1
|
Hsu CY, Lee RQ, Wong PY, Candice Lung SC, Chen YC, Chen PC, Adamkiewicz G, Wu CD. Estimating morning and evening commute period O 3 concentration in Taiwan using a fine spatial-temporal resolution ensemble mixed spatial model with Geo-AI technology. JOURNAL OF ENVIRONMENTAL MANAGEMENT 2024; 351:119725. [PMID: 38064987 DOI: 10.1016/j.jenvman.2023.119725] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/01/2023] [Revised: 11/05/2023] [Accepted: 11/25/2023] [Indexed: 01/14/2024]
Abstract
Elevated levels of ground-level ozone (O3) can have harmful effects on health. While previous studies have focused mainly on daily averages and daytime patterns, it's crucial to consider the effects of air pollution during daily commutes, as this can significantly contribute to overall exposure. This study is also the first to employ an ensemble mixed spatial model (EMSM) that integrates multiple machine learning algorithms and predictor variables selected using Shapley Additive exExplanations (SHAP) values to predict spatial-temporal fluctuations in O3 concentrations across the entire island of Taiwan. We utilized geospatial-artificial intelligence (Geo-AI), incorporating kriging, land use regression (LUR), machine learning (random forest (RF), categorical boosting (CatBoost), gradient boosting (GBM), extreme gradient boosting (XGBoost), and light gradient boosting (LightGBM)), and ensemble learning techniques to develop ensemble mixed spatial models (EMSMs) for morning and evening commute periods. The EMSMs were used to estimate long-term spatiotemporal variations of O3 levels, accounting for in-situ measurements, meteorological factors, geospatial predictors, and social and seasonal influences over a 26-year period. Compared to conventional LUR-based approaches, the EMSMs improved performance by 58% for both commute periods, with high explanatory power and an adjusted R2 of 0.91. Internal and external validation procedures and verification of O3 concentrations at the upper percentile ranges (in 1%, 5%, 10%, 15%, 20%, and 25%) and other conditions (including rain, no rain, weekday, weekend, festival, and no festival) have demonstrated that the models are stable and free from overfitting issues. Estimation maps were generated to examine changes in O3 levels before and during the implementation of COVID-19 restrictions. These findings provide accurate variations of O3 levels in commute period with high spatiotemporal resolution of daily and 50m * 50m grid, which can support control pollution efforts and aid in epidemiological studies.
Collapse
Affiliation(s)
- Chin-Yu Hsu
- Department of Safety, Health and Environmental Engineering, Ming Chi University of Technology, New Taipei, Taiwan; Center for Environmental Sustainability and Human Health, Ming Chi University of Technology, New Taipei, Taiwan
| | - Ruei-Qin Lee
- Department of Geomatics, National Cheng Kung University, Tainan, Taiwan
| | - Pei-Yi Wong
- Department of Environmental and Occupational Health, National Cheng Kung University, Tainan, Taiwan
| | - Shih-Chun Candice Lung
- Research Center for Environmental Changes, Academia Sinica, Taipei, Taiwan; Department of Atmospheric Sciences, National Taiwan University, Taipei, Taiwan
| | - Yu-Cheng Chen
- National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan
| | - Pau-Chung Chen
- National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan; Institute of Environmental and Occupational Health Sciences, National Taiwan University College of Public Health, Taipei, Taiwan; Department of Public Health, National Taiwan University College of Public Health, Taipei, Taiwan; Department of Environmental and Occupational Medicine, National Taiwan University Hospital and National Taiwan University College of Medicine, Taipei, Taiwan
| | - Gary Adamkiewicz
- Department of Environmental Health, Harvard T.H. Chan School of Public Health, Boston, MA, USA
| | - Chih-Da Wu
- Department of Geomatics, National Cheng Kung University, Tainan, Taiwan; National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan; Innovation and Development Center of Sustainable Agriculture, National Chung Hsing University, Tainan, Taiwan.
| |
Collapse
|
2
|
Tudor C. Ozone pollution in London and Edinburgh: spatiotemporal characteristics, trends, transport and the impact of COVID-19 control measures. Heliyon 2022; 8:e11384. [PMID: 36397774 PMCID: PMC9650992 DOI: 10.1016/j.heliyon.2022.e11384] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/18/2022] [Revised: 09/21/2022] [Accepted: 10/28/2022] [Indexed: 11/13/2022] Open
Abstract
Air pollution remains the most serious environmental health issue in the United Kingdom while also carrying non-trivial economic costs. The COVID-19 lockdown periods reduced anthropogenic emissions and offered unique conditions for air pollution research. This study sources fine-granularity geo-spatial air quality and meteorological data for the capital cities of two UK countries (i.e. England's capital London and Scotland's capital Edinburgh) from the UK Automatic Urban and Rural Network (AURN) spanning 2016–2022 to assess long-term trends in several criteria pollutants (PM10, PM2.5, SO2, NO2, O3, and CO) and the changes in ozone pollution during the pandemic period. Unlike other studies conducted thus far, this research integrates several tools in trend estimation, including the Mann-Kendall test, the Theil-Sen estimator with bootstrap resampling, and the generalized additive model (GAM). Moreover, several investigations, including cluster trajectory analysis, pollution rose plots, and potential source contribution function (PSCF), are also employed to identify potential origin sources for air masses carrying precursors and estimate their contributions to ozone concentrations at receptor sites and downwind areas. The main findings reveal that most of the criteria pollutants show a decreasing trend in both geographies over the seven-year period, except for O3, which presents a significant ascending trend in London and a milder ascending trend in Edinburgh. However, O3 concentrations have significantly decreased during the year 2020 in both urban areas, despite registering sharp increases during the first lockdown period. In turn, these findings indicate on one hand that the O3 generation process is in the VOC-limited regime in both UK urban areas and, on the other hand, confirm previous findings that, when stretching the analysis period, diminishing ozone levels can lead to NOx reduction even in VOC-controlled geographies. Trajectory analysis reveals that northern Europe, particularly Norway and Sweden, is a principal ozone pollution source for Edinburgh, whereas, for London, mainland Europe (i.e., the Benelux countries) is another significant source. The results have important policy implications, revealing that effective and efficient NOx abatement measures spur ozone pollution in the short-term, but the increase can be transient. Moreover, policymakers in London and Edinburgh should consider that both local and transboundary sources contribute to local ozone pollution.
Collapse
|