Communications for Statistical Applications and Methods

  • 제30권5호
  • /
  • Pages.517-530
  • /
  • 2023
  • /
  • 2287-7843(pISSN)
  • /
  • 2383-4757(eISSN)
한국통계학회 (The Korean Statistical Society)
권호 표지
DOI QR코드

DOI QR Code

Prediction of PM10 concentration in Seoul, Korea using Bayesian network

  • Minjoo Joa (Department of Statistics, Ewha Womans University) ;
  • Rosy Oh (Department of Mathematics, Korea Military Academy) ;
  • Man-Suk Oh (Department of Statistics, Ewha Womans University)
  • 투고 : 2023.04.10
  • 심사 : 2023.07.21
  • 발행 : 2023.09.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Recent studies revealed that fine dust in ambient air may cause various health problems such as respiratory diseases and cancer. To prevent the toxic effects of fine dust, it is important to predict the concentration of fine dust in advance and to identify factors that are closely related to fine dust. In this study, we developed a Bayesian network model for predicting PM10 concentration in Seoul, Korea, and visualized the relationship between important factors. The network was trained by using air quality and meteorological data collected in Seoul between 2018 and 2021. The study results showed that current PM10 concentration, season, carbon monoxide (CO) were the top 3 effective factors in 24 hours ahead prediction of PM10 concentration in Seoul, and that there were interactive effects.

키워드

과제정보

This work was supported by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIT, ME) (NRF-2022R1A2C1091256, 2020R1A2C1008699).

참고문헌

  1. An S and Lim Y (2020). Forecasting daily PMnullnull concentration in Seoul Jong-no district by using various statistical techniques, The Korean Data & Information Science Society, 31, 187-198. https://doi.org/10.7465/jkdi.2020.31.1.187
  2. Ang SL, Ong HC, and Low HC (2016). Classification using the general Bayesian network, SCIENCE & TECHNOLOGY, 24, 205-209.
  3. Cha J and Kim J (2018). Development of data mining algorithm for implementation of fine dust numerical prediction model, Journal of the Korea Institute of Information and Communication Engineering, 22, 595-601. https://doi.org/10.6109/JKIICE.2018.22.4.595
  4. Cho KW, Jung YJ, Kang CG, and Oh CH (2019). Conformity assessment of machine learning algorithm for particulate matter prediction, Journal of the Korea Institute of Information and Communication Engineering, 23, 20-26. https://doi.org/10.6109/JKIICE.2019.23.1.20
  5. Cover TM (1999). Elements of Information Theory, John Wiley & Sons, New York.
  6. Daly R, Shen Q, and Aitken S (2011). Learning Bayesian networks: Approaches and issues, The Knowledge Engineering Review, 26, 99-157. https://doi.org/10.1017/S0269888910000251
  7. Han Y, Heo Y, Hong Y, and Kwon SO (2019). Correlation between physical activity and lung function in dusty areas: Results from the chronic obstructive pulmonary disease in dusty areas (CODA) Cohort, Tuberculosis and Respiratory Diseases, 82, 311-312. https://doi.org/10.4046/trd.2019.0006
  8. Jang YK (2016). Current status and problems of fine dust pollution, Journal of Environmental Studies, 58, 4-13.
  9. Kim BY, Lim YK, and Cha JW (2022). Short-term prediction of particulate matter (PM10 and PM2.5) in Seoul, South Korea using tree-based machine learning algorithms, Atmospheric Pollution Research, 13, 101547.
  10. Kim DS, Jeong J, and Ahn J (2016). Characteristics in atmospheric chemistry between NO, NO2 and O3 at an urban site during MAPS (megacity air pollution study)-Seoul, Korea, Journal of Korean Society for Atmospheric Environment, 32, 422-424. https://doi.org/10.5572/KOSAE.2016.32.4.422
  11. Kim SY and Song I (2017). National-scale exposure prediction for long-term concentrations of particulate matter and nitrogen dioxide in South Korea, Environmental Pollution, 226, 21-29. https://doi.org/10.1016/j.envpol.2017.03.056
  12. Kim MJ (2019). The effects of transboundary air pollution from China on ambient air quality, Heliyon, 5, e02953.
  13. Korb KB and Nicholson AE (2010). Bayesian Artificial Intelligence, CRC Press, Boca Raton, FL.
  14. Lee JS, Jung YJ, and Oh CH (2020). Seasonal correlation analysis between PM10 and meteorological and air pollutant data, In Proceedings of Korea Institute of information and Communication Engineering 2020 Autumn General Conference Paper, 248-250.
  15. Lim JM (2019). An estimation model of fine dust concentration using meteorological environment data and machine learning, Journal of Information Technology Services, 18, 173-186. https://doi.org/10.9716/KITS.2019.18.1.173
  16. Madden MG (2009). On the classification performance of TAN and general Bayesian networks, Knowledge-Based Systems, 22, 489-495. https://doi.org/10.1016/j.knosys.2008.10.006
  17. Oh M and Park CK (2022). Regional source apportionment of PM2.5 in Seoul using Bayesian multivariate receptor model, Journal of Applied Statistics, 49, 738-751. https://doi.org/10.1080/02664763.2020.1822305
  18. Oh R, Lee HK, Pak YK, and Oh MS (2022). An interactive online app for predicting diabetes via machine learing from environment-polluting chemical exposure data, International Journal of Environmental Research and Public Health, 19, 1-15. https://doi.org/10.3390/ijerph19105800
  19. Park AK, Heo JB, and Kim H (2011). Analyses of factors that affect PM10 level of Seoul focusing on meteorological factors and long range transferred carbon monooxide, Particle and Aerosol Research, 7, 60-68.
  20. Park E, Chang HJ, and Nam HS (2018). A Bayesian network model for predicting post-stroke outcomes with available risk factors, Frontiers in Neurology, 9, 1-11. https://doi.org/10.3389/fneur.2018.00001
  21. Park JH, Yoo SJ, Kim KJ, Gu YH, Lee KH, and Son UH (2017). PM10 density forecast model using long short term memory, In 2017 Ninth International Conference on Ubiquitous and Future Networks (ICUFN), Milan, Italy, 576-581.
  22. Pearl J (2011). Bayesian networks, U of California, Los Angeles, department of statistics papers, Available from: https://escholarship.org/content/qt53n4f34m/qt53n4f34m.pdf
  23. Roh SY (2017). A study on interpolation for the discrete time series of Seoul prime office price, Journal of Real Estate Analysis, 3, 3-4. https://doi.org/10.30902/jrea.2017.3.2.1
  24. Scutari M, Silander T, and Ness R (2022). bnlearn: Bayesian network structure learning, parameter learning and inference, R package version 4.8.1.
  25. Sesen MB, Nicholson AE, Banares-Alcantara R, Kadir T, and Brady M (2013). Bayesian networks for clinical decision support in lung cancer care, PLoS ONE, 8, e82349.
  26. Shin DC (2007). Health effects of ambient particulate matter, Journal of the Korean Medical Association, 50, 178.
  27. Shin MK, Lee CD, Ha HS, Choe CS, and Kim YH (2007). The influence of meteorological factors on PM10 concertration in Incheon, Journal of Korean Society for Atmospheric Environment, 23, 322-323. https://doi.org/10.5572/KOSAE.2007.23.3.322
  28. Sohn KT and Kim D (2015). Development of statistical forecast model for PM10 concentration over Seoul, Journal of the Korean Data & Information Science Society, 26, 291-293. https://doi.org/10.7465/jkdi.2015.26.2.289
  29. Son S and Kim J (2020). Evaluation and predicting PM 10 concentration using multiple linear regression and machine learning, Korean Journal of Remote Sensing, 36, 1711-1720. https://doi.org/10.7780/KJRS.2020.36.6.3.7
  30. Witten IH, Frank E, and HalMA(2011). Data mining: practical machine learning tools and technique, ACM SIGSOFT Software Engineering Notes, 36, 51-52. https://doi.org/10.1145/2020976.2021004
  31. Won J and Na J (2021). Prediction of PM 10 in Seoul using penalized regression, The Korean Data & Information Science Society, 32, 631-640. https://doi.org/10.7465/jkdi.2021.32.3.631
  32. Yang WH (2019). Changes in air pollutant concentrations due to climate change and the health effect of exposure to particulate matter, Health and Welfare Forum, 269, 21-22.
  33. Yang J and Zhang BT (2000). Analysis of Web Customers Using Bayesian Belief Networks, In Proceedings of Korean Institute of Intelligent Systems 2000 Autumn Conference Paper, Jeonju, 387-388.
  34. Yang G, Lee H, and Lee G (2020). A hybrid deep learning model to forecast particulate matter concentration levels in Seoul, South Korea, Atmosphere, 11, 348, Available from: https://doi.org/10.3390/atmos110403489
  35. Korean Ministry of Environment (2014). Knowing the fine dust to protect our health, Available from: https://www.me.go.kr/home/web/board/read.do?menuId=10181&boardMasterId=54&boardCategoryId=&boardId=342997
  36. Korean Ministry of Environment (2017). Ozone, know and prepare properly, Available from: https://www.me.go.kr/home/web/board/read.do?menuId=10181&boardMasterId=54&boardId=790790