Assessing the Spatiotemporal Characteristics, Factor Importance, and Health Impacts of Air Pollution in Seoul by Integrating Machine Learning into Land-Use Regression Modeling at High Spatiotemporal Resolutions.

Previous studies have characterized spatial patterns of air pollution with land-use regression (LUR) models. However, the spatiotemporal characteristics of air pollution, the contribution of various factors to them, and the resultant health impacts have yet to be evaluated comprehensively. This study integrates machine learning (random forest) into LUR modeling (LURF) with intensive evaluations to develop high spatiotemporal resolution prediction models to estimate daily and diurnal PM2.5 and NO2 in Seoul, South Korea, at the spatial resolution of 500 m for a year (2019) and to then evaluate the contribution of driving factors and quantify the resultant premature mortality. Our results show that incorporating the random forest algorithm into our LUR model improves the model performance. Meteorological conditions have a great influence on daily models, while land-use factors play important roles in diurnal models. Our health assessment using dynamic population data estimates that PM2.5 and NO2 pollution, when combined, causes a total of 11,183 (95% CI: 5837-16,354) premature mortalities in Seoul in 2019, of which 64.9% are due to PM2.5, while the remaining are attributable to NO2. The air pollution-attributable health impacts in Seoul are largely caused by cardiovascular diseases including stroke. This study pinpoints the significant spatiotemporal variations and health impact of PM2.5 and NO2 in Seoul, providing essential data for epidemiological research and air quality management.

[1]  Andy Hong,et al.  Clustering patterns of urban form factors related to particulate matter concentrations in Seoul, South Korea , 2022, Sustainable Cities and Society.

[2]  C. Akdis,et al.  World Health Organization global air quality guideline recommendations: Executive summary , 2021, Allergy.

[3]  W. Myung,et al.  Short-term air pollution exposure and exacerbation of psychosis: A case-crossover study in the capital city of South Korea , 2021, Atmospheric Environment.

[4]  Naomi Zimmerman,et al.  Spatial Modeling of Daily PM2.5, NO2, and CO Concentrations Measured by a Low-Cost Sensor Network: Comparison of Linear, Machine Learning, and Hybrid Land Use Models. , 2021, Environmental science & technology.

[5]  Zhiyuan Li,et al.  Development and intercity transferability of land-use regression models for predicting ambient PM10, PM2.5, NO2 and O3 concentrations in northern Taiwan , 2021, Atmospheric Chemistry and Physics.

[6]  S. Cho,et al.  Development of the Global to Mesoscale Air Quality Forecast and Analysis System (GMAF) and Its Application to PM2.5 Forecast in Korea , 2021, Atmosphere.

[7]  G. Viegi,et al.  Spatial-temporal prediction of ambient nitrogen dioxide and ozone levels over Italy using a Random Forest model for population exposure assessment , 2021, Air Quality, Atmosphere & Health.

[8]  Shuxiao Wang,et al.  Developing a statistical model to explain the observed decline of atmospheric mercury , 2020 .

[9]  Mazin A. M. Al Janabi,et al.  Leveraging random forest in micro‐enterprises credit risk modelling for accuracy and interpretability , 2020 .

[10]  Siyu Li,et al.  Multi-scale spatiotemporal graph convolution network for air quality prediction , 2020, Applied Intelligence.

[11]  Hyungkyoo Kim.  Land Use Impacts on Particulate Matter Levels in Seoul, South Korea: Comparing High and Low Seasons , 2020, Land.

[12]  Ivan Ivanov,et al.  Tenfold bootstrap procedure for Support Vector Machines , 2020, Comput. Sci..

[13]  Hwamin Lee,et al.  A Hybrid Deep Learning Model to Forecast Particulate Matter Concentration Levels in Seoul, South Korea , 2020, Atmosphere.

[14]  S. Yi,et al.  Long term trends of chemical constituents and source contributions of PM2.5 in Seoul. , 2020, Chemosphere.

[15]  Simon Marvin,et al.  Air pollution dispersal in high density urban areas: Research on the triadic relation of wind, air pollution, and urban form , 2020 .

[16]  G. Hoek,et al.  Land use regression models revealing spatiotemporal co-variation in NO2, NO, and O3 in the Netherlands , 2020 .

[17]  H. Kan,et al.  Application of land use regression to assess exposure and identify potential sources in PM2.5, BC, NO2 concentrations. , 2020, Atmospheric environment.

[18]  Daniel J. Nordman,et al.  Random Forest Prediction Intervals , 2020, The American Statistician.

[19]  R. Burnett,et al.  Exposure to ambient air pollution and the incidence of lung cancer and breast cancer in the Ontario Population Health and Environment Cohort , 2020, International journal of cancer.

[20]  Hyun Cheol Kim,et al.  Long-Range Transport Influence on Key Chemical Components of PM2.5 in the Seoul Metropolitan Area, South Korea, during the Years 2012–2016 , 2019 .

[21]  Chih-Da Wu,et al.  A hybrid kriging/land-use regression model with Asian culture-specific sources to assess NO2 spatial-temporal variations. , 2019, Environmental pollution.

[22]  Michael I. Miller,et al.  A comparison of random forest variable selection methods for classification prediction modeling , 2019, Expert Syst. Appl..

[23]  Matthew A. Shapiro,et al.  Air quality and acid deposition impacts of local emissions and transboundary air pollution in Japan and South Korea , 2019, Atmospheric Chemistry and Physics.

[24]  J. Schwartz,et al.  Predicting Fine-Scale Daily NO2 for 2005-2016 Incorporating OMI Satellite Data Across Switzerland. , 2019, Environmental science & technology.

[25]  Matthias Ketzel,et al.  A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide. , 2019, Environment international.

[26]  T. Eck,et al.  Analysis of long-range transboundary transport (LRTT) effect on Korean aerosol pollution during the KORUS-AQ campaign , 2019, Atmospheric Environment.

[27]  Ye Tian,et al.  Analysis of spatial and seasonal distributions of air pollutants by incorporating urban morphological characteristics , 2019, Comput. Environ. Urban Syst..

[28]  D. Henze,et al.  Impacts of local vs. trans-boundary emissions from different sectors on PM2.5 exposure in South Korea during the KORUS-AQ campaign , 2019, Atmospheric Environment.

[29]  X. Hou,et al.  Contribution of local emissions and transboundary air pollution to air quality in Hong Kong during El Niño-Southern Oscillation and heatwaves , 2019, Atmospheric Research.

[30]  Chris C. Lim,et al.  Advancing environmental exposure assessment science to benefit society , 2019, Nature Communications.

[31]  G. Dong,et al.  Impacts of transboundary air pollution and local emissions on PM2.5 pollution in the Pearl River Delta region of China and the public health, and the policy implications , 2019, Environmental Research Letters.

[32]  Michael Brauer,et al.  Local variation of PM2.5 and NO2 concentrations within metropolitan Beijing , 2019, Atmospheric Environment.

[33]  Congcong Wen,et al.  A novel spatiotemporal convolutional long short-term neural network for air pollution prediction. , 2019, The Science of the total environment.

[34]  Ji-Ho Park,et al.  Regional characteristics of NO2 column densities from Pandora observations during the MAPS-Seoul campaign. , 2018, Aerosol and air quality research.

[35]  S. Deguen,et al.  Premature Adult Death and Equity Impact of a Reduction of NO2, PM10, and PM2.5 Levels in Paris—A Health Impact Assessment Study Conducted at the Census Block Level , 2018, International journal of environmental research and public health.

[36]  Y. Lim,et al.  Air quality management policy and reduced mortality rates in Seoul Metropolitan Area: A quasi-experimental study. , 2018, Environment international.

[37]  M. Shima,et al.  Spatiotemporal land use random forest model for estimating metropolitan NO2 exposure in Japan. , 2018, The Science of the total environment.

[38]  K F Ho,et al.  Impacts of sectoral emissions in China and the implications: air quality, public health, crop production, and economic costs , 2018, Environmental Research Letters.

[39]  J. Heo,et al.  Source apportionment of PM10 and PM2.5 air pollution, and possible impacts of study characteristics in South Korea. , 2018, Environmental pollution.

[40]  Y. Lim,et al.  Spatial and Temporal Trends of Number of Deaths Attributable to Ambient PM2.5 in the Korea , 2018, Journal of Korean medical science.

[41]  Sun Kyoung Park.  Assessing the impact of air pollution on mortality rate from cardiovascular disease in Seoul, Korea , 2018 .

[42]  Ming Luo,et al.  Trans-boundary air pollution in a city under various atmospheric conditions. , 2018, The Science of the total environment.

[43]  Hyun Cheol Kim,et al.  Regional contributions to particulate matter concentration in the Seoul metropolitan area, South Korea: seasonal variation and sensitivity to meteorology and emissions inventory , 2017 .

[44]  Hyungkyoo Kim,et al.  The Seasonal and Diurnal Influence of Surrounding Land Use on Temperature: Findings from Seoul, South Korea , 2017 .

[45]  Shih-Chun Candice Lung,et al.  Land-use regression with long-term satellite-based greenness index and culture-specific sources to model PM2.5 spatial-temporal variability. , 2017, Environmental pollution.

[46]  Jhoon Kim,et al.  Assessing the effect of long-range pollutant transportation on air quality in Seoul using the conditional potential source contribution function method , 2017 .

[47]  C. Shim,et al.  PM2.5 source attribution for Seoul in May from 2009 to 2013 using GEOS-Chem and its adjoint model. , 2017, Environmental pollution.

[48]  G. Lemasters,et al.  Exposure assessment models for elemental components of particulate matter in an urban environment: A comparison of regression and random forest approaches. , 2017, Atmospheric environment.

[49]  S. Yim,et al.  The air quality and health impacts of domestic trans-boundary pollution in various regions of China. , 2016, Environment international.

[50]  Marloes Eeftens,et al.  Development of land use regression models for nitrogen dioxide, ultrafine particles, lung deposited surface area, and four other markers of particulate matter pollution in the Swiss SAPALDIA regions , 2016, Environmental Health.

[51]  A. Cohen,et al.  A class of non-linear exposure-response models suitable for health impact assessment applicable to large cohort studies of ambient air pollution , 2016, Air Quality, Atmosphere & Health.

[52]  Michael Brauer,et al.  Risk estimates of mortality attributed to low concentrations of ambient fine particulate matter in the Canadian community health survey cohort , 2016, Environmental Health.

[53]  J. D. Whyatt,et al.  Evaluation of the performance of different atmospheric chemical transport models and inter-comparison of nitrogen and sulphur deposition estimates for the UK , 2015 .

[54]  Eun-Hye Yoo,et al.  Geospatial Estimation of Individual Exposure to Air Pollutants: Moving from Static Monitoring to Activity-Based Dynamic Exposure Assessment , 2015 .

[55]  Yuhong Yang,et al.  Cross-validation for selecting a model selection procedure , 2015 .

[56]  Zhengqiang Li,et al.  Remote sensing of atmospheric fine particulate matter (PM2.5) mass concentration near the ground from satellite observation , 2015 .

[57]  Jean-Michel Guldmann,et al.  Land-use regression panel models of NO2 concentrations in Seoul, Korea , 2015 .

[58]  Ki‐Hyun Kim,et al.  Long-term trend of NO2 in major urban areas of Korea and possible consequences for health , 2015 .

[59]  Bin Zou,et al.  Performance comparison of LUR and OK in PM2.5 concentration mapping: a multidimensional perspective , 2015, Scientific Reports.

[60]  J. Leem,et al.  Public-health impact of outdoor air pollution for 2nd air pollution management policy in Seoul metropolitan area, Korea , 2015, Annals of Occupational and Environmental Medicine.

[61]  Yan Zhang,et al.  A land use regression model for estimating the NO2 concentration in Shanghai, China. , 2015, Environmental research.

[62]  Y. Lim,et al.  Spatial analysis of PM10 and cardiovascular mortality in the Seoul metropolitan area , 2014, Environmental health and toxicology.

[63]  Michael Brauer,et al.  An Integrated Risk Function for Estimating the Global Burden of Disease Attributable to Ambient Fine Particulate Matter Exposure , 2014, Environmental health perspectives.

[64]  Bert Brunekreef,et al.  Development of NO2 and NOx land use regression models for estimating air pollution exposure in 36 study areas in Europe - The ESCAPE project , 2013 .

[65]  Luc Int Panis,et al.  Health impact assessment of air pollution using a dynamic exposure profile: Implications for exposure and health impact estimates , 2012 .

[66]  Jean-Michel Guldmann,et al.  Impact of traffic flows and wind directions on air pollution concentrations in Seoul, Korea , 2011 .

[67]  Ki-Hyun Kim,et al.  Impact of emission control strategy on NO2 in urban areas of Korea , 2011 .

[68]  Michael Charles Sawada,et al.  The role of spatial representation in the development of a LUR model for Ottawa, Canada , 2010, Air Quality, Atmosphere & Health.

[69]  Daniel J. Jacob,et al.  Correlations between fine particulate matter (PM2.5) and meteorological variables in the United States: implications for the sensitivity of PM2.5 to climate change. , 2010 .

[70]  Soon-Chang Yoon,et al.  Ground-based remote sensing measurements of aerosol and ozone in an urban area: A case study of mixing height evolution and its effect on ground-level ozone concentrations , 2007 .

[71]  Michael Brauer,et al.  Application of land use regression to estimate long-term concentrations of traffic-related nitrogen oxides and fine particulate matter. , 2007, Environmental science & technology.

[72]  Dimitrios Melas,et al.  Development and Assessment of Neural Network and Multiple Regression Models in Order to Predict PM10 Levels in a Medium-sized Mediterranean City , 2007 .

[73]  Y. J. Kim,et al.  Source contributions to fine particulate matter in an urban atmosphere. , 2005, Chemosphere.

[74]  Altaf Arain,et al.  A review and evaluation of intraurban air pollution exposure models , 2005, Journal of Exposure Analysis and Environmental Epidemiology.

[75]  D. Christiani,et al.  PM(10) exposure, gaseous pollutants, and daily mortality in Inchon, South Korea. , 1999, Environmental health perspectives.