Skip to main content

Thank you for visiting nature.com. You are using a browser version with limited support for CSS. To obtain the best experience, we recommend you use a more up to date browser (or turn off compatibility mode in Internet Explorer). In the meantime, to ensure continued support, we are displaying the site without styles and JavaScript.

  • Article
  • Published:

Evaluating long-term and high spatiotemporal resolution of wet-bulb globe temperature through land-use based machine learning model

Journal of Exposure Science & Environmental Epidemiology (2023)Cite this article

Abstract

Background

The increase in global temperature and urban warming has led to the exacerbation of heatwaves, which negatively affect human health and cause long-term loss of work productivity. Therefore, a global assessment in temperature variation is essential.

Objective

This paper is the first of its kind to propose land-use based spatial machine learning (LBSM) models for predicting highly spatial-temporal variations of wet-bulb globe temperature (WBGT), which is a heat stress indicator used to assess thermal comfort in indoor and outdoor environments, specifically for the main island of Taiwan.

Methods

To develop spatiotemporal prediction models for both the working period and noon period, we calculated the WBGT of each weather station from 2001 to 2019 using temperature, humidity, and solar radiation data. These WBGT estimations were then used as the dependent variable for developing the spatiotemporal prediction models. To enhance model performance, we used innovative approaches that combined SHapley Additive exPlanations (SHAP) values for the selection of non-linear variables, along with machine learning algorithms for model development.

Results

When incorporating temperature along with other land-use/land cover predictor variables, the performance of LBSM models was excellent, with an R2 value of up to 0.99. The LBSM models explained 98% and 99% of the spatial-temporal variations in WBGT for the working and noon periods, respectively, within the complete models. In the temperature-excluded models, the explained variances were 94% and 96% for the working and noon periods, respectively.

Impact

WBGT is a common method used by many organizations to access the impact of heat stress on human beings. However, limited studies have mentioned the association between WBGT and health impacts due to the absence of spatiotemporal databases. This study develops a new approach using land-use-based spatial machine learning (LBSM) models to better predict the fine spatial-temporal WBGT levels, with a 50-m × 50-m grid resolution for both working time and noontime. Our proposed methodology could be used in future studies aimed at evaluating the potential long-term loss of work productivity due to the effects of global warming or urban heat island.

This is a preview of subscription content, access via your institution

Access options

Buy this article

  • Purchase on Springer Link
  • Instant access to full article PDF
Buy now

Prices may be subject to local taxes which are calculated during checkout

Fig. 1
Fig. 2
Fig. 3
Fig. 4

Similar content being viewed by others

Data availability

All data and code supporting this study are available from the corresponding author on reasonable request.

References

  1. Santamouris M. Regulating the damaged thermostat of the cities—Status, impacts and mitigation challenges. Energy Build. 2015;91:43–56.

    Article  Google Scholar 

  2. UN (United Nations) Department of Economic and Social Affairs. World Urbanization Prospects: The 2018 Revision [Internet]. 2018. Available from: https://www.un.org/development/desa/pd/zh/node/3124

  3. Kumar P, Sharma A. Study on importance, procedure, and scope of outdoor thermal comfort–A review. Sustain Cities Soc. 2020;61:102297.

    Article  Google Scholar 

  4. Ren, G.Y. Urbanization as a major driver of urban climate change. Adv. Clim. Chang. Res. 2015;6:1–6. Retrieved from https://www.scipedia.com/public/Ren_2015a.

  5. He BJ, Wang J, Liu H, Ulpiani G. Localized synergies between heat waves and urban heat islands: Implications on human thermal comfort and urban heat management. Environ Res. 2021;193:110584.

    Article  CAS  PubMed  Google Scholar 

  6. Burkart K, Schneider A, Breitner S, Khan MH, Krämer A, Endlicher W. The effect of atmospheric thermal conditions and urban thermal pollution on all-cause and cardiovascular mortality in Bangladesh. Environ Pollut. 2011;159:2035–43.

    Article  CAS  PubMed  Google Scholar 

  7. Gao X, Yang L, Cheng S, Gao R, Zhou Y, Xue L, et al. Semi-continuous measurement of water-soluble ions in PM2.5 in Jinan, China: temporal variations and source apportionments. Atmos Environ. 2011;45:6048–56.

    Article  CAS  Google Scholar 

  8. Lin YK, Chang CK, Li MH, Wu YC, Wang YC. High-temperature indices associated with mortality and outpatient visits: characterizing the association with elevated temperature. Sci Total Environ. 2012;427:41–9.

    Article  PubMed  PubMed Central  Google Scholar 

  9. Michelozzi P, Accetta G, DeSario M, D’Ippoliti D, Marino C, Baccini M, et al. High temperature and hospitalizations for cardiovascular and respiratory causes in 12 European cities. Am J Respir Crit Care Med. 2009;179:383–9.

    Article  PubMed  Google Scholar 

  10. Turner LR, Connell D, Tong S. Exposure to hot and cold temperatures and ambulance attendances in Brisbane, Australia: a time-series study. BMJ Open. 2012;2:e001074.

    Article  PubMed  PubMed Central  Google Scholar 

  11. Urban A, Davídkovová H, Kyselý J. Heat-and cold-stress effects on cardiovascular mortality and morbidity among urban and rural populations in the Czech Republic. Int J Biometeorol. 2014;58:1057–68.

    Article  PubMed  Google Scholar 

  12. Chen NT, Lin PH, Guo YLL. Long-term exposure to high temperature associated with the incidence of major depressive disorder. Sci Total Environ. 2019;659:1016–20.

    Article  CAS  PubMed  Google Scholar 

  13. Ding N, Berry HL, Bennett CM. The importance of humidity in the relationship between heat and population mental health: evidence from Australia. PLoS One. 2016;11:e0164190.

    Article  PubMed  PubMed Central  Google Scholar 

  14. Shapira A, Shiloh R, Potchter O, Hermesh H, Popper M, Weizman A. Admission rates of bipolar depressed patients increase during spring/summer and correlate with maximal environmental temperature. Bipolar Disord. 2004;6:90–3.

    Article  PubMed  Google Scholar 

  15. Gasparrini A, Guo Y, Sera F, Vicedo-Cabrera AM, Huber V, Tong S, et al. Projections of temperature-related excess mortality under climate change scenarios. Lancet Planet Heal. 2017;1:e360–7.

    Article  Google Scholar 

  16. Lee JW, Hong SY, Chang EC, Suh MS, Kang HS. Assessment of future climate change over East Asia due to the RCP scenarios downscaled by GRIMs-RMP. Clim Dyn. 2014;42:733–47.

    Article  Google Scholar 

  17. Schoetter R, Cattiaux J, Douville H. Changes of western European heat wave characteristics projected by the CMIP5 ensemble. Clim Dyn. 2015;45:1601–16.

    Article  Google Scholar 

  18. Li X, Chow KH, Zhu Y, Lin Y. Evaluating the impacts of high-temperature outdoor working environments on construction labor productivity in China: A case study of rebar workers. Build Environ. 2016;95:42–52.

    Article  Google Scholar 

  19. Cheng W, SpenglerJ O, Brown RD. A Comprehensive Model for Estimating Heat Vulnerability of Young Athletes. Int J Environ Res Public Health. 2020;17:6156.

    Article  PubMed  PubMed Central  Google Scholar 

  20. ISO7243. Ergonomics of the thermal environment — Assessment of heat stress using the WBGT (wet bulb globe temperature) index. Available from: chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/ https://cdn.standards.iteh.ai/samples/67188/5a4c5553da5945aa872478c36755cded/ISO-7243-2017.pdf

  21. Occupational Safety and Health Administration (OSHA). Technical Manual (OTM) Section III: Chapter 4 Heat Stress. 2017. Available from: https://www.osha.gov/otm/section-3-health-hazards/chapter-4#introduction

  22. Budd GM. Wet-bulb globe temperature (WBGT)—its history and its limitations. J Sci Med Sport. 2008;11:20–32.

    Article  PubMed  Google Scholar 

  23. d’Ambrosio Alfano FR, Malchaire J, Palella BI, Riccio G. WBGT index revisited after 60 years of use. Ann Occup Hyg. 2014;58:955–70.

    PubMed  Google Scholar 

  24. Lucas RAI, Epstein Y, Kjellstrom T. Excessive occupational heat exposure: a significant ergonomic challenge and health risk for current and future workers. Extrem Physiol Med. 2014;3:1–8.

    Article  Google Scholar 

  25. Heo S, Bell ML, Lee JT. Comparison of health risks by heat wave definition: Applicability of wet-bulb globe temperature for heat wave criteria. Environ Res. 2019;168:158–70.

    Article  PubMed  Google Scholar 

  26. Park JK, Jung WS, Kim SC, Park GU. On the characteristics of globe temperature variation observed at downtown in summer season. J Environ Sci Int. 2008;17:907–18.

    Article  Google Scholar 

  27. Lin HT, Lee KP. Experimental analyses of urban heat island effects of the four metropolitan cities in Taiwan (I)–The comparision of the heat island intensities between Taiwan and the world cities (In Chinese). J Arch. 1999;31:51–73.

    Google Scholar 

  28. Ministry of the Environment Government of Japan. Investigation Report of Heat Island Measures and Method (In Japanese). 2001.

  29. Taiwan Central Weather Bureau. CWB Observation Data. Inquire System (CODiS). 2020.

  30. Sun CY, Jian ZX. Heat island effect of Taipei Metropolitan Area. J City Plan. 2016;43:437–62.

    CAS  Google Scholar 

  31. Huang JM, Chang HY, Wang YS. Spatiotemporal changes in the built environment characteristics and urban heat island effect in a medium-sized city, Chiayi City, Taiwan. Sustainability. 2020;12:365.

    Article  Google Scholar 

  32. MOI (Ministry of the Interior). Population by Sex and 5 Year Age Group for Counties and Cities. End Year. 2021.

  33. CWB. Global and Taiwan Temperature Trend Analysis Report. 2020.

  34. Aguilera I, Foraster M, Basagaña X, Corradi E, Deltell A, Morelli X, et al. Application of land use regression modelling to assess the spatial distribution of road traffic noise in three European cities. J Expo Sci Environ Epidemiol. 2015;25:97–105.

    Article  PubMed  Google Scholar 

  35. Hsu CY, Zeng YT, Chen YC, Chen MJ, Lung SCC, Wu CD. Kriging-based land-use regression models that use machine learning algorithms to estimate the monthly BTEX concentration. Int J Environ Res Public Health. 2020;17:6956.

    Article  PubMed  PubMed Central  Google Scholar 

  36. Hsu CY, Wu JY, Chen YC, Chen NT, Chen MJ, Pan WC, et al. Asian culturally specific predictors in a large-scale land use regression model to predict spatial-temporal variability of ozone concentration. Int J Environ Res Public Health. 2019;16:1300.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  37. Pan WC, Wu CD, Chen MJ, Huang YT, Chen CJ, Su HJ, et al. Fine particle pollution, alanine transaminase, and liver cancer: a Taiwanese prospective cohort study (REVEAL-HBV). J Natl Cancer Inst. 2016;108:djv341.

    Article  Google Scholar 

  38. Tsin PK, Knudby A, Krayenhoff ES, Brauer M, Henderson SB. Land use regression modeling of microscale urban air temperatures in greater Vancouver, Canada. Urban Clim. 2020;32:100636.

    Article  Google Scholar 

  39. Wu CD, Chen YC, Pan WC, Zeng YT, Chen MJ, Guo YL, et al. Land-use regression with long-term satellite-based greenness index and culture-specific sources to model PM2.5 spatial-temporal variability. Environ Pollut. 2017;224:148–57.

    Article  CAS  PubMed  Google Scholar 

  40. Xie D, Liu Y, Chen J. Mapping urban environmental noise: a land use regression method. Environ Sci Technol. 2011;45:7358–64.

    Article  CAS  PubMed  Google Scholar 

  41. DeMers MN. Fundamentals of geographic information systems. John Wiley & Sons; 2008.

  42. Liu L, Zhang Y. Urban heat island analysis using the Landsat TM data and ASTER data: A case study in Hong Kong. Remote Sens. 2011;3:1535–52.

    Article  Google Scholar 

  43. Yuan F, Bauer ME. Comparison of impervious surface area and normalized difference vegetation index as indicators of surface urban heat island effects in Landsat imagery. Remote Sens Environ. 2007;106:375–86.

    Article  Google Scholar 

  44. Corburn J. Cities, climate change and urban heat island mitigation: Localising global environmental science. Urban Stud. 2009;46:413–27.

    Article  Google Scholar 

  45. Ahmed AQ, Ossen DR, Jamei E, Manaf NA, Said I, Ahmad MH. Urban surface temperature behaviour and heat island effect in a tropical planned city. Theor Appl Climatol. 2015;119:493–514.

    Article  Google Scholar 

  46. Chen J, deHoogh K, Gulliver J, Hoffmann B, Hertel O, Ketzel M, et al. A comparison of linear regression, regularization, and machine learning algorithms to develop Europe-wide spatial models of fine particles and nitrogen dioxide. Environ Int. 2019;130:104934.

    Article  CAS  PubMed  Google Scholar 

  47. Kamińska JA. A random forest partition model for predicting NO2 concentrations from traffic flow and meteorological conditions. Sci Total Environ. 2019;651:475–83.

    Article  PubMed  Google Scholar 

  48. Wong PY, Lee HY, Zeng YT, Chern YR, Chen NT, Lung SCC, et al. Using a land use regression model with machine learning to estimate ground level PM2.5. Environ Pollut. 2021;116846.

  49. DGB. Statistical Yearbook Of The Republic Of China 2020. 2021.

  50. MOTC (Ministry of Transportation and Communications). Number of Registered Motor Vehicles. Annu Transp Rep. 2020. Retrived from https://stat.motc.gov.tw/mocdb/stmain.jsp?sys=100&funid=a3301.

  51. Liljegren JC, Carhart RA, Lawday P, Tschopp S, Sharp R. Modeling the wet bulb globe temperature using standard meteorological measurements. J Occup Environ Hyg. 2008;5:645–55.

    Article  PubMed  Google Scholar 

  52. Alfano FRDA, Dell’Isola M, Ficco G, Palella BI, Riccio G. Small globes and pocket heat stress meters for WBGT and PHS evaluations. A critical analysis under controlled conditions. Build Environ. 2022;226:109781.

    Article  Google Scholar 

  53. TSI. User manual of QUESTEMP Heat stress monitors models 34 and 36]. 2018. Available from: chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/ https://multimedia.3m.com/mws/media/760839O/questemp-34-36-heat-stress-monitor-user-manual.pdf

  54. Chen TH, Hsu YC, Zeng YT, Lung SCC, Su HJ, Chao HJ, et al. A hybrid kriging/land-use regression model with Asian culture-specific sources to assess NO2 spatial-temporal variations. Environ Pollut. 2020;259:113875.

    Article  CAS  PubMed  Google Scholar 

  55. Chen T, Guestrin C Xgboost: A scalable tree boosting system. In: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM; 2016. p. 785–94.

  56. Xu Y, Ho HC, Wong MS, Deng C, Shi Y, Chan TC, et al. Evaluation of machine learning techniques with multiple remote sensing datasets in estimating monthly concentrations of ground-level PM2.5. Environ Pollut. 2018;242:1417–26.

    Article  CAS  PubMed  Google Scholar 

  57. Zhang L, Zhan C. Machine learning in rock facies classification: an application of XGBoost. In: International Geophysical Conference, Qingdao, China, 17–20 April 2017. Society of Exploration Geophysicists and Chinese Petroleum Society; 2017. p. 1371–4.

  58. Breiman L. Random forests. Mach Learn. 2001;45:5–32.

    Article  Google Scholar 

  59. Ke G, Meng Q, Finley T, Wang T, Chen W, Ma W, et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv Neural Inf Process Syst. 2017;30:3146–54.

    Google Scholar 

  60. Wei J, Li Z, Pinker RT, Wang J, Sun L, Xue W, et al. Himawari-8-derived diurnal variations in ground-level PM2.5 pollution across China using the fast space-time Light Gradient Boosting Machine (LightGBM). Atmos Chem Phys. 2021;21:7863–80.

    Article  CAS  Google Scholar 

  61. Feurer M, Klein A, Eggensperger K, Springenberg J, Blum M, Hutter F Efficient and robust automated machine learning. Adv Neural Inf Process Syst. 2015;28.

  62. Li J, An X, Li Q, Wang C, Yu H, Zhou X, et al. Application of XGBoost algorithm in the optimization of pollutant concentration. Atmos Res. 2022;276:106238.

    Article  CAS  Google Scholar 

  63. Bellinger C, Mohomed Jabbar MS, Zaïane O, Osornio-Vargas A. A systematic review of data mining and machine learning for air pollution epidemiology. BMC Public Health. 2017;17:1–19.

    Article  Google Scholar 

  64. Wei W, Ramalho O, Malingre L, Sivanantham S, Little JC, Mandin C. Machine learning and statistical models for predicting indoor air quality. Indoor Air. 2019;29:704–26.

    Article  CAS  PubMed  Google Scholar 

  65. Wu CD, Zeng YT, Lung SCC. A hybrid kriging/land-use regression model to assess PM2.5 spatial-temporal variability. Sci Total Environ. 2018;645:1456–64.

    Article  CAS  PubMed  Google Scholar 

  66. Hsu CY, Wu CD, Hsiao YP, Chen YC, Chen MJ, Lung SCC. Developing land-use regression models to estimate PM2.5-bound compound concentrations. Remote Sens. 2018;10:1971.

    Article  Google Scholar 

  67. Young MT, Bechle MJ, Sampson PD, Szpiro AA, Marshall JD, Sheppard L, et al. Satellite-based NO2 and model validation in a national prediction model based on universal kriging and land-use regression. Environ Sci Technol. 2016;50:3686–94.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  68. Zander KK, Botzen WJW, Oppermann E, Kjellstrom T, Garnett ST. Heat stress causes substantial labour productivity loss in Australia. Nat Clim Chang. 2015;5:647–51.

    Article  Google Scholar 

  69. Zhao Y, Sultan B, Vautard R, Braconnot P, Wang HJ, Ducharne A. Potential escalation of heat-related working costs with climate and socioeconomic changes in China. Proc Natl Acad Sci. 2016;113:4640–5.

    Article  CAS  PubMed  PubMed Central  Google Scholar 

  70. Kjellstrom T, Freyberg C, Lemke B, Otto M, Briggs D. Estimating population heat exposure and impacts on working people in conjunction with climate change. Int J Biometeorol. 2018;62:291–306.

    Article  PubMed  Google Scholar 

  71. BLSU. Fatal occupational injuries by event or exposure for all fatal injuries and major private industry sector, All US, 2011 (Table A-9). 4/25/2013; 2013.

  72. Chan APC, Yam MCH, Chung JWY, Yi W. Developing a heat stress model for construction workers. J Facil Manag. 2012;10:59–74.

    Article  Google Scholar 

  73. Yengoh GT, Ardö J. Climate change and the future heat stress challenges among smallholder farmers in East Africa. Atmosphere. 2020;11:753.

    Article  Google Scholar 

  74. Tigchelaar M, Battisti DS, Spector JT. Work adaptations insufficient to address growing heat risk for US agricultural workers. Environ Res Lett ERL. 2020;15:94035. [Web site]

    Article  Google Scholar 

  75. Hu D. Identification of Shrinking Cities on the Main Island of Taiwan Based on Census Data and Population Registers: A Spatial Analysis. ISPRS Int J Geo-Inf. 2021;10:694.

    Article  Google Scholar 

Download references

Acknowledgements

This study was granted by the National Science and Technology Council, Taiwan (MOST 110-2628-M-006-001-MY3; 112-2121-M-006-015-; NSTC 112-2123-M-001-008) and Academia Sinica, Taiwan, under “Trans-disciplinary PM2.5 Exposure Research in Urban Areas for Health-oriented Preventive Strategies (II)”. Project No.: AS-SS-110-02. This work was also financially supported by the “Innovation and Development Center of Sustainable Agriculture” from The Featured Areas Research Center Program within the framework of the Higher Education Sprout Project by the Minisstry of Education (MOE) in Taiwan.

Author information

Authors and Affiliations

  1. Department of Safety, Health and Environmental Engineering, Ming Chi University of Technology, New Taipei City, Taiwan

    Chin-Yu Hsu

  2. Center for Environmental Sustainability and Human Health, Ming Chi University of Technology, New Taipei City, Taiwan

    Chin-Yu Hsu

  3. Department of Environmental and Occupational Health, National Cheng Kung University, Tainan, Taiwan

    Pei-Yi Wong

  4. Department of Geomatics, National Cheng Kung University, Tainan, Taiwan

    Yinq-Rong Chern & Chih-Da Wu

  5. Research Center for Environmental Changes, Academia Sinica, Taipei, Taiwan

    Shih-Chun Candice Lung

  6. Department of Atmospheric Sciences, National Taiwan University, Taipei, Taiwan

    Shih-Chun Candice Lung

  7. National Institute of Environmental Health Sciences, National Health Research Institutes, Miaoli, Taiwan

    Chih-Da Wu

  8. Innovation and Development Center of Sustainable Agriculture, National Chung Hsing University, Tainan, Taiwan

    Chih-Da Wu

Authors
  1. Chin-Yu Hsu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Pei-Yi Wong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yinq-Rong Chern
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Shih-Chun Candice Lung
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Chih-Da Wu
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Conceptualization, CDW; methodology, YRC, PYW, and CDW; formal analysis, YRC; writing—original draft preparation, CYH, PYW, and CDW; writing—review and editing, CYH, P.Y.W., SCCL, and CDW; resources, SCCL and CDW; supervision, SCCL; funding acquisition, SCCL and CDW.

Corresponding author

Correspondence to Chih-Da Wu.

Ethics declarations

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

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.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Hsu, CY., Wong, PY., Chern, YR. et al. Evaluating long-term and high spatiotemporal resolution of wet-bulb globe temperature through land-use based machine learning model. J Expo Sci Environ Epidemiol (2023). https://doi.org/10.1038/s41370-023-00630-1

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1038/s41370-023-00630-1

Search

Advanced search

Quick links