Abstract
This study used four individual machine learning (ML) models (random forest, adaptive boosting, gradient boosting, and extreme gradient boosting), and a stacked ensemble model (SEM) for PM2.5 estimation over Greater Bangkok (GBK) during the dry season for 2018–2022. Aerosol optical depth (AOD) from Fengyun-4A satellite was used as the main predictor variable. The other predictor variables include meteorological variables, fire hotspots, vegetation index, terrain elevation, and population density. Surface PM2.5 from 17 air quality monitoring stations was used for model development and evaluation. Satellite AOD aligns reasonably well with AOD from two AERONET stations in the study area in terms of correlation coefficient (r), mean bias (MB), mean error (ME), and root mean square error (RMSE). Among the individual models, adaptive boosting performed the best with r = 0.75, MB = 0.55 µg m−3, ME = 9.1 µg m−3, and RMSE = 12.9 µg m−3. As for SEM which comprises all individual models, it outperformed every individual model, with r = 0.84, zero MB, ME = 7.2 µg m−3, and RMSE = 10.4 µg m−3. In two additional cases of haze hours and clean hours, SEM is best overall while adaptive boosting is superior to the other individual ML models. The case of haze hours has lower model predictability, suggesting elevated PM2.5 is difficult to predict. SEM was thus chosen to map PM2.5 as well as exposure intensity over GBK. Good agreement between the observed and predicted diurnal and monthly patterns is achieved by every model. PM2.5 tends to be relatively high at 08–10 LT and declines in later hours, corresponding to higher traffic emissions in the morning and daytime meteorological conditions more favorable to dilute air pollutants, respectively. PM2.5 intensifies in the winter but decreases in March and April. During these two months, the areas outside Bangkok tend to have higher PM2.5 than within Bangkok, possibly linked to active summertime biomass burning in those areas that are less urbanized with more agricultural lands. Relatively high exposure intensity is constrained to Bangkok due likely to its much denser population. The findings indicate a significant potential for leveraging the Fengyun-4A satellite data and ML to advance space-based air quality monitoring for Thailand and other data-scare regions in Southeast Asia. A satellite-based PM2.5 dataset could support the formulation of effective air quality management strategies in GBK.
Similar content being viewed by others
Data availability
The data used in the study are available upon request, some of which may be subject to copyright.
References
Aman N, Manomaiphiboon K, Pengchai P, Suwanathada P, Srichawana J, Assareh N (2019) Long-term observed visibility in eastern Thailand: temporal variation, association with air pollutants and weather factors, and trends. Atmosphere 10:122. https://doi.org/10.3390/atmos10030122
Aman N, Manomaiphiboon K, Pala-En N, Kokkaew E, Boonyoo T, Pattaramunikul S, Devkota B, Chotamonsak C (2020) Evolution of urban haze in Greater Bangkok and association with local weather and synoptic characteristics during two recent haze episodes. Int J Environ Res Public Health 17:9499. https://doi.org/10.3390/ijerph17249499
Aman N, Manomaiphiboon K, Suwattiga P, Assareh N, Limpaseni W, Suwanathada P, Soonsin V, Wang Y (2022) Visibility, aerosol optical depth, and low-visibility events in Bangkok during the dry season and associated local weather and synoptic patterns. Environ Monit Assess 194:322. https://doi.org/10.1007/s10661-022-09880-2
Aman N, Manomaiphiboon K, Pala-En N, Devkota B, Inerb M, Kokkaew E (2023) A study of urban haze and its association with cold surge and sea breeze for Greater Bangkok. Int J Environ Res Public Health 20:3482. https://doi.org/10.3390/ijerph20043482
Amnuaylojaroen T, Parasin N, Limsakul A (2022) Health risk assessment of exposure near-future PM2.5 in Northern Thailand. Air Qual Atmos Health 15:1963–1979. https://doi.org/10.1007/s11869-022-01231-x
Ångström A (1929) On the atmospheric transmission of sun radiation and on dust in the air. Geogr Ann 11:156–166. https://doi.org/10.1080/20014422.1929.11880498
Breiman L (2001) Random forests. Mach Learn 45:5–32. https://doi.org/10.1023/A:1010933404324
Cai J (2016) An R package for calculating water vapor measures from temperature and relative humidity. R package version 0.1.1. Available at: https://github.com/caijun/humidity. Accessed 1 Oct 2023
Chalermpong S, Thaithatkul P, Anuchitchanchai O, Sanghatawatana P (2021) Land use regression modeling for fine particulate matters in Bangkok, Thailand, using time-variant predictors: effects of seasonal factors, open biomass burning, and traffic-related factors. Atmos Environ 246:118128. https://doi.org/10.1016/j.atmosenv.2020.118128
Chen T, Guestrin C (2016) XGBoost: a scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on knowledge discovery and data mining—KDD ’16, San Francisco, CA, USA, pp 785–794. https://doi.org/10.1145/2939672.2939785
ChooChuay C, Pongpiachan S, Tipmanee D, Suttinun O, Deelaman W, Wang Q, Li X, Li G, Han Y, Palakun J, Cao J (2020) Impacts of PM2.5 sources on variations in particulate chemical compounds in ambient air of Bangkok. Thailand Atmos Pollut Res 11:1657–1667. https://doi.org/10.1016/j.apr.2020.06.030
Department of Provincial Administration (DOPA) (2023) Statistic of population by province in 2022. (In Thai). https://stat.bora.dopa.go.th/new_stat/webPage/statByYear.php (accessed on 28 September 2023)
Didan K (2021) MODIS/Terra vegetation indices 16-day L3 global 500m SIN grid V061. Distributed by NASA EOSDIS Land Processes DAAC. https://doi.org/10.5067/MODIS/MOD13A1.061. Accessed 5 Oct 2023
Fathollahi L, Wu F, Maleki R, Pongracic B (2023) PM2.5 concentrations estimation using machine learning methods with combination of MAIAC - MODIS AOD product - a case study in western Iran. Air Qual Atmos Health 16:1529–1541. https://doi.org/10.1007/s11869-023-01354-9
Freund Y, Schapire RE (1999) A short introduction to boosting. J Japan Soc Artif Intell 14:771–780
Friedman JH (2001) Greedy function approximation: a gradient boosting machine. Ann Stat 29:1189–1232
Gao L, Chen L, Li J, Li C, Zhu L (2021) An improved dark target method for aerosol optical depth retrieval over China from Himawari-8. Atmos Environ 250:105399. https://doi.org/10.1016/j.atmosres.2020.105399
Giglio L, Schroeder W, Justice CO (2016) The collection 6 MODIS active fire detection algorithm and fire products. Remote Sens Environ 178:31–41. https://doi.org/10.1016/j.rse.2016.02.054
Gupta P, Christopher SA (2009) Particulate matter air quality assessment using integrated surface, satellite, and weather products: multiple regression approach. J Geophys Res Atmos 114:D14205. https://doi.org/10.1029/2008JD011496
Gupta P, Zhan S, Mishra V, Aekakkararungroj A, Markert A, Paibong S, Chishtie F (2021) Machine learning algorithm for estimating surface PM2.5 in Thailand. Aerosol Air Qual Res 21:210105. https://doi.org/10.4209/aaqr.210105
Han S, Kundhikanjana W, Towashiraporn P, Stratoulias D (2022) Interpolation-based fusion of sentinel-5P, SRTM, and regulatory-grade ground stations data for producing spatially continuous maps of PM2.5 concentrations nationwide over Thailand. Atmosphere 13:161. https://doi.org/10.3390/atmos13020161
Handschuh J, Erbertseder T, Baier F (2023) Systematic evaluation of four satellite AOD datasets for estimating PM2.5 using a random forest approach. Remote Sens 15:2064. https://doi.org/10.3390/rs15082064
Holben BN, Eck TF, Slutsker I, Tanré D, Buis JP, Setzer A, Vermote E, Reagan JA, Kaufman YA, Nakajima T, Lavenu F, Jankowiak I, Smirnov A (1998) AERONET-a federated instrument network and data achieve for aerosol characterization. Remote Sens Environ 66:1–16. https://doi.org/10.1016/S0034-4257(98)00031-5
Hu X, Waller LA, Lyapustin A, Wang Y, Liu Y (2014) Improving satellite-driven PM2.5 models with moderate resolution imaging spectroradiometer fire counts in the southeastern U.S. J Geophys Res Atmos 119:11375–11386. https://doi.org/10.1002/2014JD021920
Hu X, Belle JH, Meng X, Wildani A, Waller LA, Strickland MJ, Liu Y (2017) Estimating PM2.5 concentrations in the conterminous United States using the random forest approach. Environ Sci Technol 51:6936–6944. https://doi.org/10.1021/acs.est.7b01210
Hu Y, Zeng C, Li T, Shen H (2022) Performance comparison of Fengyun-4A and Himawari-8 in PM2.5 estimation in China. Atmos Environ 271:118898. https://doi.org/10.1016/j.atmosenv.2021.118898
Jiang T, Chen B, Chan KKY, Xu B (2019) Himawari-8/AHI and MODIS aerosol optical depths in China: evaluation and comparison. Remote Sens 11:1011. https://doi.org/10.3390/rs11091011
Kloog I, Koutrakis P, Coull BA, Lee HJ, Schwartz J (2011) Assessing temporally and spatially resolved PM2.5 exposures for epidemiological studies using satellite aerosol optical depth measurements. Atmos Environ 45:6267–6275. https://doi.org/10.1016/j.atmosenv.2011.08.066
Land Development Department (LDD) (2016) Land use and land cover data for Thailand for the years 2012–2016 [CD–ROM Product]. Land Development Department. Bangkok, Thailand
Lelieveld J, Evans J, Fnais M, Giannadaki D, Pozzer A (2015) The contribution of outdoor air pollution sources to premature mortality on a global scale. Nature 525:367–371. https://doi.org/10.1038/nature15371
Liu Y, Sarnat JA, Kilaru V, Jacob DJ, Koutrakis P (2005) Estimating ground-level PM2.5 in the eastern United States using satellite remote sensing. Environ Sci Technol 39:3269–3278. https://doi.org/10.1021/es049352m
Ma Z, Hu X, Huang L, Bi J, Liu Y (2014) Estimating ground-level PM2.5 in China using satellite remote sensing. Environ Sci Technol 48:7436–7444. https://doi.org/10.1021/es5009399
Ma Z, Hu X, Sayer AM, Levy R, Zhang Q, Xue Y, Tong S, Bi J, Huang L, Liu Y (2016) Satellite-based spatiotemporal trends in PM2.5 concentrations: China, 2004–2013. Environ Health Perspect 124:184–192. https://doi.org/10.1289/ehp.1409481
Ma Z, Dey S, Christopher S, Liu R, Bi J, Balyan P, Liu Y (2022) A review of statistical methods used for developing large-scale and long-term PM2.5 models from satellite data. Remote Sens Environ 269:112827. https://doi.org/10.1016/j.rse.2021.112827
Nantawong N, Aman N, Manomaiphiboon K, Chankasem P, Surapipith V, Phongphiphat A (2021) Assessment of satellite aerosol optical depth over Greater Bangkok during 2003–2018. J Sustain Energy Environ 12:65–73
Narita D, Oanh NTK, Sato K, Huo M, Permadi DA, Chi NNH, Ratanajaratroj T, Pawarmart I (2019) Pollution characteristics and policy actions on fine particulate matter in a growing Asian economy: the case of Bangkok Metropolitan Region. Atmosphere 10:227. https://doi.org/10.3390/atmos10050227
National Economic and Social Development Board (NESDB) (2022) Gross regional and provincial product, chain volume measures, 2021 edition; Office of the National Economic and Social Development Board: Bangkok, Thailand, 2022. Available online: https://www.nesdc.go.th/main.php?filename=gross_regional (accessed on 28 September 2022)
Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V et al (2011) Scikit-learn: machine learning in python. J Mach Learn Res 12:2825–2830
Peng-In B, Sanitluea P, Monjatturat P, Boonkerd P, Phosri A (2022) Estimating ground-level PM2.5 over Bangkok metropolitan region in Thailand using aerosol optical depth retrieved by MODIS. Air Qual Atmos Health 15:2091–2102. https://doi.org/10.1007/s11869-022-01238-4
Phairuang W, Suwattiga P, Chetiyanukornkul T, Hongtieab S, Limpaseni W, Ikemori F, Hata M, Furuuchi M (2019) The influence of the open burning of agricultural biomass and forest fires in Thailand on the carbonaceous components in size-fractionated particles. Environ Pollut 247:238–247. https://doi.org/10.1016/j.envpol.2019.01.001
Pollution Control Department (PCD) (2023a) Thailand air quality index 2023. https://www.pcd.go.th/wp-content/uploads/2023/06/pcdnew-2023-06-02_09-43-56_071099.pdf. Accessed 6 June 2023
Pollution Control Department (PCD) (2023b) Annual report 2022. Pollution Control Department, Bangkok, Thailand (in Thai). https://www.pcd.go.th/wp-content/uploads/2023/04/pcdnew-2023-05-02_04-27-17_828080.pdf. Accessed 6 June 2023
Shogrkhodaei SZ, Razavi-Termeh SV, Fathnia A (2021) Spatio-temporal modeling of PM2.5 risk mapping using three machine learning algorithms. Environ Pollut 289:117859. https://doi.org/10.1016/j.envpol.2021.117859
Thai Meteorological Department (TMD) (2023) The climate of Thailand. Thai Meteorological Department. https://www.tmd.go.th/en/archive/thailand_climate.pdf. (accessed on 28 September 2023)
Thongphunchung K, Phosri A, Sihabut T, Patthanaissaranukool W (2021) Short-term effects of particulate matter on outpatient department visits for respiratory diseases among children in Bangkok metropolitan region: a case-crossover study. Air Qual Atmos Health 14:1785–1795. https://doi.org/10.1007/s11869-021-01053-3
Thongthammachart T, Jinsart W (2020) Estimating PM2.5 concentrations with statistical distribution techniques for health risk assessment in Bangkok. Hum Ecol Risk Assess 26:1848–1863. https://doi.org/10.1080/10807039.2019.1613630
Thongthammachart T, Shimadera H, Araki S, Matsuo T, Kondo A (2023) Land use regression model established using light gradient boosting machine incorporating the WRF/CMAQ model for highly accurate spatiotemporal PM2.5 estimation in the central region of Thailand. Atmos Environ 297:119595. https://doi.org/10.1016/j.atmosenv.2023.119595
Wang J, Christopher SA (2003) Intercomparison between satellite-derived aerosol optical thickness and PM2.5 mass: implications for air quality studies. Geophys Res Lett 30:2095. https://doi.org/10.1029/2003GL018174
Wimolwattanapun W, Hopke PK, Pongkiatkul P (2011) Source apportionment and potential source locations of PM2.5 and PM2.5-10 at residential sites in metropolitan Bangkok. Atmos Pollut Res 2:172–181. https://doi.org/10.5094/APR.2011.022
Wood S (2022) Mgcv: mixed GAM computation vehicle with automatic smoothness estimation. R package version 1.8–40. https://cran.r-project.org/package=mgcv. Accessed 10 Oct 2023
Xian D, Zhang P, Gao L, Sun R, Zhang H, Jia X (2021) Fengyun meteorological satellite products for earth system science applications. Adv Atmos Sci 38:1267–1284. https://doi.org/10.1007/s00376-021-0425-3
Xu W, Wang W, Chen B (2020) Comparison of hourly aerosol retrievals from JAXA Himawari/AHI in version 3.0 and a simple customized method. Sci Rep 10:20884. https://doi.org/10.1038/s41598-020-77948-5
Xu X, Zhang C, Liang Y (2021) Review of satellite-driven statistical models PM2.5 concentration estimation with comprehensive information. Atmos Environ 256:118302. https://doi.org/10.1016/j.atmosenv.2021.118302
You W, Zang Z, Zhang L, Zhang M, Pan X, Li Y (2016) A nonlinear model for estimating ground-level PM10 concentration in Xi’an using MODIS aerosol optical depth retrieval. Atmos Res 168:169–179. https://doi.org/10.1016/j.atmosres.2015.09.008
ZamaniJoharestani M, Cao C, Ni X, Bashir B, Talebiesfandarani S (2019) PM2.5 prediction based on random forest, XGBoost, and deep learning using multisource remote sensing data. Atmosphere 10:373. https://doi.org/10.3390/atmos10070373
Zhang P, Zhu L, Tang S, Gao L, Chen L, Zheng W, Han X, Chen J, Shao J (2019) General comparison of FY-4A/AGRI with other GEO/LEO instruments and its potential and challenges in non-meteorological applications. Front Earth Sci 6:224. https://doi.org/10.3389/feart.2018.00224
Zou B, Chen J, Zhai L, Fang X, Zheng Z (2016) Satellite based mapping of ground PM2.5 concentration using generalized additive modeling. Remote Sens 9:1. https://doi.org/10.3390/rs9010001
Acknowledgements
The authors sincerely thank the Pollution Control Department (PCD) for the observational data. The authors thank Muanfun Inerb, Bikash Devkota, and Eakkachai Kokkaew for their general assistance. We thank the anonymous reviewer for his/her useful comments and suggestions.
Funding
This study was financially supported by King Mongkut’s University of Technology Thonburi (KMUTT) and the National Research Council of Thailand (NRCT) through a postdoctoral fellowship to the first author, the Asia Pacific Space Cooperation Organization (APSCO, China), and the Energy Conservation Promotion Fund (ENCONFUND) of the Ministry of Energy (Thailand). The Office of the National Digital Economy and Society Commission (ONDE) helped administer the APSCO funding.
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
Ethics approval
Not applicable.
Consent to participate
Not applicable.
Consent for publication
Not applicable.
Competing interests
The authors declare no competing interests.
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Supplementary information
Below is the link to the electronic supplementary material.
Rights and permissions
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
About this article
Cite this article
Aman, N., Manomaiphiboon, K., Xian, D. et al. Spatiotemporal estimation of hourly PM2.5 using AOD derived from geostationary satellite Fengyun-4A and machine learning models for Greater Bangkok. Air Qual Atmos Health (2024). https://doi.org/10.1007/s11869-024-01524-3
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11869-024-01524-3