Estimating monthly NO2, O3, and SO2 concentrations via an ensemble three-stage procedure with downscaled satellite remote sensing data and ground measurements

Chu-Chih Chen; Yin-Ru Wang; Fu-Cheng Wang; Yi-Shiang Shiu; Chang-Fu Wu; Tang-Huang Lin

doi:10.1016/j.jhazmat.2024.136392

Estimating monthly NO₂, O₃, and SO₂ concentrations via an ensemble three-stage procedure with downscaled satellite remote sensing data and ground measurements

J Hazard Mater. 2024 Nov 2:480:136392. doi: 10.1016/j.jhazmat.2024.136392. Online ahead of print.

Authors

Chu-Chih Chen¹, Yin-Ru Wang², Fu-Cheng Wang³, Yi-Shiang Shiu⁴, Chang-Fu Wu⁵, Tang-Huang Lin⁶

Affiliations

¹ Institute of Population Health Sciences, National Health Research Institutes, Taiwan; Research Center for Precision Environmental Medicine, Kaohsiung Medical University, Taiwan. Electronic address: ccchen@nhri.edu.tw.
² Institute of Population Health Sciences, National Health Research Institutes, Taiwan.
³ Center for Space and Remote Sensing Research, National Central University.
⁴ Department of Urban Planning and Spatial Information, Feng Chia University, Taiwan.
⁵ Institute of Environmental and Occupational Health Sciences, School of Public Health, National Taiwan University, Taiwan; Department of Public Health, School of Public Health, National Taiwan University, Taiwan.
⁶ Center for Space and Remote Sensing Research, National Central University. Electronic address: thlin@csrsr.ncu.edu.tw.

PMID: 39515140
DOI: 10.1016/j.jhazmat.2024.136392

Abstract

The gaseous air pollutants nitrogen dioxide (NO₂), ozone (O₃), and sulfur dioxide (SO₂), in addition to particulate matter (PM_2.5), are known to be associated with many adverse health effects. However, exposure estimates may not be available in rural or mountainous areas without monitoring stations. In this study, we retrieved satellite remote sensing data for NO₂, O₃, and SO₂ from the Ozone Monitoring Instrument (OMI) L3 products. Together with ground measurements (air monitoring stations and meteorological and land use data), we estimated the monthly NO₂, O₃, and SO₂ concentrations with a spatial resolution of 3×3 km across Taiwan from 2005 to 2019. A three-stage estimation procedure was utilized: in Stage 1, an ensemble generalized additive model (GAM) and machine learning method were used to determine the spatiotemporal variations; in Stage 2, the remote sensing data were downscaled; and in Stage 3, the downscaled concentrations were reused in the Stage 1 procedure for fine-tuning estimations. We obtained overall leave-one-out cross-validation (LOOCV) R² values ranging from 0.927-0.950, 0.704-0.721, and 0.601-0.716, and root-mean-square-errors (RMSEs) ranging from 1.59-2.28, 3.81-4.18, and 0.67-1.32 ppb for NO₂, O₃, and SO₂, respectively, via the random forest procedure. The annual NO₂ and SO₂ concentrations greatly improved from 2005-2019, especially in the western residential area of Taiwan. However, despite these improvements in air quality, the annual O₃ concentrations tended to increase from 2015-2019. This might be due to the complex mixtures of precursors (e.g., NO₂), atmospheric circulation, barriers of the Central Mountain Ridge, and increasing ground temperatures over the past decade. The proposed multistage estimation procedure performed well over the whole island with complex terrain and topography. The study outcomes may provide epidemiological information for long-term ambient exposure estimates and guidance for future administrative policies.

Keywords: Cross-validation; Downscaling; Generalized additive model; Machine learning; OMI L3.