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

TY - JOUR

T1 - National Empirical Models of Air Pollution Using Microscale Measures of the Urban Environment

AU - Lu, Tianjun

AU - Marshall, Julian D.

AU - Zhang, Wenwen

AU - Hystad, Perry

AU - Kim, Sun Young

AU - Bechle, Matthew J.

AU - Demuzere, Matthias

AU - Hankey, Steve

N1 - Funding Information: This publication was developed as part of the Center for Clean Air Climate Solutions (CACES), which was supported under Assistance Agreement No. R835873 awarded by the U.S. Environmental Protection Agency (EPA). It has not been formally reviewed by the EPA. The views expressed in this document are solely those of the authors and do not necessarily reflect those of the Agency. EPA does not endorse any products or commercial services mentioned in this publication. M.D. is supported by the ENLIGHT project, funded by the German Research Foundation (DFG) under Grant No. 437467569. We thank Dr. A. A. Szpiro from the University of Washington for valuable comments on the model development. We also thank M. Qi from Virginia Tech for providing the Google Street View imagery variables of Blacksburg, Virginia. Publisher Copyright: © 2021 American Chemical Society.

PY - 2021/11/16

Y1 - 2021/11/16

N2 - National-scale empirical models of air pollution (e.g., Land Use Regression) rely on predictor variables (e.g., population density, land cover) at different geographic scales. These models typically lack microscale variables (e.g., street level), which may improve prediction with fine-spatial gradients. We developed microscale variables of the urban environment including Point of Interest (POI) data, Google Street View (GSV) imagery, and satellite-based measures of urban form. We developed United States national models for six criteria pollutants (NO2, PM2.5, O3, CO, PM10, SO2) using various modeling approaches: Stepwise Regression + kriging (SW-K), Partial Least Squares + kriging (PLS-K), and Machine Learning + kriging (ML-K). We compared predictor variables (e.g., traditional vs microscale) and emerging modeling approaches (ML-K) to well-established approaches (i.e., traditional variables in a PLS-K or SW-K framework). We found that combined predictor variables (traditional + microscale) in the ML-K models outperformed the well-established approaches (10-fold spatial cross-validation (CV) R2 increased 0.02-0.42 [average: 0.19] among six criteria pollutants). Comparing all model types using microscale variables to models with traditional variables, the performance is similar (average difference of 10-fold spatial CV R2 = 0.05) suggesting microscale variables are a suitable substitute for traditional variables. ML-K and microscale variables show promise for improving national empirical models.

AB - National-scale empirical models of air pollution (e.g., Land Use Regression) rely on predictor variables (e.g., population density, land cover) at different geographic scales. These models typically lack microscale variables (e.g., street level), which may improve prediction with fine-spatial gradients. We developed microscale variables of the urban environment including Point of Interest (POI) data, Google Street View (GSV) imagery, and satellite-based measures of urban form. We developed United States national models for six criteria pollutants (NO2, PM2.5, O3, CO, PM10, SO2) using various modeling approaches: Stepwise Regression + kriging (SW-K), Partial Least Squares + kriging (PLS-K), and Machine Learning + kriging (ML-K). We compared predictor variables (e.g., traditional vs microscale) and emerging modeling approaches (ML-K) to well-established approaches (i.e., traditional variables in a PLS-K or SW-K framework). We found that combined predictor variables (traditional + microscale) in the ML-K models outperformed the well-established approaches (10-fold spatial cross-validation (CV) R2 increased 0.02-0.42 [average: 0.19] among six criteria pollutants). Comparing all model types using microscale variables to models with traditional variables, the performance is similar (average difference of 10-fold spatial CV R2 = 0.05) suggesting microscale variables are a suitable substitute for traditional variables. ML-K and microscale variables show promise for improving national empirical models.

KW - Empirical models

KW - exposure assessment

KW - machine learning

KW - street-level features

KW - urban form

UR - http://www.scopus.com/inward/record.url?scp=85119082451&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85119082451&partnerID=8YFLogxK

U2 - https://doi.org/10.1021/acs.est.1c04047

DO - https://doi.org/10.1021/acs.est.1c04047

M3 - Article

C2 - 34739226

SN - 0013-936X

VL - 55

SP - 15519

EP - 15530

JO - ES and T Contents

JF - ES and T Contents

IS - 22

ER -