representing different pollution sources such as soil, industrial sources, and biomass burning, which could not be applied in prior area-specific models. The availability of these predictors increased the specificity of our models, which is useful to study associated health effects of specific single components.
While inclusion of industrial point source data was an improvement over the simple land use categories available in CORINE land cover, a dispersion model for point sources would have been the method of choice. We did not have the possibility to use Europe-wide small-scale dispersion modeling, and we did not have information on chimney height and wind direction around chimneys. We therefore used inverse distance weighting to create variables from industrial point sources, which can lead to overestimation of pollution levels in areas very close to the industrial sites. (40) The misclassification is expected to be minimal given that it is unlikely that many people live very close to the large point source chimneys included in the European Pollutant Release and Transfer Register databases. The small truncation frequency (<0.1%) above the maximum values in a total of around 42,000 random locations across Europe suggested the overestimation might not have a large impact.
The prediction ability of our Europe-wide model at small-scale, however, is limited, especially in areas without main sources present. The lack of specificity of the small-scale land use predictors might have contributed to the poor predictive ability for some elements. The poor within-area predictive ability suggests our Europe-wide models should be applied with caution in small-scale individual study areas, with the possible exception of the Cu and Fe models. Our model is more suited for multicenter studies.
Moderate to high overall correlations between our Europe-wide SLR and previous area-specific ESCAPE model predictions at monitoring sites were observed except for K and Zn (Table S4). The within-area correlations between SLR and ESCAPE varied considerably and the average correlations were high for Cu and Fe. The results suggested applying the newly developed Europe-wide models in epidemiological studies could lead to different findings from the ESCAPE study. The leave-one-out-cross-validation (LOOCV) r2s of the area-specific ESCAPE models are not quantitatively comparable with the within-area fivefold cross-validation r2s in this study as the LOOCV is based on a small number of sites and tends to overestimate predictive ability. (10,11)
Given the discrepancies in predictions derived from the two methods, applying the two sets of models in epidemiological studies could lead to different associations with health. SLR and RF model performances were similar for the within-area concentration variability, while RF model explained overall concentration variability (including between-area variability) better than SLR. In SLR, we did not add fixed or random intercepts for study area as such models could not be applied outside the specific study areas. In a previous study on PM2.5 and NO2, (33) we found that adding indicators for study area or the measured regional background in each study area, improved the overall explained variability. Therefore, when applied in epidemiological studies, it depends on the contrast exploited in the epidemiological study which method is the preferred method. If both between- and within-area variability are exploited, RF would be the method of choice based on the cross-validation statistics. If an epidemiological study only includes within-area exposure contrast, then both methods should be interpreted equally, without a prior preference for one of the methods. Given the moderate performance of both models, it would be important to observe robustness of the findings in epidemiological studies. If health effects are found with only one model, this should be interpreted cautiously.
Because of the lack of external validation data, we cannot draw strong conclusions about the preferred method. We note that RF models might be more difficult to interpret in terms of how predictor variables act in the models, although the “importance” statistics provide useful information on the relative importance of individual predictors. The classification nature of RF led to visible boundary effects in some exposure maps, which might require smoothing before application in epidemiological studies. On the other hand, SLR might fail to capture some complex nonlinear relationships and/or interactions between predictors and pollutants, or might induce overfitting if multiple nonlinear and interaction terms were added to the model. Despite the discrepancies in predictions, we believe our models are stable and the results are robust, as different cross-validation methods and several sensitivity analyses showed moderate to good performance, especially at the overall Europe-wide scale and similar results.

Supporting Information

ARTICLE SECTIONS
Jump To

The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acs.est.0c06595.

  • Overview of potential predictor variables; performance of PM2.5 composition models over Europe; truncation frequency for model predictions at random locations; correlation of predictions at monitoring sites; distribution of 416 ESCAPE monitoring sites; boxplots of annual mean concentrations for PM2.5 composition; scatter plots of the stacked predictions at five held-out sites versus measurements; within-area r2s and RMSEs of PM2.5 composition models; maps of PM2.5 components; and Pearson correlation between model predictions at random locations across ELAPSE countries (PDF)

Terms & Conditions

Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

Author Information

ARTICLE SECTIONS
Jump To

  • Corresponding Author
  • Authors
    • Kees de Hoogh - Swiss Tropical and Public Health Institute, Socinstrasse 57, 4051 Basel, SwitzerlandUniversity of Basel, Petersplatz 1, Postfach 4001 Basel, SwitzerlandOrcidhttp://orcid.org/0000-0001-5974-2007
    • John Gulliver - Centre for Environmental Health and Sustainability, School of Geography, Geology and the Environment, University of Leicester, University Road, LE1 7RH Leicester, U.K.Orcidhttp://orcid.org/0000-0003-3423-2013
    • Barbara Hoffmann - Institute for Occupational, Social and Environmental Medicine, Centre for Health and Society, Medical Faculty, Heinrich Heine University Düsseldorf, Universitätsstraße 1, 40225 Düsseldorf, Germany
    • Ole Hertel - Department of Environmental Science, Aarhus University, P.O. Box 358, Frederiksborgvej 399, 4000 Roskilde, Denmark
    • Matthias Ketzel - Department of Environmental Science, Aarhus University, P.O. Box 358, Frederiksborgvej 399, 4000 Roskilde, DenmarkGlobal Centre for Clean Air Research (GCARE), Department of Civil and Environmental Engineering, University of Surrey, GU2 7XH Guildford, U.K.
    • Gudrun Weinmayr - Institute of Epidemiology and Medical Biometry, Ulm University, Helmholtzstr. 22, 89081 Ulm, Germany
    • Mariska Bauwelinck - Interface Demography—Department of Sociology, Vrije Universiteit Brussel, Pleinlaan 2, 1050 Brussels, Belgium
    • Aaron van Donkelaar - Department of Physics and Atmospheric Science, Dalhousie University, B3H 4R2 Halifax, Nova Scotia, CanadaDepartment of Energy, Environmental & Chemical Engineering, Washington University in St. Louis, 63130 St. Louis, Missouri, United States
    • Ulla A. Hvidtfeldt - Danish Cancer Society Research Center, Strandboulevarden 49, 2100 Copenhagen, Denmark
    • Richard Atkinson - St George’s University of London, SW17 0RE London, U.K.
    • Nicole A. H. Janssen - National Institute for Public Health and the Environment (RIVM), P.O. Box 1, 3720 BA Bilthoven, The Netherlands
    • Randall V. Martin - Danish Cancer Society Research Center, Strandboulevarden 49, 2100 Copenhagen, DenmarkDepartment of Physics and Atmospheric Science, Dalhousie University, B3H 4R2 Halifax, Nova Scotia, CanadaAtomic and Molecular Physics Division, Harvard-Smithsonian Center for Astrophysics, Cambridge, 60 Garden Street, 02138 Cambridge, Massachusetts, United States
    • Evangelia Samoli - Department of Hygiene, Epidemiology and Medical Statistics, Medical School, National and Kapodistrian University of Athens, 75 Mikras Asias Str, 115 27 Athens, Greece
    • Zorana J. Andersen - University of Copenhagen, 1165 Copenhagen, Denmark
    • Bente M. Oftedal - Department of Environmental Health, Norwegian Institute of Public Health, P.O. Box 4404 Nydalen, N-0403 Oslo, Norway
    • Massimo Stafoggia - Department of Epidemiology, Lazio Region Health Service/ASL Roma 1, Via Cristoforo Colombo, 112, 00147 Rome, ItalyInstitute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden
    • Tom Bellander - Institute of Environmental Medicine, Karolinska Institutet, SE-171 77 Stockholm, Sweden
    • Maciej Strak - Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The NetherlandsAtomic and Molecular Physics Division, Harvard-Smithsonian Center for Astrophysics, Cambridge, 60 Garden Street, 02138 Cambridge, Massachusetts, United States
    • Kathrin Wolf - Helmholtz Zentrum München, German Research Center for Environmental Health (GmbH), Institute of Epidemiology, Ingolstädter Landstr. 1, D-85764 Neuherberg, GermanyOrcidhttp://orcid.org/0000-0002-4343-201X
    • Danielle Vienneau - Swiss Tropical and Public Health Institute, Socinstrasse 57, 4051 Basel, SwitzerlandUniversity of Basel, Petersplatz 1, Postfach 4001 Basel, Switzerland
    • Bert Brunekreef - Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The NetherlandsJulius Center for Health Sciences and Primary Care, University Medical Center Utrecht, Heidelberglaan 100, 3584 CX Utrecht, Netherlands
    • Gerard Hoek - Institute for Risk Assessment Sciences (IRAS), Utrecht University, Postbus 80125, 3508 TC Utrecht, The Netherlands
  • Notes
    The authors declare no competing financial interest.

Acknowledgments

ARTICLE SECTIONS
Jump To

The research described in this article was conducted under contract to the Health Effects Institute (HEI), an organization jointly funded by the United States Environmental Protection Agency (EPA) (Assistance award no. R-82811201) and certain motor vehicle and engine manufacturers. The contents of this article do not necessarily reflect the views of the HEI, or its sponsors, nor do they necessarily reflect the views and policies of the EPA or motor vehicle and engine manufacturers. This work was also supported by a scholarship under the State Scholarship Fund by the China Scholarship Council (file no. 201606010329).

References

ARTICLE SECTIONS
Jump To

This article references 40 other publications.

  1. 1
    Adar, S. D.; Filigrana, P. A.; Clements, N.; Peel, J. L. Ambient coarse particulate matter and human health: a systematic review and meta-analysis. Curr. Environ. Health Rep. 2014, 1, 258274,  DOI: 10.1007/s40572-014-0022-z
  2. 2
    Vodonos, A.; Awad, Y. A.; Schwartz, J. The concentration-response between long-term PM2.5 exposure and mortality; A meta-regression approach. Environ. Res. 2018, 166, 677689,  DOI: 10.1016/j.envres.2018.06.021
  3. 3
    Adams, K.; Greenbaum, D. S.; Shaikh, R.; van Erp, A. M.; Russell, A. G. Particulate matter components, sources, and health: Systematic approaches to testing effects. J. Air Waste Manage. Assoc. 2015, 65, 544558,  DOI: 10.1080/10962247.2014.1001884
  4. 4
    Badaloni, C.; Cesaroni, G.; Cerza, F.; Davoli, M.; Brunekreef, B.; Forastiere, F. Effects of long-term exposure to particulate matter and metal components on mortality in the Rome longitudinal study. Environ. Int. 2017, 109, 146154,  DOI: 10.1016/j.envint.2017.09.005
  5. 5
    Pennington, A. F.; Strickland, M. J.; Gass, K.; Klein, M.; Sarnat, S. E.; Tolbert, P. E.; Balachandran, S.; Chang, H. H.; Russell, A. G.; Mulholland, J. A.; Darrow, L. A. Source-Apportioned PM2.5 and Cardiorespiratory Emergency Department Visits: Accounting for Source Contribution Uncertainty. Epidemiology 2019, 30, 789798,  DOI: 10.1097/ede.0000000000001089
  6. 6
    Eeftens, M.; Tsai, M.-Y.; Ampe, C.; Anwander, B.; Beelen, R.; Bellander, T.; Cesaroni, G.; Cirach, M.; Cyrys, J.; de Hoogh, K.; De Nazelle, A.; de Vocht, F.; Declercq, C.; Dėdelė, A.; Eriksen, K.; Galassi, C.; Gražulevičienė, R.; Grivas, G.; Heinrich, J.; Hoffmann, B.; Iakovides, M.; Ineichen, A.; Katsouyanni, K.; Korek, M.; Krämer, U.; Kuhlbusch, T.; Lanki, T.; Madsen, C.; Meliefste, K.; Mölter, A.; Mosler, G.; Nieuwenhuijsen, M.; Oldenwening, M.; Pennanen, A.; Probst-Hensch, N.; Quass, U.; Raaschou-Nielsen, O.; Ranzi, A.; Stephanou, E.; Sugiri, D.; Udvardy, O.; Vaskövi, É.; Weinmayr, G.; Brunekreef, B.; Hoek, G. Spatial variation of PM2.5, PM10, PM2.5 absorbance and PMcoarse concentrations between and within 20 European study areas and the relationship with NO2—Results of the ESCAPE project. Atmos. Environ. 2012, 62, 303317,  DOI: 10.1016/j.atmosenv.2012.08.038
  7. 7
    Tsai, M.-Y.; Hoek, G.; Eeftens, M.; de Hoogh, K.; Beelen, R.; Beregszászi, T.; Cesaroni, G.; Cirach, M.; Cyrys, J.; De Nazelle, A.; de Vocht, F.; Ducret-Stich, R.; Eriksen, K.; Galassi, C.; Gražuleviciene, R.; Gražulevicius, T.; Grivas, G.; Gryparis, A.; Heinrich, J.; Hoffmann, B.; Iakovides, M.; Keuken, M.; Krämer, U.; Künzli, N.; Lanki, T.; Madsen, C.; Meliefste, K.; Merritt, A.-S.; Mölter, A.; Mosler, G.; Nieuwenhuijsen, M. J.; Pershagen, G.; Phuleria, H.; Quass, U.; Ranzi, A.; Schaffner, E.; Sokhi, R.; Stempfelet, M.; Stephanou, E.; Sugiri, D.; Taimisto, P.; Tewis, M.; Udvardy, O.; Wang, M.; Brunekreef, B. Spatial variation of PM elemental composition between and within 20 European study areas--Results of the ESCAPE project. Environ. Int. 2015, 84, 181192,  DOI: 10.1016/j.envint.2015.04.015
  8. 8
    de Hoogh, K.; Wang, M.; Adam, M.; Badaloni, C.; Beelen, R.; Birk, M.; Cesaroni, G.; Cirach, M.; Declercq, C.; Dėdelė, A.; Dons, E.; de Nazelle, A.; Eeftens, M.; Eriksen, K.; Eriksson, C.; Fischer, P.; Gražulevičienė, R.; Gryparis, A.; Hoffmann, B.; Jerrett, M.; Katsouyanni, K.; Iakovides, M.; Lanki, T.; Lindley, S.; Madsen, C.; Mölter, A.; Mosler, G.; Nádor, G.; Nieuwenhuijsen, M.; Pershagen, G.; Peters, A.; Phuleria, H.; Probst-Hensch, N.; Raaschou-Nielsen, O.; Quass, U.; Ranzi, A.; Stephanou, E.; Sugiri, D.; Schwarze, P.; Tsai, M.-Y.; Yli-Tuomi, T.; Varró, M. J.; Vienneau, D.; Weinmayr, G.; Brunekreef, B.; Hoek, G. Development of land use regression models for particle composition in twenty study areas in Europe. Environ. Sci. Technol. 2013, 47, 57785786,  DOI: 10.1021/es400156t
  9. 9
    Beelen, R.; Hoek, G.; Raaschou-Nielsen, O.; Stafoggia, M.; Andersen, Z. J.; Weinmayr, G.; Hoffmann, B.; Wolf, K.; Samoli, E.; Fischer, P. H.; Nieuwenhuijsen, M. J.; Xun, W. W.; Katsouyanni, K.; Dimakopoulou, K.; Marcon, A.; Vartiainen, E.; Lanki, T.; Yli-Tuomi, T.; Oftedal, B.; Schwarze, P. E.; Nafstad, P.; De Faire, U.; Pedersen, N. L.; Östenson, C.-G.; Fratiglioni, L.; Penell, J.; Korek, M.; Pershagen, G.; Eriksen, K. T.; Overvad, K.; Sørensen, M.; Eeftens, M.; Peeters, P. H.; Meliefste, K.; Wang, M.; Bueno-de-Mesquita, H. B.; Sugiri, D.; Krämer, U.; Heinrich, J.; de Hoogh, K.; Key, T.; Peters, A.; Hampel, R.; Concin, H.; Nagel, G.; Jaensch, A.; Ineichen, A.; Tsai, M.-Y.; Schaffner, E.; Probst-Hensch, N. M.; Schindler, C.; Ragettli, M. S.; Vilier, A.; Clavel-Chapelon, F.; Declercq, C.; Ricceri, F.; Sacerdote, C.; Galassi, C.; Migliore, E.; Ranzi, A.; Cesaroni, G.; Badaloni, C.; Forastiere, F.; Katsoulis, M.; Trichopoulou, A.; Keuken, M.; Jedynska, A.; Kooter, I. M.; Kukkonen, J.; Sokhi, R. S.; Vineis, P.; Brunekreef, B. Natural-cause mortality and long-term exposure to particle components: an analysis of 19 European cohorts within the multi-center ESCAPE project. Environ. Health Perspect. 2015, 123, 525533,  DOI: 10.1289/ehp.1408095
  10. 10
    Basagaña, X.; Rivera, M.; Aguilera, I.; Agis, D.; Bouso, L.; Elosua, R.; Foraster, M.; de Nazelle, A.; Nieuwenhuijsen, M.; Vila, J.; Künzli, N. Effect of the number of measurement sites on land use regression models in estimating local air pollution. Atmos. Environ. 2012, 54, 634642,  DOI: 10.1016/j.atmosenv.2012.01.064
  11. 11
    Wang, M.; Beelen, R.; Eeftens, M.; Meliefste, K.; Hoek, G.; Brunekreef, B. Systematic evaluation of land use regression models for NO2. Environ. Sci. Technol. 2012, 46, 44814489,  DOI: 10.1021/es204183v
  12. 12
    De Hoogh, K.; Chen, J.; Gulliver, J.; Hoffmann, B.; Hertel, O.; Ketzel, M.; Bauwelinck, M.; van Donkelaar, A.; Hvidtfeldt, U. A.; Katsouyanni, K.; Klompmaker, J.; Martin, R. V.; Samoli, E.; Schwartz, P. E.; Stafoggia, M.; Bellander, T.; Strak, M.; Wolf, K.; Vienneau, D.; Brunekreef, B.; Hoek, G. Spatial PM2.5, NO2, O3 and BC models for Western Europe—Evaluation of spatiotemporal stability. Environ. Int. 2018, 120, 8192,  DOI: 10.1016/j.envint.2018.07.036
  13. 13
    de Hoogh, K.; Gulliver, J.; van Donkelaar, A.; Martin, R. V.; Marshall, J. D.; Bechle, M. J.; Cesaroni, G.; Pradas, M. C.; Dedele, A.; Eeftens, M.; Forsberg, B.; Galassi, C.; Heinrich, J.; Hoffmann, B.; Jacquemin, B.; Katsouyanni, K.; Korek, M.; Künzli, N.; Lindley, S. J.; Lepeule, J.; Meleux, F.; de Nazelle, A.; Nieuwenhuijsen, M.; Nystad, W.; Raaschou-Nielsen, O.; Peters, A.; Peuch, V.-H.; Rouil, L.; Udvardy, O.; Slama, R.; Stempfelet, M.; Stephanou, E. G.; Tsai, M. Y.; Yli-Tuomi, T.; Weinmayr, G.; Brunekreef, B.; Vienneau, D.; Hoek, G. Development of West-European PM 2.5 and NO 2 land use regression models incorporating satellite-derived and chemical transport modelling data. Environ. Res. 2016, 151, 110,  DOI: 10.1016/j.envres.2016.07.005
  14. 14
    Brauer, M.; Hoek, G.; van Vliet, P.; Meliefste, K.; Fischer, P.; Gehring, U.; Heinrich, J.; Cyrys, J.; Bellander, T.; Lewne, M.; Brunekreef, B. Estimating long-term average particulate air pollution concentrations: application of traffic indicators and geographic information systems. Epidemiology 2003, 14, 228239,  DOI: 10.1097/01.ede.0000041910.49046.9b
  15. 15
    Henderson, S. B.; Beckerman, B.; Jerrett, M.; Brauer, M. Application of land use regression to estimate long-term concentrations of traffic-related nitrogen oxides and fine particulate matter. Environ. Sci. Technol. 2007, 41, 24222428,  DOI: 10.1021/es0606780
  16. 16
    Chen, J.; de Hoogh, K.; Gulliver, J.; Hoffmann, B.; Hertel, O.; Ketzel, M.; Bauwelinck, M.; van Donkelaar, A.; Hvidtfeldt, U. A.; Katsouyanni, K.; Janssen, N. A. H.; Martin, R. V.; Samoli, E.; Schwartz, P. E.; Stafoggia, M.; Bellander, T.; Strak, M.; Wolf, K.; Vienneau, D.; Vermeulen, R.; Brunekreef, B.; Hoek, G. A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide. Environ. Int. 2019, 130, 104934,  DOI: 10.1016/j.envint.2019.104934
  17. 17
    Kerckhoffs, J.; Hoek, G.; Portengen, L.; Brunekreef, B.; Vermeulen, R. C. H. Performance of Prediction Algorithms for Modeling Outdoor Air Pollution Spatial Surfaces. Environ. Sci. Technol. 2019, 53, 14131421,  DOI: 10.1021/acs.est.8b06038
  18. 18
    Meng, X.; Hand, J. L.; Schichtel, B. A.; Liu, Y. Space-time trends of PM2.5 constituents in the conterminous United States estimated by a machine learning approach, 2005-2015. Environ. Int. 2018, 121, 11371147,  DOI: 10.1016/j.envint.2018.10.029
  19. 19
    Hu, X.; Belle, J. H.; Meng, X.; Wildani, A.; Waller, L. A.; Strickland, M. J.; Liu, Y. Estimating PM2.5 Concentrations in the Conterminous United States Using the Random Forest Approach. Environ. Sci. Technol. 2017, 51, 69366944,  DOI: 10.1021/acs.est.7b01210
  20. 20
    Breiman, L. Random forests. Mach. Learn. 2001, 45, 532,  DOI: 10.1023/a:1010933404324
  21. 21
    Brokamp, C.; Jandarov, R.; Rao, M. B.; LeMasters, G.; Ryan, P. Exposure assessment models for elemental components of particulate matter in an urban environment: A comparison of regression and random forest approaches. Atmos. Environ. 2017, 151, 111,  DOI: 10.1016/j.atmosenv.2016.11.066
  22. 22
    Hoek, G.; Beelen, R.; De Hoogh, K.; Vienneau, D.; Gulliver, J.; Fischer, P.; Briggs, D. A review of land-use regression models to assess spatial variation of outdoor air pollution. Atmos. Environ. 2008, 42, 75617578,  DOI: 10.1016/j.atmosenv.2008.05.057
  23. 23
    Eeftens, M.; Beelen, R.; de Hoogh, K.; Bellander, T.; Cesaroni, G.; Cirach, M.; Declercq, C.; Dėdelė, A.; Dons, E.; de Nazelle, A.; Dimakopoulou, K.; Eriksen, K.; Falq, G.; Fischer, P.; Galassi, C.; Gražulevičienė, R.; Heinrich, J.; Hoffmann, B.; Jerrett, M.; Keidel, D.; Korek, M.; Lanki, T.; Lindley, S.; Madsen, C.; Mölter, A.; Nádor, G.; Nieuwenhuijsen, M.; Nonnemacher, M.; Pedeli, X.; Raaschou-Nielsen, O.; Patelarou, E.; Quass, U.; Ranzi, A.; Schindler, C.; Stempfelet, M.; Stephanou, E.; Sugiri, D.; Tsai, M.-Y.; Yli-Tuomi, T.; Varró, M. J.; Vienneau, D.; Klot, S. v.; Wolf, K.; Brunekreef, B.; Hoek, G. Development of Land Use Regression Models for PM2.5, PM2.5 Absorbance, PM10 and PMcoarse in 20 European Study Areas; Results of the ESCAPE Project. Environ. Sci. Technol. 2012, 46, 1119511205,  DOI: 10.1021/es301948k
  24. 24
    GEOSTAT (version 2.0.1). 2011, https://ec.europa.eu/eurostat/web/gisco/geodata/reference-data/population-distribution-demography/geostat (last accessed July 19, 2019).
  25. 25
    CGIAR-CSI. Srtm 90m Digital Elevation Data , 2013.
  26. 26
    CLC. 2012, https://land.copernicus.eu/pan-european/corine-land-cover/clc-2012 (last accessed July 19, 2019).
  27. 27
    van Donkelaar, A.; Martin, R. V.; Li, C.; Burnett, R. T. Regional Estimates of Chemical Composition of Fine Particulate Matter Using a Combined Geoscience-Statistical Method with Information from Satellites, Models, and Monitors. Environ. Sci. Technol. 2019, 53, 25952611,  DOI: 10.1021/acs.est.8b06392
  28. 28
    ECMWF. https://apps.ecmwf.int/datasets/data/macc-reanalysis/levtype=sfc/ (last accessed July 23, 2019).
  29. 29
    Inness, A.; Baier, F.; Benedetti, A.; Bouarar, I.; Chabrillat, S.; Clark, H.; Clerbaux, C.; Coheur, P.; Engelen, R. J.; Errera, Q.; Flemming, J.; George, M.; Granier, C.; Hadji-Lazaro, J.; Huijnen, V.; Hurtmans, D.; Jones, L.; Kaiser, J. W.; Kapsomenakis, J.; Lefever, K.; Leitão, J.; Razinger, M.; Richter, A.; Schultz, M. G.; Simmons, A. J.; Suttie, M.; Stein, O.; Thépaut, J.-N.; Thouret, V.; Vrekoussis, M.; Zerefos, C. The MACC reanalysis: an 8 yr data set of atmospheric composition. Atmos. Chem. Phys. 2013, 13, 40734109,  DOI: 10.5194/acp-13-4073-2013
  30. 31
    Liaw, A.; Wiener, M. Classification and regression by randomForest. R News 2002, 2, 1822
  31. 32
    Murray, N. L.; Holmes, H. A.; Liu, Y.; Chang, H. H. A Bayesian ensemble approach to combine PM2.5 estimates from statistical models using satellite imagery and numerical model simulation. Environ. Res. 2019, 178, 108601,  DOI: 10.1016/j.envres.2019.108601
  32. 33
    Wang, M.; Beelen, R.; Bellander, T.; Birk, M.; Cesaroni, G.; Cirach, M.; Cyrys, J.; de Hoogh, K.; Declercq, C.; Dimakopoulou, K.; Eeftens, M.; Eriksen, K. T.; Forastiere, F.; Galassi, C.; Grivas, G.; Heinrich, J.; Hoffmann, B.; Ineichen, A.; Korek, M.; Lanki, T.; Lindley, S.; Modig, L.; Mölter, A.; Nafstad, P.; Nieuwenhuijsen, M. J.; Nystad, W.; Olsson, D.; Raaschou-Nielsen, O.; Ragettli, M.; Ranzi, A.; Stempfelet, M.; Sugiri, D.; Tsai, M.-Y.; Udvardy, O.; Varró, M. J.; Vienneau, D.; Weinmayr, G.; Wolf, K.; Yli-Tuomi, T.; Hoek, G.; Brunekreef, B. Performance of multi-city land use regression models for nitrogen dioxide and fine particles. Environ. Health Perspect. 2014, 122, 843849,  DOI: 10.1289/ehp.1307271
  33. 34
    Vedal, S.; Campen, M. J.; McDonald, J. D.; Kaufman, J. D.; Larson, T. V.; Sampson, P. D.; Sheppard, L.; Simpson, C. D.; Szpiro, A. A. National Particle Component Toxicity (NPACT) Initiative Report on Cardiovascular Effects. Research Report 178. Health Effects Institute: Boston, MA, 2013.
  34. 35
    Belis, C. A.; Karagulian, F.; Larsen, B. R.; Hopke, P. K. Critical review and meta-analysis of ambient particulate matter source apportionment using receptor models in Europe. Atmos. Environ. 2013, 69, 94108,  DOI: 10.1016/j.atmosenv.2012.11.009
  35. 36
    Ito, K.; Johnson, S.; Kheirbek, I.; Clougherty, J.; Pezeshki, G.; Ross, Z.; Eisl, H.; Matte, T. D. Intraurban Variation of Fine Particle Elemental Concentrations in New York City. Environ. Sci. Technol. 2016, 50, 75177526,  DOI: 10.1021/acs.est.6b00599
  36. 37
    Tripathy, S.; Tunno, B. J.; Michanowicz, D. R.; Kinnee, E.; Shmool, J. L. C.; Gillooly, S.; Clougherty, J. E. Hybrid land use regression modeling for estimating spatio-temporal exposures to PM2.5, BC, and metal components across a metropolitan area of complex terrain and industrial sources. Sci. Total Environ. 2019, 673, 5463,  DOI: 10.1016/j.scitotenv.2019.03.453
  37. 38
    Zhang, J. J. Y.; Sun, L.; Barrett, O.; Bertazzon, S.; Underwood, F. E.; Johnson, M. Development of land-use regression models for metals associated with airborne particulate matter in a North American city. Atmos. Environ. 2015, 106, 165177,  DOI: 10.1016/j.atmosenv.2015.01.008
  38. 39
    Viana, M.; Kuhlbusch, T. A. J.; Querol, X.; Alastuey, A.; Harrison, R. M.; Hopke, P. K.; Winiwarter, W.; Vallius, M.; Szidat, S.; Prévôt, A. S. H.; Hueglin, C.; Bloemen, H.; Waåhlin, P.; Vecchi, R.; Miranda, A. I.; Kasper-Giebl, A.; Maenhaut, W.; Hitzenberger, R. Source apportionment of particulate matter in Europe: A review of methods and results. J. Aerosol Sci. 2008, 39, 827849,  DOI: 10.1016/j.jaerosci.2008.05.007
  39. 40
    Michanowicz, D. R.; Shmool, J. L. C.; Tunno, B. J.; Tripathy, S.; Gillooly, S.; Kinnee, E.; Clougherty, J. E. A hybrid land use regression/AERMOD model for predicting intra-urban variation in PM2.5. Atmos. Environ. 2016, 131, 307315,  DOI: 10.1016/j.atmosenv.2016.01.045

Cited By

ARTICLE SECTIONS
Jump To

This article is cited by 41 publications.

  1. Zhiyang Liao, Jinrong Lu, Kunting Xie, Yi Wang, Yong Yuan. Prediction of Photochemical Properties of Dissolved Organic Matter Using Machine Learning. Environmental Science & Technology 2023, 57 (46) , 17971-17980. https://doi.org/10.1021/acs.est.2c07545
  2. Labeeb Ali, Kaushik Sivaramakrishnan, Mohamed Shafi Kuttiyathil, Vignesh Chandrasekaran, Oday H. Ahmed, Mohammad Al-Harahsheh, Mohammednoor Altarawneh. Prediction of Thermogravimetric Data in the Thermal Recycling of e-waste Using Machine Learning Techniques: A Data-driven Approach. ACS Omega 2023, 8 (45) , 43254-43270. https://doi.org/10.1021/acsomega.3c07228
  3. Kaushik Sivaramakrishnan, Joy H. Tannous, Vignesh Chandrasekaran. Prediction of Thermogravimetric Data for Asphaltenes Extracted from Deasphalted Oil Using Machine Learning Techniques. Industrial & Engineering Chemistry Research 2023, 62 (43) , 17787-17804. https://doi.org/10.1021/acs.iecr.3c01798
  4. Labeeb Ali, Kaushik Sivaramakrishnan, Mohamed Shafi Kuttiyathil, Vignesh Chandrasekaran, Oday H. Ahmed, Mohammad Al-Harahsheh, Mohammednoor Altarawneh. Prediction of Thermogravimetric Data in Bromine Captured from Brominated Flame Retardants (BFRs) in e-Waste Treatment Using Machine Learning Approaches. Journal of Chemical Information and Modeling 2023, 63 (8) , 2305-2320. https://doi.org/10.1021/acs.jcim.3c00183
  5. Provat K. Saha, Albert A. Presto, Steve Hankey, Benjamin N. Murphy, Chris Allen, Wenwen Zhang, Julian D. Marshall, Allen L. Robinson. National Exposure Models for Source-Specific Primary Particulate Matter Concentrations Using Aerosol Mass Spectrometry Data. Environmental Science & Technology 2022, 56 (20) , 14284-14295. https://doi.org/10.1021/acs.est.2c03398
  6. Jie Chen, Gerard Hoek, Kees de Hoogh, Sophia Rodopoulou, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Ulla Arthur Hvidtfeldt, W. M. Monique Verschuren, Karl-Heinz Jöckel, Jeanette T. Jørgensen, Klea Katsouyanni, Matthias Ketzel, Diego Yacamán Méndez, Karin Leander, Shuo Liu, Petter Ljungman, Elodie Faure, Patrik K. E. Magnusson, Gabriele Nagel, Göran Pershagen, Annette Peters, Ole Raaschou-Nielsen, Debora Rizzuto, Evangelia Samoli, Yvonne T. van der Schouw, Sara Schramm, Gianluca Severi, Massimo Stafoggia, Maciej Strak, Mette Sørensen, Anne Tjønneland, Gudrun Weinmayr, Kathrin Wolf, Emanuel Zitt, Bert Brunekreef, George D. Thurston. Long-Term Exposure to Source-Specific Fine Particles and Mortality─A Pooled Analysis of 14 European Cohorts within the ELAPSE Project. Environmental Science & Technology 2022, 56 (13) , 9277-9290. https://doi.org/10.1021/acs.est.2c01912
  7. Julia C. Fussell, Meredith Franklin, David C. Green, Mats Gustafsson, Roy M. Harrison, William Hicks, Frank J. Kelly, Franceska Kishta, Mark R. Miller, Ian S. Mudway, Farzan Oroumiyeh, Liza Selley, Meng Wang, Yifang Zhu. A Review of Road Traffic-Derived Non-Exhaust Particles: Emissions, Physicochemical Characteristics, Health Risks, and Mitigation Measures. Environmental Science & Technology 2022, 56 (11) , 6813-6835. https://doi.org/10.1021/acs.est.2c01072
  8. Beatrice Cornu Hewitt, Lidwien A.M. Smit, Warner van Kersen, Inge M. Wouters, Dick J.J. Heederik, Jules Kerckhoffs, Gerard Hoek, Myrna M.T. de Rooij. Residential exposure to microbial emissions from livestock farms: Implementation and evaluation of land use regression and random forest spatial models. Environmental Pollution 2024, 346 , 123590. https://doi.org/10.1016/j.envpol.2024.123590
  9. Gabriele Nagel, Jie Chen, Andrea Jaensch, Lea Skodda, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Ulla Arthur Hvidtfeldt, Klea Katsouyanni, Matthias Ketzel, Karin Leander, Patrik K. E. Magnusson, Göran Pershagen, Debora Rizzuto, Evangelia Samoli, Gianluca Severi, Massimo Stafoggia, Anne Tjønneland, Roel C. H. Vermeulen, Kathrin Wolf, Emanuel Zitt, Bert Brunekreef, Gerard Hoek, Ole Raaschou‐Nielsen, Gudrun Weinmayr. Long‐term exposure to air pollution and incidence of gastric and the upper aerodigestive tract cancers in a pooled European cohort: The ELAPSE project. International Journal of Cancer 2024, 11 https://doi.org/10.1002/ijc.34864
  10. Gudrun Weinmayr, Jie Chen, Andrea Jaensch, Lea Skodda, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Ulla Arthur Hvidtfeldt, Klea Katsouyanni, Matthias Ketzel, Karin Leander, Patrik K.E. Magnusson, Göran Pershagen, Debora Rizzuto, Evangelia Samoli, Gianluca Severi, Massimo Stafoggia, Anne Tjønneland, Roel Vermeulen, Kathrin Wolf, Emanuel Zitt, Bert Brunekreef, George Thurston, Gerard Hoek, Ole Raaschou-Nielsen, Gabriele Nagel. Long-term exposure to several constituents and sources of PM2.5 is associated with incidence of upper aerodigestive tract cancers but not gastric cancer: Results from the large pooled European cohort of the ELAPSE project. Science of The Total Environment 2024, 912 , 168789. https://doi.org/10.1016/j.scitotenv.2023.168789
  11. Jacopo Vanoli, Malcolm N. Mistry, Arturo De La Cruz Libardi, Pierre Masselot, Rochelle Schneider, Chris Fook Sheng Ng, Lina Madaniyazi, Antonio Gasparrini. Reconstructing individual-level exposures in cohort analyses of environmental risks: an example with the UK Biobank. Journal of Exposure Science & Environmental Epidemiology 2024, 151 https://doi.org/10.1038/s41370-023-00635-w
  12. Zhiyuan Li, Kin-Fai Ho, Harry Fung Lee, Steve Hung Lam Yim. Development of an integrated model framework for multi-air-pollutant exposure assessments in high-density cities. Atmospheric Chemistry and Physics 2024, 24 (1) , 649-661. https://doi.org/10.5194/acp-24-649-2024
  13. Behzad Valipour Shokouhi, Kees de Hoogh, Regula Gehrig, Marloes Eeftens. Estimation of historical daily airborne pollen concentrations across Switzerland using a spatio temporal random forest model. Science of The Total Environment 2024, 906 , 167286. https://doi.org/10.1016/j.scitotenv.2023.167286
  14. Danielle Vienneau, Massimo Stafoggia, Sophia Rodopoulou, Jie Chen, Richard W. Atkinson, Mariska Bauwelinck, Jochem O. Klompmaker, Bente Oftedal, Zorana J. Andersen, Nicole A. H. Janssen, Rina So, Youn-Hee Lim, Benjamin Flückiger, Regina Ducret-Stich, Martin Röösli, Nicole Probst-Hensch, Nino Künzli, Maciek Strak, Evangelia Samoli, Kees de Hoogh, Bert Brunekreef, Gerard Hoek. Association between exposure to multiple air pollutants, transportation noise and cause-specific mortality in adults in Switzerland. Environmental Health 2023, 22 (1) https://doi.org/10.1186/s12940-023-00983-y
  15. Ulla Arthur Hvidtfeldt, Jie Chen, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Francesco Forastiere, Boel Brynedal, Ole Hertel, Barbara Hoffmann, Klea Katsouyanni, Matthias Ketzel, Karin Leander, Patrik K.E. Magnusson, Gabriele Nagel, Göran Pershagen, Debora Rizzuto, Evangelia Samoli, Rina So, Massimo Stafoggia, Anne Tjønneland, Gudrun Weinmayr, Kathrin Wolf, Emanuel Zitt, Bert Brunekreef, Gerard Hoek, Ole Raaschou-Nielsen. Multiple myeloma risk in relation to long-term air pollution exposure - A pooled analysis of four European cohorts. Environmental Research 2023, 239 , 117230. https://doi.org/10.1016/j.envres.2023.117230
  16. Yun Zhang, Yubo Wang, Huanhuan Cheng, Fei Yan, Dingning Li, Dawei Song, Qiang Wang, Liyu Huang. EEG spectral slope: A reliable indicator for continuous evaluation of consciousness levels during propofol anesthesia. NeuroImage 2023, 283 , 120426. https://doi.org/10.1016/j.neuroimage.2023.120426
  17. Ulla Arthur Hvidtfeldt, Jie Chen, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Klea Katsouyanni, Matthias Ketzel, Karin Leander, Patrik K. E. Magnusson, Gabriele Nagel, Göran Pershagen, Debora Rizzuto, Evangelia Samoli, Rina So, Massimo Stafoggia, Anne Tjønneland, Gudrun Weinmayr, Kathrin Wolf, Jiawei Zhang, Emanuel Zitt, Bert Brunekreef, Gerard Hoek, Ole Raaschou-Nielsen. Long-term air pollution exposure and malignant intracranial tumours of the central nervous system: a pooled analysis of six European cohorts. British Journal of Cancer 2023, 129 (4) , 656-664. https://doi.org/10.1038/s41416-023-02348-1
  18. Zhendong Yuan, Jules Kerckhoffs, Youchen Shen, Kees de Hoogh, Gerard Hoek, Roel Vermeulen. Integrating large-scale stationary and local mobile measurements to estimate hyperlocal long-term air pollution using transfer learning methods. Environmental Research 2023, 228 , 115836. https://doi.org/10.1016/j.envres.2023.115836
  19. Rina So, Jie Chen, Massimo Stafoggia, Kees de Hoogh, Klea Katsouyanni, Danielle Vienneau, Evangelia Samoli, Sophia Rodopoulou, Steffen Loft, Youn-Hee Lim, Rudi G.J. Westendorp, Heresh Amini, Thomas Cole-Hunter, Marie Bergmann, Seyed Mahmood Taghavi Shahri, Jiawei Zhang, Matija Maric, Laust H. Mortensen, Mariska Bauwelinck, Jochem O. Klompmaker, Richard W. Atkinson, Nicole A.H. Janssen, Bente Oftedal, Matteo Renzi, Francesco Forastiere, Maciek Strak, Bert Brunekreef, Gerard Hoek, Zorana J. Andersen. Long-term exposure to elemental components of fine particulate matter and all-natural and cause-specific mortality in a Danish nationwide administrative cohort study. Environmental Research 2023, 224 , 115552. https://doi.org/10.1016/j.envres.2023.115552
  20. Ulla Arthur Hvidtfeldt, Jie Chen, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara H. Hoffmann, Klea Katsouyanni, Matthias Ketzel, Boel Brynedal, Karin Leander, Petter L.S. Ljungman, Patrik K.E. Magnusson, Gabriele Nagel, Göran Pershagen, Debora Rizzuto, Marie-Christine Boutron-Ruault, Evangelia Samoli, Rina So, Massimo Stafoggia, Anne Tjønneland, Roel Vermeulen, W.M. Monique Verschuren, Gudrun Weinmayr, Kathrin Wolf, Jiawei Zhang, Emanuel Zitt, Bert Brunekreef, Gerard Hoek, Ole Raaschou-Nielsen. Breast Cancer Incidence in Relation to Long-Term Low-Level Exposure to Air Pollution in the ELAPSE Pooled Cohort. Cancer Epidemiology, Biomarkers & Prevention 2023, 32 (1) , 105-113. https://doi.org/10.1158/1055-9965.EPI-22-0720
  21. Thomas Cole-Hunter, Jiawei Zhang, Rina So, Evangelia Samoli, Shuo Liu, Jie Chen, Maciej Strak, Kathrin Wolf, Gudrun Weinmayr, Sophia Rodopolou, Elizabeth Remfry, Kees de Hoogh, Tom Bellander, Jørgen Brandt, Hans Concin, Emanuel Zitt, Daniela Fecht, Francesco Forastiere, John Gulliver, Barbara Hoffmann, Ulla A. Hvidtfeldt, Karl-Heinz Jöckel, Laust H. Mortensen, Matthias Ketzel, Diego Yacamán Méndez, Karin Leander, Petter Ljungman, Elodie Faure, Pei-Chen Lee, Alexis Elbaz, Patrik K.E. Magnusson, Gabriele Nagel, Göran Pershagen, Annette Peters, Debora Rizzuto, Roel C.H. Vermeulen, Sara Schramm, Massimo Stafoggia, Klea Katsouyanni, Bert Brunekreef, Gerard Hoek, Youn-Hee Lim, Zorana J. Andersen. Long-term air pollution exposure and Parkinson’s disease mortality in a large pooled European cohort: An ELAPSE study. Environment International 2023, 171 , 107667. https://doi.org/10.1016/j.envint.2022.107667
  22. Jia Xu, Peng Wang, Tiantian Li, Guoliang Shi, Meng Wang, Lei Huang, Shaofei Kong, Jicheng Gong, Wen Yang, Xinhua Wang, Chunmei Geng, Bin Han, Zhipeng Bai. Exposure to Source-Specific Particulate Matter and Health Effects: a Review of Epidemiological Studies. Current Pollution Reports 2022, 8 (4) , 569-593. https://doi.org/10.1007/s40726-022-00235-6
  23. Yihang Hong, Fang Cao, Mei-Yi Fan, Yu-Chi Lin, Mengying Bao, Yongwen Xue, Jiyan Wu, Mingyuan Yu, Xia Wu, Yan-Lin Zhang. Using machine learning to quantify sources of light-absorbing water-soluble humic-like substances (HULISws) in Northeast China. Atmospheric Environment 2022, 291 , 119371. https://doi.org/10.1016/j.atmosenv.2022.119371
  24. Zorana J. Andersen, Jiawei Zhang, Jeanette T. Jørgensen, Evangelia Samoli, Shuo Liu, Jie Chen, Maciej Strak, Kathrin Wolf, Gudrun Weinmayr, Sophia Rodopolou, Elizabeth Remfry, Kees de Hoogh, Tom Bellander, Jørgen Brandt, Hans Concin, Emanuel Zitt, Daniela Fecht, Francesco Forastiere, John Gulliver, Barbara Hoffmann, Ulla A. Hvidtfeldt, W.M. Monique Verschuren, Karl-Heinz Jöckel, Rina So, Tom Cole-Hunter, Amar J. Mehta, Laust H. Mortensen, Matthias Ketzel, Anton Lager, Karin Leander, Petter Ljungman, Gianluca Severi, Marie-Christine Boutron-Ruault, Patrik K.E. Magnusson, Gabriele Nagel, Göran Pershagen, Annette Peters, Debora Rizzuto, Yvonne T. van der Schouw, Sara Schramm, Massimo Stafoggia, Klea Katsouyanni, Bert Brunekreef, Gerard Hoek, Youn-Hee Lim. Long-term exposure to air pollution and mortality from dementia, psychiatric disorders, and suicide in a large pooled European cohort: ELAPSE study. Environment International 2022, 170 , 107581. https://doi.org/10.1016/j.envint.2022.107581
  25. Ulla Arthur Hvidtfeldt, Tahir Taj, Jie Chen, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Jeanette T. Jørgensen, Klea Katsouyanni, Matthias Ketzel, Anton Lager, Karin Leander, Petter Ljungman, Patrik K.E. Magnusson, Gabriele Nagel, Göran Pershagen, Debora Rizzuto, Evangelia Samoli, Rina So, Massimo Stafoggia, Anne Tjønneland, Roel Vermeulen, Gudrun Weinmayr, Kathrin Wolf, Jiawei Zhang, Emanuel Zitt, Bert Brunekreef, Gerard Hoek, Ole Raaschou-Nielsen. Long term exposure to air pollution and kidney parenchyma cancer – Effects of low-level air pollution: a Study in Europe (ELAPSE). Environmental Research 2022, 215 , 114385. https://doi.org/10.1016/j.envres.2022.114385
  26. Youchen Shen, Kees de Hoogh, Oliver Schmitz, Nicholas Clinton, Karin Tuxen-Bettman, Jørgen Brandt, Jesper H. Christensen, Lise M. Frohn, Camilla Geels, Derek Karssenberg, Roel Vermeulen, Gerard Hoek. Europe-wide air pollution modeling from 2000 to 2019 using geographically weighted regression. Environment International 2022, 168 , 107485. https://doi.org/10.1016/j.envint.2022.107485
  27. Xiaozhe Yin, Meredith Franklin, Masoud Fallah-Shorshani, Martin Shafer, Rob McConnell, Scott Fruin. Exposure models for particulate matter elemental concentrations in Southern California. Environment International 2022, 165 , 107247. https://doi.org/10.1016/j.envint.2022.107247
  28. Emeline Lequy, Caroline Meyer, Danielle Vienneau, Claudine Berr, Marcel Goldberg, Marie Zins, Sébastien Leblond, Kees de Hoogh, Bénédicte Jacquemin. Modeling exposure to airborne metals using moss biomonitoring in cemeteries in two urban areas around Paris and Lyon in France. Environmental Pollution 2022, 303 , 119097. https://doi.org/10.1016/j.envpol.2022.119097
  29. Jie Chen, Sophia Rodopoulou, Maciej Strak, Kees de Hoogh, Tahir Taj, Aslak Harbo Poulsen, Zorana J. Andersen, Tom Bellander, Jørgen Brandt, Emanuel Zitt, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Ulla Arthur Hvidtfeldt, W. M. Monique Verschuren, Jeanette T. Jørgensen, Klea Katsouyanni, Matthias Ketzel, Anton Lager, Karin Leander, Shuo Liu, Petter Ljungman, Gianluca Severi, Marie-Christine Boutron-Ruault, Patrik K. E. Magnusson, Gabriele Nagel, Göran Pershagen, Annette Peters, Debora Rizzuto, Yvonne T. van der Schouw, Evangelia Samoli, Mette Sørensen, Massimo Stafoggia, Anne Tjønneland, Gudrun Weinmayr, Kathrin Wolf, Bert Brunekreef, Ole Raaschou-Nielsen, Gerard Hoek. Long-term exposure to ambient air pollution and bladder cancer incidence in a pooled European cohort: the ELAPSE project. British Journal of Cancer 2022, 126 (10) , 1499-1507. https://doi.org/10.1038/s41416-022-01735-4
  30. Md Mostafijur Rahman, George Thurston. A hybrid satellite and land use regression model of source-specific PM2.5 and PM2.5 constituents. Environment International 2022, 163 , 107233. https://doi.org/10.1016/j.envint.2022.107233
  31. Konstantina Dimakopoulou, Evangelia Samoli, Antonis Analitis, Joel Schwartz, Sean Beevers, Nutthida Kitwiroon, Andrew Beddows, Benjamin Barratt, Sophia Rodopoulou, Sofia Zafeiratou, John Gulliver, Klea Katsouyanni. Development and Evaluation of Spatio-Temporal Air Pollution Exposure Models and Their Combinations in the Greater London Area, UK. International Journal of Environmental Research and Public Health 2022, 19 (9) , 5401. https://doi.org/10.3390/ijerph19095401
  32. Zhiyuan Li, Kin-Fai Ho, Guanghui Dong, Harry Fung Lee, Steve Hung Lam Yim. A novel approach for assessing the spatiotemporal trend of health risk from ambient particulate matter components: Case of Hong Kong. Environmental Research 2022, 204 , 111866. https://doi.org/10.1016/j.envres.2021.111866
  33. Joyce J.Y. Zhang, Liu Sun, Daniel Rainham, Trevor J.B. Dummer, Amanda J. Wheeler, Angelos Anastasopolos, Mark Gibson, Markey Johnson. Predicting intraurban airborne PM1.0-trace elements in a port city: Land use regression by ordinary least squares and a machine learning algorithm. Science of The Total Environment 2022, 806 , 150149. https://doi.org/10.1016/j.scitotenv.2021.150149
  34. Sophia Rodopoulou, Massimo Stafoggia, Jie Chen, Kees de Hoogh, Mariska Bauwelinck, Amar J. Mehta, Jochem O. Klompmaker, Bente Oftedal, Danielle Vienneau, Nicole A.H. Janssen, Maciej Strak, Zorana J. Andersen, Matteo Renzi, Giulia Cesaroni, Carl Fredrik Nordheim, Terese Bekkevold, Richard Atkinson, Francesco Forastiere, Klea Katsouyanni, Bert Brunekreef, Evangelia Samoli, Gerard Hoek. Long-term exposure to fine particle elemental components and mortality in Europe: Results from six European administrative cohorts within the ELAPSE project. Science of The Total Environment 2022, 809 , 152205. https://doi.org/10.1016/j.scitotenv.2021.152205
  35. Rina So, Jie Chen, Amar J. Mehta, Shuo Liu, Maciej Strak, Kathrin Wolf, Ulla A. Hvidtfeldt, Sophia Rodopoulou, Massimo Stafoggia, Jochem O. Klompmaker, Evangelia Samoli, Ole Raaschou‐Nielsen, Richard Atkinson, Mariska Bauwelinck, Tom Bellander, Marie‐Christine Boutron‐Ruault, Jørgen Brandt, Bert Brunekreef, Giulia Cesaroni, Hans Concin, Francesco Forastiere, Carla H. van Gils, John Gulliver, Ole Hertel, Barbara Hoffmann, Kees de Hoogh, Nicole Janssen, Youn‐hee Lim, Rudi Westendorp, Jeanette T. Jørgensen, Klea Katsouyanni, Matthias Ketzel, Anton Lager, Alois Lang, Petter L. Ljungman, Patrik K.E. Magnusson, Gabriele Nagel, Mette K. Simonsen, Göran Pershagen, Raphael S. Peter, Annette Peters, Matteo Renzi, Debora Rizzuto, Torben Sigsgaard, Danielle Vienneau, Gudrun Weinmayr, Gianluca Severi, Daniela Fecht, Anne Tjønneland, Karin Leander, Gerard Hoek, Zorana J. Andersen. Long‐term exposure to air pollution and liver cancer incidence in six European cohorts. International Journal of Cancer 2021, 149 (11) , 1887-1897. https://doi.org/10.1002/ijc.33743
  36. Ornella Luminati, Bartolomeu Ledebur de Antas de Campos, Benjamin Flückiger, Alexandra Brentani, Martin Röösli, Günther Fink, Kees de Hoogh. Land use regression modelling of NO2 in São Paulo, Brazil. Environmental Pollution 2021, 289 , 117832. https://doi.org/10.1016/j.envpol.2021.117832
  37. Chun-Sheng Huang, Ho-Tang Liao, Tang-Huang Lin, Jung-Chi Chang, Chien-Lin Lee, Eric Cheuk-Wai Yip, Yee-Lin Wu, Chang-Fu Wu. Evaluation of Using Satellite-Derived Aerosol Optical Depth in Land Use Regression Models for Fine Particulate Matter and Its Elemental Composition. Atmosphere 2021, 12 (8) , 1018. https://doi.org/10.3390/atmos12081018
  38. Jie Chen, Sophia Rodopoulou, Kees de Hoogh, Maciej Strak, Zorana J. Andersen, Richard Atkinson, Mariska Bauwelinck, Tom Bellander, Jørgen Brandt, Giulia Cesaroni, Hans Concin, Daniela Fecht, Francesco Forastiere, John Gulliver, Ole Hertel, Barbara Hoffmann, Ulla Arthur Hvidtfeldt, Nicole A. H. Janssen, Karl-Heinz Jöckel, Jeanette Jørgensen, Klea Katsouyanni, Matthias Ketzel, Jochem O. Klompmaker, Anton Lager, Karin Leander, Shuo Liu, Petter Ljungman, Conor J. MacDonald, Patrik K.E. Magnusson, Amar Mehta, Gabriele Nagel, Bente Oftedal, Göran Pershagen, Annette Peters, Ole Raaschou-Nielsen, Matteo Renzi, Debora Rizzuto, Evangelia Samoli, Yvonne T. van der Schouw, Sara Schramm, Per Schwarze, Torben Sigsgaard, Mette Sørensen, Massimo Stafoggia, Anne Tjønneland, Danielle Vienneau, Gudrun Weinmayr, Kathrin Wolf, Bert Brunekreef, Gerard Hoek. Long-Term Exposure to Fine Particle Elemental Components and Natural and Cause-Specific Mortality—a Pooled Analysis of Eight European Cohorts within the ELAPSE Project. Environmental Health Perspectives 2021, 129 (4) https://doi.org/10.1289/EHP8368
  39. Ulla Arthur Hvidtfeldt, Jie Chen, Zorana Jovanovic Andersen, Richard Atkinson, Mariska Bauwelinck, Tom Bellander, Jørgen Brandt, Bert Brunekreef, Giulia Cesaroni, Hans Concin, Daniela Fecht, Francesco Forastiere, Carla H. van Gils, John Gulliver, Ole Hertel, Gerard Hoek, Barbara Hoffmann, Kees de Hoogh, Nicole Janssen, Jeanette Therming Jørgensen, Klea Katsouyanni, Karl-Heinz Jöckel, Matthias Ketzel, Jochem O. Klompmaker, Alois Lang, Karin Leander, Shuo Liu, Petter L.S. Ljungman, Patrik K.E. Magnusson, Amar Jayant Mehta, Gabriele Nagel, Bente Oftedal, Göran Pershagen, Raphael Simon Peter, Annette Peters, Matteo Renzi, Debora Rizzuto, Sophia Rodopoulou, Evangelia Samoli, Per Everhard Schwarze, Gianluca Severi, Torben Sigsgaard, Massimo Stafoggia, Maciej Strak, Danielle Vienneau, Gudrun Weinmayr, Kathrin Wolf, Ole Raaschou-Nielsen. Long-term exposure to fine particle elemental components and lung cancer incidence in the ELAPSE pooled cohort. Environmental Research 2021, 193 , 110568. https://doi.org/10.1016/j.envres.2020.110568
  40. Jinlian Jin, Haiyan Zhou, Shulin Sun, Zhe Tian, Haibing Ren, Jinwu Feng. Supervised Learning Based Systemic Inflammatory Markers Enable Accurate Additional Surgery for pT1NxM0 Colorectal Cancer: A Comparative Analysis of Two Practical Prediction Models for Lymph Node Metastasis. Cancer Management and Research 2021, Volume 13 , 8967-8977. https://doi.org/10.2147/CMAR.S337516
  41. Jelle Vlaanderen, Kees de Hoogh, Gerard Hoek, Annette Peters, Nicole Probst-Hensch, Augustin Scalbert, Erik Melén, Cathryn Tonne, G. Ardine de Wit, Marc Chadeau-Hyam, Klea Katsouyanni, Tõnu Esko, Karin R. Jongsma, Roel Vermeulen. Developing the building blocks to elucidate the impact of the urban exposome on cardiometabolic-pulmonary disease. Environmental Epidemiology 2021, 5 (4) , e162. https://doi.org/10.1097/EE9.0000000000000162
  • Abstract

    Figure 1

    Figure 1. Regression slopes (shown in red) of predictors selected in SLR and relative variable importance (shown in blue) of the 15 most important predictors in RF.

    Figure 2

    Figure 2. Maps of PM2.5 components developed by our main SLR (two-step, step2) and RF (two-step, step1) models.

  • References

    ARTICLE SECTIONS
    Jump To

    This article references 40 other publications.

    1. 1
      Adar, S. D.; Filigrana, P. A.; Clements, N.; Peel, J. L. Ambient coarse particulate matter and human health: a systematic review and meta-analysis. Curr. Environ. Health Rep. 2014, 1, 258274,  DOI: 10.1007/s40572-014-0022-z
    2. 2
      Vodonos, A.; Awad, Y. A.; Schwartz, J. The concentration-response between long-term PM2.5 exposure and mortality; A meta-regression approach. Environ. Res. 2018, 166, 677689,  DOI: 10.1016/j.envres.2018.06.021
    3. 3
      Adams, K.; Greenbaum, D. S.; Shaikh, R.; van Erp, A. M.; Russell, A. G. Particulate matter components, sources, and health: Systematic approaches to testing effects. J. Air Waste Manage. Assoc. 2015, 65, 544558,  DOI: 10.1080/10962247.2014.1001884
    4. 4
      Badaloni, C.; Cesaroni, G.; Cerza, F.; Davoli, M.; Brunekreef, B.; Forastiere, F. Effects of long-term exposure to particulate matter and metal components on mortality in the Rome longitudinal study. Environ. Int. 2017, 109, 146154,  DOI: 10.1016/j.envint.2017.09.005
    5. 5
      Pennington, A. F.; Strickland, M. J.; Gass, K.; Klein, M.; Sarnat, S. E.; Tolbert, P. E.; Balachandran, S.; Chang, H. H.; Russell, A. G.; Mulholland, J. A.; Darrow, L. A. Source-Apportioned PM2.5 and Cardiorespiratory Emergency Department Visits: Accounting for Source Contribution Uncertainty. Epidemiology 2019, 30, 789798,  DOI: 10.1097/ede.0000000000001089
    6. 6
      Eeftens, M.; Tsai, M.-Y.; Ampe, C.; Anwander, B.; Beelen, R.; Bellander, T.; Cesaroni, G.; Cirach, M.; Cyrys, J.; de Hoogh, K.; De Nazelle, A.; de Vocht, F.; Declercq, C.; Dėdelė, A.; Eriksen, K.; Galassi, C.; Gražulevičienė, R.; Grivas, G.; Heinrich, J.; Hoffmann, B.; Iakovides, M.; Ineichen, A.; Katsouyanni, K.; Korek, M.; Krämer, U.; Kuhlbusch, T.; Lanki, T.; Madsen, C.; Meliefste, K.; Mölter, A.; Mosler, G.; Nieuwenhuijsen, M.; Oldenwening, M.; Pennanen, A.; Probst-Hensch, N.; Quass, U.; Raaschou-Nielsen, O.; Ranzi, A.; Stephanou, E.; Sugiri, D.; Udvardy, O.; Vaskövi, É.; Weinmayr, G.; Brunekreef, B.; Hoek, G. Spatial variation of PM2.5, PM10, PM2.5 absorbance and PMcoarse concentrations between and within 20 European study areas and the relationship with NO2—Results of the ESCAPE project. Atmos. Environ. 2012, 62, 303317,  DOI: 10.1016/j.atmosenv.2012.08.038
    7. 7
      Tsai, M.-Y.; Hoek, G.; Eeftens, M.; de Hoogh, K.; Beelen, R.; Beregszászi, T.; Cesaroni, G.; Cirach, M.; Cyrys, J.; De Nazelle, A.; de Vocht, F.; Ducret-Stich, R.; Eriksen, K.; Galassi, C.; Gražuleviciene, R.; Gražulevicius, T.; Grivas, G.; Gryparis, A.; Heinrich, J.; Hoffmann, B.; Iakovides, M.; Keuken, M.; Krämer, U.; Künzli, N.; Lanki, T.; Madsen, C.; Meliefste, K.; Merritt, A.-S.; Mölter, A.; Mosler, G.; Nieuwenhuijsen, M. J.; Pershagen, G.; Phuleria, H.; Quass, U.; Ranzi, A.; Schaffner, E.; Sokhi, R.; Stempfelet, M.; Stephanou, E.; Sugiri, D.; Taimisto, P.; Tewis, M.; Udvardy, O.; Wang, M.; Brunekreef, B. Spatial variation of PM elemental composition between and within 20 European study areas--Results of the ESCAPE project. Environ. Int. 2015, 84, 181192,  DOI: 10.1016/j.envint.2015.04.015
    8. 8
      de Hoogh, K.; Wang, M.; Adam, M.; Badaloni, C.; Beelen, R.; Birk, M.; Cesaroni, G.; Cirach, M.; Declercq, C.; Dėdelė, A.; Dons, E.; de Nazelle, A.; Eeftens, M.; Eriksen, K.; Eriksson, C.; Fischer, P.; Gražulevičienė, R.; Gryparis, A.; Hoffmann, B.; Jerrett, M.; Katsouyanni, K.; Iakovides, M.; Lanki, T.; Lindley, S.; Madsen, C.; Mölter, A.; Mosler, G.; Nádor, G.; Nieuwenhuijsen, M.; Pershagen, G.; Peters, A.; Phuleria, H.; Probst-Hensch, N.; Raaschou-Nielsen, O.; Quass, U.; Ranzi, A.; Stephanou, E.; Sugiri, D.; Schwarze, P.; Tsai, M.-Y.; Yli-Tuomi, T.; Varró, M. J.; Vienneau, D.; Weinmayr, G.; Brunekreef, B.; Hoek, G. Development of land use regression models for particle composition in twenty study areas in Europe. Environ. Sci. Technol. 2013, 47, 57785786,  DOI: 10.1021/es400156t
    9. 9
      Beelen, R.; Hoek, G.; Raaschou-Nielsen, O.; Stafoggia, M.; Andersen, Z. J.; Weinmayr, G.; Hoffmann, B.; Wolf, K.; Samoli, E.; Fischer, P. H.; Nieuwenhuijsen, M. J.; Xun, W. W.; Katsouyanni, K.; Dimakopoulou, K.; Marcon, A.; Vartiainen, E.; Lanki, T.; Yli-Tuomi, T.; Oftedal, B.; Schwarze, P. E.; Nafstad, P.; De Faire, U.; Pedersen, N. L.; Östenson, C.-G.; Fratiglioni, L.; Penell, J.; Korek, M.; Pershagen, G.; Eriksen, K. T.; Overvad, K.; Sørensen, M.; Eeftens, M.; Peeters, P. H.; Meliefste, K.; Wang, M.; Bueno-de-Mesquita, H. B.; Sugiri, D.; Krämer, U.; Heinrich, J.; de Hoogh, K.; Key, T.; Peters, A.; Hampel, R.; Concin, H.; Nagel, G.; Jaensch, A.; Ineichen, A.; Tsai, M.-Y.; Schaffner, E.; Probst-Hensch, N. M.; Schindler, C.; Ragettli, M. S.; Vilier, A.; Clavel-Chapelon, F.; Declercq, C.; Ricceri, F.; Sacerdote, C.; Galassi, C.; Migliore, E.; Ranzi, A.; Cesaroni, G.; Badaloni, C.; Forastiere, F.; Katsoulis, M.; Trichopoulou, A.; Keuken, M.; Jedynska, A.; Kooter, I. M.; Kukkonen, J.; Sokhi, R. S.; Vineis, P.; Brunekreef, B. Natural-cause mortality and long-term exposure to particle components: an analysis of 19 European cohorts within the multi-center ESCAPE project. Environ. Health Perspect. 2015, 123, 525533,  DOI: 10.1289/ehp.1408095
    10. 10
      Basagaña, X.; Rivera, M.; Aguilera, I.; Agis, D.; Bouso, L.; Elosua, R.; Foraster, M.; de Nazelle, A.; Nieuwenhuijsen, M.; Vila, J.; Künzli, N. Effect of the number of measurement sites on land use regression models in estimating local air pollution. Atmos. Environ. 2012, 54, 634642,  DOI: 10.1016/j.atmosenv.2012.01.064
    11. 11
      Wang, M.; Beelen, R.; Eeftens, M.; Meliefste, K.; Hoek, G.; Brunekreef, B. Systematic evaluation of land use regression models for NO2. Environ. Sci. Technol. 2012, 46, 44814489,  DOI: 10.1021/es204183v
    12. 12
      De Hoogh, K.; Chen, J.; Gulliver, J.; Hoffmann, B.; Hertel, O.; Ketzel, M.; Bauwelinck, M.; van Donkelaar, A.; Hvidtfeldt, U. A.; Katsouyanni, K.; Klompmaker, J.; Martin, R. V.; Samoli, E.; Schwartz, P. E.; Stafoggia, M.; Bellander, T.; Strak, M.; Wolf, K.; Vienneau, D.; Brunekreef, B.; Hoek, G. Spatial PM2.5, NO2, O3 and BC models for Western Europe—Evaluation of spatiotemporal stability. Environ. Int. 2018, 120, 8192,  DOI: 10.1016/j.envint.2018.07.036
    13. 13
      de Hoogh, K.; Gulliver, J.; van Donkelaar, A.; Martin, R. V.; Marshall, J. D.; Bechle, M. J.; Cesaroni, G.; Pradas, M. C.; Dedele, A.; Eeftens, M.; Forsberg, B.; Galassi, C.; Heinrich, J.; Hoffmann, B.; Jacquemin, B.; Katsouyanni, K.; Korek, M.; Künzli, N.; Lindley, S. J.; Lepeule, J.; Meleux, F.; de Nazelle, A.; Nieuwenhuijsen, M.; Nystad, W.; Raaschou-Nielsen, O.; Peters, A.; Peuch, V.-H.; Rouil, L.; Udvardy, O.; Slama, R.; Stempfelet, M.; Stephanou, E. G.; Tsai, M. Y.; Yli-Tuomi, T.; Weinmayr, G.; Brunekreef, B.; Vienneau, D.; Hoek, G. Development of West-European PM 2.5 and NO 2 land use regression models incorporating satellite-derived and chemical transport modelling data. Environ. Res. 2016, 151, 110,  DOI: 10.1016/j.envres.2016.07.005
    14. 14
      Brauer, M.; Hoek, G.; van Vliet, P.; Meliefste, K.; Fischer, P.; Gehring, U.; Heinrich, J.; Cyrys, J.; Bellander, T.; Lewne, M.; Brunekreef, B. Estimating long-term average particulate air pollution concentrations: application of traffic indicators and geographic information systems. Epidemiology 2003, 14, 228239,  DOI: 10.1097/01.ede.0000041910.49046.9b
    15. 15
      Henderson, S. B.; Beckerman, B.; Jerrett, M.; Brauer, M. Application of land use regression to estimate long-term concentrations of traffic-related nitrogen oxides and fine particulate matter. Environ. Sci. Technol. 2007, 41, 24222428,  DOI: 10.1021/es0606780
    16. 16
      Chen, J.; de Hoogh, K.; Gulliver, J.; Hoffmann, B.; Hertel, O.; Ketzel, M.; Bauwelinck, M.; van Donkelaar, A.; Hvidtfeldt, U. A.; Katsouyanni, K.; Janssen, N. A. H.; Martin, R. V.; Samoli, E.; Schwartz, P. E.; Stafoggia, M.; Bellander, T.; Strak, M.; Wolf, K.; Vienneau, D.; Vermeulen, R.; Brunekreef, B.; Hoek, G. A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide. Environ. Int. 2019, 130, 104934,  DOI: 10.1016/j.envint.2019.104934
    17. 17
      Kerckhoffs, J.; Hoek, G.; Portengen, L.; Brunekreef, B.; Vermeulen, R. C. H. Performance of Prediction Algorithms for Modeling Outdoor Air Pollution Spatial Surfaces. Environ. Sci. Technol. 2019, 53, 14131421,  DOI: 10.1021/acs.est.8b06038
    18. 18
      Meng, X.; Hand, J. L.; Schichtel, B. A.; Liu, Y. Space-time trends of PM2.5 constituents in the conterminous United States estimated by a machine learning approach, 2005-2015. Environ. Int. 2018, 121, 11371147,  DOI: 10.1016/j.envint.2018.10.029
    19. 19
      Hu, X.; Belle, J. H.; Meng, X.; Wildani, A.; Waller, L. A.; Strickland, M. J.; Liu, Y. Estimating PM2.5 Concentrations in the Conterminous United States Using the Random Forest Approach. Environ. Sci. Technol. 2017, 51, 69366944,  DOI: 10.1021/acs.est.7b01210
    20. 20
      Breiman, L. Random forests. Mach. Learn. 2001, 45, 532,  DOI: 10.1023/a:1010933404324
    21. 21
      Brokamp, C.; Jandarov, R.; Rao, M. B.; LeMasters, G.; Ryan, P. Exposure assessment models for elemental components of particulate matter in an urban environment: A comparison of regression and random forest approaches. Atmos. Environ. 2017, 151, 111,  DOI: 10.1016/j.atmosenv.2016.11.066
    22. 22
      Hoek, G.; Beelen, R.; De Hoogh, K.; Vienneau, D.; Gulliver, J.; Fischer, P.; Briggs, D. A review of land-use regression models to assess spatial variation of outdoor air pollution. Atmos. Environ. 2008, 42, 75617578,  DOI: 10.1016/j.atmosenv.2008.05.057
    23. 23
      Eeftens, M.; Beelen, R.; de Hoogh, K.; Bellander, T.; Cesaroni, G.; Cirach, M.; Declercq, C.; Dėdelė, A.; Dons, E.; de Nazelle, A.; Dimakopoulou, K.; Eriksen, K.; Falq, G.; Fischer, P.; Galassi, C.; Gražulevičienė, R.; Heinrich, J.; Hoffmann, B.; Jerrett, M.; Keidel, D.; Korek, M.; Lanki, T.; Lindley, S.; Madsen, C.; Mölter, A.; Nádor, G.; Nieuwenhuijsen, M.; Nonnemacher, M.; Pedeli, X.; Raaschou-Nielsen, O.; Patelarou, E.; Quass, U.; Ranzi, A.; Schindler, C.; Stempfelet, M.; Stephanou, E.; Sugiri, D.; Tsai, M.-Y.; Yli-Tuomi, T.; Varró, M. J.; Vienneau, D.; Klot, S. v.; Wolf, K.; Brunekreef, B.; Hoek, G. Development of Land Use Regression Models for PM2.5, PM2.5 Absorbance, PM10 and PMcoarse in 20 European Study Areas; Results of the ESCAPE Project. Environ. Sci. Technol. 2012, 46, 1119511205,  DOI: 10.1021/es301948k
    24. 24
      GEOSTAT (version 2.0.1). 2011, https://ec.europa.eu/eurostat/web/gisco/geodata/reference-data/population-distribution-demography/geostat (last accessed July 19, 2019).
    25. 25
      CGIAR-CSI. Srtm 90m Digital Elevation Data , 2013.
    26. 26
      CLC. 2012, https://land.copernicus.eu/pan-european/corine-land-cover/clc-2012 (last accessed July 19, 2019).
    27. 27
      van Donkelaar, A.; Martin, R. V.; Li, C.; Burnett, R. T. Regional Estimates of Chemical Composition of Fine Particulate Matter Using a Combined Geoscience-Statistical Method with Information from Satellites, Models, and Monitors. Environ. Sci. Technol. 2019, 53, 25952611,  DOI: 10.1021/acs.est.8b06392
    28. 28
      ECMWF. https://apps.ecmwf.int/datasets/data/macc-reanalysis/levtype=sfc/ (last accessed July 23, 2019).
    29. 29
      Inness, A.; Baier, F.; Benedetti, A.; Bouarar, I.; Chabrillat, S.; Clark, H.; Clerbaux, C.; Coheur, P.; Engelen, R. J.; Errera, Q.; Flemming, J.; George, M.; Granier, C.; Hadji-Lazaro, J.; Huijnen, V.; Hurtmans, D.; Jones, L.; Kaiser, J. W.; Kapsomenakis, J.; Lefever, K.; Leitão, J.; Razinger, M.; Richter, A.; Schultz, M. G.; Simmons, A. J.; Suttie, M.; Stein, O.; Thépaut, J.-N.; Thouret, V.; Vrekoussis, M.; Zerefos, C. The MACC reanalysis: an 8 yr data set of atmospheric composition. Atmos. Chem. Phys. 2013, 13, 40734109,  DOI: 10.5194/acp-13-4073-2013
    30. 31
      Liaw, A.; Wiener, M. Classification and regression by randomForest. R News 2002, 2, 1822
    31. 32
      Murray, N. L.; Holmes, H. A.; Liu, Y.; Chang, H. H. A Bayesian ensemble approach to combine PM2.5 estimates from statistical models using satellite imagery and numerical model simulation. Environ. Res. 2019, 178, 108601,  DOI: 10.1016/j.envres.2019.108601
    32. 33
      Wang, M.; Beelen, R.; Bellander, T.; Birk, M.; Cesaroni, G.; Cirach, M.; Cyrys, J.; de Hoogh, K.; Declercq, C.; Dimakopoulou, K.; Eeftens, M.; Eriksen, K. T.; Forastiere, F.; Galassi, C.; Grivas, G.; Heinrich, J.; Hoffmann, B.; Ineichen, A.; Korek, M.; Lanki, T.; Lindley, S.; Modig, L.; Mölter, A.; Nafstad, P.; Nieuwenhuijsen, M. J.; Nystad, W.; Olsson, D.; Raaschou-Nielsen, O.; Ragettli, M.; Ranzi, A.; Stempfelet, M.; Sugiri, D.; Tsai, M.-Y.; Udvardy, O.; Varró, M. J.; Vienneau, D.; Weinmayr, G.; Wolf, K.; Yli-Tuomi, T.; Hoek, G.; Brunekreef, B. Performance of multi-city land use regression models for nitrogen dioxide and fine particles. Environ. Health Perspect. 2014, 122, 843849,  DOI: 10.1289/ehp.1307271
    33. 34
      Vedal, S.; Campen, M. J.; McDonald, J. D.; Kaufman, J. D.; Larson, T. V.; Sampson, P. D.; Sheppard, L.; Simpson, C. D.; Szpiro, A. A. National Particle Component Toxicity (NPACT) Initiative Report on Cardiovascular Effects. Research Report 178. Health Effects Institute: Boston, MA, 2013.
    34. 35
      Belis, C. A.; Karagulian, F.; Larsen, B. R.; Hopke, P. K. Critical review and meta-analysis of ambient particulate matter source apportionment using receptor models in Europe. Atmos. Environ. 2013, 69, 94108,  DOI: 10.1016/j.atmosenv.2012.11.009
    35. 36
      Ito, K.; Johnson, S.; Kheirbek, I.; Clougherty, J.; Pezeshki, G.; Ross, Z.; Eisl, H.; Matte, T. D. Intraurban Variation of Fine Particle Elemental Concentrations in New York City. Environ. Sci. Technol. 2016, 50, 75177526,  DOI: 10.1021/acs.est.6b00599
    36. 37
      Tripathy, S.; Tunno, B. J.; Michanowicz, D. R.; Kinnee, E.; Shmool, J. L. C.; Gillooly, S.; Clougherty, J. E. Hybrid land use regression modeling for estimating spatio-temporal exposures to PM2.5, BC, and metal components across a metropolitan area of complex terrain and industrial sources. Sci. Total Environ. 2019, 673, 5463,  DOI: 10.1016/j.scitotenv.2019.03.453
    37. 38
      Zhang, J. J. Y.; Sun, L.; Barrett, O.; Bertazzon, S.; Underwood, F. E.; Johnson, M. Development of land-use regression models for metals associated with airborne particulate matter in a North American city. Atmos. Environ. 2015, 106, 165177,  DOI: 10.1016/j.atmosenv.2015.01.008
    38. 39
      Viana, M.; Kuhlbusch, T. A. J.; Querol, X.; Alastuey, A.; Harrison, R. M.; Hopke, P. K.; Winiwarter, W.; Vallius, M.; Szidat, S.; Prévôt, A. S. H.; Hueglin, C.; Bloemen, H.; Waåhlin, P.; Vecchi, R.; Miranda, A. I.; Kasper-Giebl, A.; Maenhaut, W.; Hitzenberger, R. Source apportionment of particulate matter in Europe: A review of methods and results. J. Aerosol Sci. 2008, 39, 827849,  DOI: 10.1016/j.jaerosci.2008.05.007
    39. 40
      Michanowicz, D. R.; Shmool, J. L. C.; Tunno, B. J.; Tripathy, S.; Gillooly, S.; Kinnee, E.; Clougherty, J. E. A hybrid land use regression/AERMOD model for predicting intra-urban variation in PM2.5. Atmos. Environ. 2016, 131, 307315,  DOI: 10.1016/j.atmosenv.2016.01.045
  • Supporting Information

    Supporting Information

    ARTICLE SECTIONS
    Jump To

    The Supporting Information is available free of charge at https://pubs.acs.org/doi/10.1021/acs.est.0c06595.

    • Overview of potential predictor variables; performance of PM2.5 composition models over Europe; truncation frequency for model predictions at random locations; correlation of predictions at monitoring sites; distribution of 416 ESCAPE monitoring sites; boxplots of annual mean concentrations for PM2.5 composition; scatter plots of the stacked predictions at five held-out sites versus measurements; within-area r2s and RMSEs of PM2.5 composition models; maps of PM2.5 components; and Pearson correlation between model predictions at random locations across ELAPSE countries (PDF)


    Terms & Conditions

    Most electronic Supporting Information files are available without a subscription to ACS Web Editions. Such files may be downloaded by article for research use (if there is a public use license linked to the relevant article, that license may permit other uses). Permission may be obtained from ACS for other uses through requests via the RightsLink permission system: http://pubs.acs.org/page/copyright/permissions.html.

Pair your accounts.

Export articles to Mendeley

Get article recommendations from ACS based on references in your Mendeley library.

Pair your accounts.

Export articles to Mendeley

Get article recommendations from ACS based on references in your Mendeley library.

You’ve supercharged your research process with ACS and Mendeley!

STEP 1:
Click to create an ACS ID

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

Please note: If you switch to a different device, you may be asked to login again with only your ACS ID.

MENDELEY PAIRING EXPIRED
Your Mendeley pairing has expired. Please reconnect