An Ensemble Learning Approach for Estimating High Spatiotemporal Resolution of Ground-Level Ozone in the Contiguous United States
Research output: Contribution to journal › Journal article › Research › peer-review
Standard
An Ensemble Learning Approach for Estimating High Spatiotemporal Resolution of Ground-Level Ozone in the Contiguous United States. / Requia, Weeberb J.; Di, Qian; Silvern, Rachel; Kelly, James T.; Koutrakis, Petros; Mickley, Loretta J.; Sulprizio, Melissa P.; Amini, Heresh; Shi, Liuhua; Schwartz, Joel.
In: Environmental Science & Technology, Vol. 54, No. 18, 2020, p. 11037-11047.Research output: Contribution to journal › Journal article › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - JOUR
T1 - An Ensemble Learning Approach for Estimating High Spatiotemporal Resolution of Ground-Level Ozone in the Contiguous United States
AU - Requia, Weeberb J.
AU - Di, Qian
AU - Silvern, Rachel
AU - Kelly, James T.
AU - Koutrakis, Petros
AU - Mickley, Loretta J.
AU - Sulprizio, Melissa P.
AU - Amini, Heresh
AU - Shi, Liuhua
AU - Schwartz, Joel
PY - 2020
Y1 - 2020
N2 - In this paper, we integrated multiple types of predictor variables and three types of machine learners (neural network, random forest, and gradient boosting) into a geographically weighted ensemble model to estimate the daily maximum 8 h O3 with high resolution over both space (at 1 km × 1 km grid cells covering the contiguous United States) and time (daily estimates between 2000 and 2016). We further quantify monthly model uncertainty for our 1 km × 1 km gridded domain. The results demonstrate high overall model performance with an average cross-validated R2 (coefficient of determination) against observations of 0.90 and 0.86 for annual averages. Overall, the model performance of the three machine learning algorithms was quite similar. The overall model performance from the ensemble model outperformed those from any single algorithm. The East North Central region of the United States had the highest R2, 0.93, and performance was weakest for the western mountainous regions (R2 of 0.86) and New England (R2 of 0.87). For the cross validation by season, our model had the best performance during summer with an R2 of 0.88. This study can be useful for the environmental health community to more accurately estimate the health impacts of O3 over space and time, especially in health studies at an intra-urban scale.
AB - In this paper, we integrated multiple types of predictor variables and three types of machine learners (neural network, random forest, and gradient boosting) into a geographically weighted ensemble model to estimate the daily maximum 8 h O3 with high resolution over both space (at 1 km × 1 km grid cells covering the contiguous United States) and time (daily estimates between 2000 and 2016). We further quantify monthly model uncertainty for our 1 km × 1 km gridded domain. The results demonstrate high overall model performance with an average cross-validated R2 (coefficient of determination) against observations of 0.90 and 0.86 for annual averages. Overall, the model performance of the three machine learning algorithms was quite similar. The overall model performance from the ensemble model outperformed those from any single algorithm. The East North Central region of the United States had the highest R2, 0.93, and performance was weakest for the western mountainous regions (R2 of 0.86) and New England (R2 of 0.87). For the cross validation by season, our model had the best performance during summer with an R2 of 0.88. This study can be useful for the environmental health community to more accurately estimate the health impacts of O3 over space and time, especially in health studies at an intra-urban scale.
U2 - 10.1021/acs.est.0c01791
DO - 10.1021/acs.est.0c01791
M3 - Journal article
C2 - 32808786
AN - SCOPUS:85091125941
VL - 54
SP - 11037
EP - 11047
JO - Environmental Science & Technology
JF - Environmental Science & Technology
SN - 0013-936X
IS - 18
ER -
ID: 249764343