Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging

Research output: Contribution to journal › Journal article › Research › peer-review

Standard

Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging. / Di, Qian; Amini, Heresh; Shi, Liuhua; Kloog, Itai; Silvern, Rachel; Kelly, James; Sabath, M. Benjamin; Choirat, Christine; Koutrakis, Petros; Lyapustin, Alexei; Wang, Yujie; Mickley, Loretta J.; Schwartz, Joel.

In: Environmental Science and Technology, Vol. 54, No. 3, 2020, p. 1372-1384.

Research output: Contribution to journal › Journal article › Research › peer-review

Harvard

Di, Q, Amini, H, Shi, L, Kloog, I, Silvern, R, Kelly, J, Sabath, MB, Choirat, C, Koutrakis, P, Lyapustin, A, Wang, Y, Mickley, LJ & Schwartz, J 2020, 'Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging', Environmental Science and Technology, vol. 54, no. 3, pp. 1372-1384. https://doi.org/10.1021/acs.est.9b03358

APA

Di, Q., Amini, H., Shi, L., Kloog, I., Silvern, R., Kelly, J., Sabath, M. B., Choirat, C., Koutrakis, P., Lyapustin, A., Wang, Y., Mickley, L. J., & Schwartz, J. (2020). Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging. Environmental Science and Technology, 54(3), 1372-1384. https://doi.org/10.1021/acs.est.9b03358

Vancouver

Di Q, Amini H, Shi L, Kloog I, Silvern R, Kelly J et al. Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging. Environmental Science and Technology. 2020;54(3):1372-1384. https://doi.org/10.1021/acs.est.9b03358

Author

Di, Qian ; Amini, Heresh ; Shi, Liuhua ; Kloog, Itai ; Silvern, Rachel ; Kelly, James ; Sabath, M. Benjamin ; Choirat, Christine ; Koutrakis, Petros ; Lyapustin, Alexei ; Wang, Yujie ; Mickley, Loretta J. ; Schwartz, Joel. / Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging. In: Environmental Science and Technology. 2020 ; Vol. 54, No. 3. pp. 1372-1384.

Bibtex

@article{99232479dc2b43f2b46181031f5515ff,
title = "Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging",
abstract = "NO2 is a combustion byproduct that has been associated with multiple adverse health outcomes. To assess NO2 levels with high accuracy, we propose the use of an ensemble model to integrate multiple machine learning algorithms, including neural network, random forest, and gradient boosting, with a variety of predictor variables, including chemical transport models. This NO2 model covers the entire contiguous U.S. with daily predictions on 1-km-level grid cells from 2000 to 2016. The ensemble produced a cross-validated R2 of 0.788 overall, a spatial R2 of 0.844, and a temporal R2 of 0.729. The relationship between daily monitored and predicted NO2 is almost linear. We also estimated the associated monthly uncertainty level for the predictions and address-specific NO2 levels. This NO2 estimation has a very high spatiotemporal resolution and allows the examination of the health effects of NO2 in unmonitored areas. We found the highest NO2 levels along highways and in cities. We also observed that nationwide NO2 levels declined in early years and stagnated after 2007, in contrast to the trend at monitoring sites in urban areas, where the decline continued. Our research indicates that the integration of different predictor variables and fitting algorithms can achieve an improved air pollution modeling framework.",
author = "Qian Di and Heresh Amini and Liuhua Shi and Itai Kloog and Rachel Silvern and James Kelly and Sabath, {M. Benjamin} and Christine Choirat and Petros Koutrakis and Alexei Lyapustin and Yujie Wang and Mickley, {Loretta J.} and Joel Schwartz",
note = "Publisher Copyright: {\textcopyright} 2019 American Chemical Society.",
year = "2020",
doi = "10.1021/acs.est.9b03358",
language = "English",
volume = "54",
pages = "1372--1384",
journal = "Environmental Science & Technology",
issn = "0013-936X",
publisher = "American Chemical Society",
number = "3",

}

RIS

TY - JOUR

T1 - Assessing no2 concentration and model uncertainty with high spatiotemporal resolution across the contiguous united states using ensemble model averaging

AU - Di, Qian

AU - Amini, Heresh

AU - Shi, Liuhua

AU - Kloog, Itai

AU - Silvern, Rachel

AU - Kelly, James

AU - Sabath, M. Benjamin

AU - Choirat, Christine

AU - Koutrakis, Petros

AU - Lyapustin, Alexei

AU - Wang, Yujie

AU - Mickley, Loretta J.

AU - Schwartz, Joel

N1 - Publisher Copyright: © 2019 American Chemical Society.

PY - 2020

Y1 - 2020

N2 - NO2 is a combustion byproduct that has been associated with multiple adverse health outcomes. To assess NO2 levels with high accuracy, we propose the use of an ensemble model to integrate multiple machine learning algorithms, including neural network, random forest, and gradient boosting, with a variety of predictor variables, including chemical transport models. This NO2 model covers the entire contiguous U.S. with daily predictions on 1-km-level grid cells from 2000 to 2016. The ensemble produced a cross-validated R2 of 0.788 overall, a spatial R2 of 0.844, and a temporal R2 of 0.729. The relationship between daily monitored and predicted NO2 is almost linear. We also estimated the associated monthly uncertainty level for the predictions and address-specific NO2 levels. This NO2 estimation has a very high spatiotemporal resolution and allows the examination of the health effects of NO2 in unmonitored areas. We found the highest NO2 levels along highways and in cities. We also observed that nationwide NO2 levels declined in early years and stagnated after 2007, in contrast to the trend at monitoring sites in urban areas, where the decline continued. Our research indicates that the integration of different predictor variables and fitting algorithms can achieve an improved air pollution modeling framework.

AB - NO2 is a combustion byproduct that has been associated with multiple adverse health outcomes. To assess NO2 levels with high accuracy, we propose the use of an ensemble model to integrate multiple machine learning algorithms, including neural network, random forest, and gradient boosting, with a variety of predictor variables, including chemical transport models. This NO2 model covers the entire contiguous U.S. with daily predictions on 1-km-level grid cells from 2000 to 2016. The ensemble produced a cross-validated R2 of 0.788 overall, a spatial R2 of 0.844, and a temporal R2 of 0.729. The relationship between daily monitored and predicted NO2 is almost linear. We also estimated the associated monthly uncertainty level for the predictions and address-specific NO2 levels. This NO2 estimation has a very high spatiotemporal resolution and allows the examination of the health effects of NO2 in unmonitored areas. We found the highest NO2 levels along highways and in cities. We also observed that nationwide NO2 levels declined in early years and stagnated after 2007, in contrast to the trend at monitoring sites in urban areas, where the decline continued. Our research indicates that the integration of different predictor variables and fitting algorithms can achieve an improved air pollution modeling framework.

U2 - 10.1021/acs.est.9b03358

DO - 10.1021/acs.est.9b03358

M3 - Journal article

C2 - 31851499

AN - SCOPUS:85078716285

VL - 54

SP - 1372

EP - 1384

JO - Environmental Science & Technology

JF - Environmental Science & Technology

SN - 0013-936X

IS - 3

ER -

ID: 311200392