Using a land use regression model with machine learning to estimate ground level PM2.5

Pei-Yi Wong; Hsiao-Yun Lee; Yu-Cheng Chen; Yu-Ting Zeng; Yinq-Rong Chern; Nai-Tzu Chen; Shih-Chun Candice Lung; Huey-Jen Su; Chih-Da Wu

doi:10.1016/j.envpol.2021.116846

Using a land use regression model with machine learning to estimate ground level PM_2.5

Environ Pollut. 2021 May 15:277:116846. doi: 10.1016/j.envpol.2021.116846. Epub 2021 Mar 1.

Authors

Pei-Yi Wong¹, Hsiao-Yun Lee², Yu-Cheng Chen³, Yu-Ting Zeng⁴, Yinq-Rong Chern⁴, Nai-Tzu Chen⁵, Shih-Chun Candice Lung⁶, Huey-Jen Su¹, Chih-Da Wu⁷

Affiliations

¹ Department of Environmental and Occupational Health, National Cheng Kung University, Tainan, Taiwan.
² Department of Leisure Industry and Health Promotion, National Taipei University of Nursing and Health Sciences, Taipei, Taiwan.
³ National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan.
⁴ Department of Geomatics, National Cheng Kung University, Tainan, Taiwan.
⁵ Research Center of Environmental Trace Toxic Substances, National Cheng Kung University, Tainan, Taiwan.
⁶ Research Center for Environmental Changes, Academia Sinica, Taipei, Taiwan; Department of Atmospheric Sciences, National Taiwan University, Taipei, Taiwan; Institute of Environmental Health, National Taiwan University, Taipei, Taiwan.
⁷ National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan; Department of Geomatics, National Cheng Kung University, Tainan, Taiwan. Electronic address: chidawu@mail.ncku.edu.tw.

PMID: 33735646
DOI: 10.1016/j.envpol.2021.116846

Abstract

Ambient fine particulate matter (PM_2.5) has been ranked as the sixth leading risk factor globally for death and disability. Modelling methods based on having access to a limited number of monitor stations are required for capturing PM_2.5 spatial and temporal continuous variations with a sufficient resolution. This study utilized a land use regression (LUR) model with machine learning to assess the spatial-temporal variability of PM_2.5. Daily average PM_2.5 data was collected from 73 fixed air quality monitoring stations that belonged to the Taiwan EPA on the main island of Taiwan. Nearly 280,000 observations from 2006 to 2016 were used for the analysis. Several datasets were collected to determine spatial predictor variables, including the EPA environmental resources dataset, a meteorological dataset, a land-use inventory, a landmark dataset, a digital road network map, a digital terrain model, MODIS Normalized Difference Vegetation Index (NDVI) database, and a power plant distribution dataset. First, conventional LUR and Hybrid Kriging-LUR were utilized to identify the important predictor variables. Then, deep neural network, random forest, and XGBoost algorithms were used to fit the prediction model based on the variables selected by the LUR models. Data splitting, 10-fold cross validation, external data verification, and seasonal-based and county-based validation methods were used to verify the robustness of the developed models. The results demonstrated that the proposed conventional LUR and Hybrid Kriging-LUR models captured 58% and 89% of PM_2.5 variations, respectively. When XGBoost algorithm was incorporated, the explanatory power of the models increased to 73% and 94%, respectively. The Hybrid Kriging-LUR with XGBoost algorithm outperformed the other integrated methods. This study demonstrates the value of combining Hybrid Kriging-LUR model and an XGBoost algorithm for estimating the spatial-temporal variability of PM_2.5 exposures.

Keywords: Extreme gradient boosting; Land-use regression; Machine learning; PM(2.5); Variable selection.

MeSH terms

Air Pollutants* / analysis
Air Pollution* / analysis
Environmental Monitoring
Machine Learning
Particulate Matter / analysis
Taiwan

Substances

Air Pollutants
Particulate Matter