융합정보논문지 (Journal of Convergence for Information Technology)

중소기업융합학회 (Convergence Society for SMB)
권호 표지
DOI QR코드

DOI QR Code

다중 선형 회귀에 의한 광산란 초미세먼지 측정기의 황사 보정 기법

An Asian Dust Compensation Scheme of Light-Scattering Fine Particulate Matter Monitors by Multiple Linear Regression

  • 투고 : 2021.06.29
  • 심사 : 2021.08.20
  • 발행 : 2021.08.28
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

광산란법을 이용한 초미세먼지 측정기는 초 단위의 측정이 가능하고 휴대할 수 있는 크기로 설계될 수 있다. 또한 하나의 센서로 여러 크기별 (PM1.0, PM2.5, PM4.0, 및 PM10) 농도를 측정할 수 있다. 이 방식은 입자의 개수와 크기를 측정하고 이를 단위 부피당 무게인 농도로 변환하는 과정 때문에 큰 밀도를 가지는 황사에 대해서는 큰 오차를 나타낸다. 본 논문은 광산란 초미세먼지 측정기가 여러 크기별 PM 농도를 이용하여 황사 발생 시 초미세먼지(PM2.5)의 농도의 오차를 정확히 보정할 수 있고, 황사가 발생하지 않을 때도 영향을 받지 않는, 다중 선형외기 기법의 기계학습에 의한 보정 기법을 제시한다. 두 가지 또는 세 가지의 PM 크기 입력만으로도 광산란 미세먼지 측정 장치의 황사 오류를 크게 보정할 수 있음을 보인다. 한 달 동안 중부권대기환경연구소의 베타레이 측정기와 광산란 측정기의 측정값을 비교·분석하였다. 황사가 없는 구간에서 이 두 장비의 상관계수(R2)는 0.927이었고, 황사를 포함한 전 구간에서 상관계수는 0.763이었지만, 기계학습을 통하여 상관계수가 0.944로 향상되었다.

Light-scattering fine particulate matter monitors can measure particulate matter (PM) concentrations in every second and can be designed in a portable size. They can measure the concentrations of various PM sizes (PM1.0, PM2.5, PM4.0 and PM10) with a single sensor. They measure the number and size of particulate matters and convert them to weight per volume (concentration). These devices show a large error for asian dust. This paper proposes a scheme that compensates the PM2.5 concenstration error for asian dust by multiple linear regression machine learning in light-scattering PM monitors. This scheme can be effective with only two or three types of PM sizes. The experimental results compare a beta-ray PM monitor of national institute of environmental research and a light-scattering PM monitor during a month. The correlation coefficient (R2) of theses two devices was 0.927 without asian dust, but it was 0.763 due to asian dust during the entire experimental period and improved to 0.944 by the proposed machine learning.

키워드

과제정보

This work was conducted while a Sabbatical at Jungwon Univeristy in 2020.

참고문헌

  1. J. Lelieveld, K. Klingmuller, A. Pozzer, U. Poschl, M. Fnais, A. Daiber & T. Munzel. (2019). Cardiovascular disease burden from ambient air pollution in Europe reassessed using novel hazard ratio functions. European heart journal, 40(20), 1590-1596. DOI : 10.1093/eurheartj/ehz135
  2. B. Choubin, M. Abdolshahnejad, E. Moradi, X. Querol, A. Mosavi, S. Shamshirband & P. Ghamisi. (2020). Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain. Science of The Total Environment, 701, 134474. DOI : 10.1016/j.scitotenv.2019.134474
  3. Kampa, M., & Castanas, E. (2008). Human health effects of air pollution. Environmental pollution, 151(2), 362-367. DOI : 10.1016/j.envpol.2007.06.012
  4. X. Wu, R. C. Nethery, B. M. Sabath, D. Braun & F. Dominici. (2020). Exposure to air pollution and COVID-19 mortality in the United States. MedRxiv.
  5. Teledyne Advanced Pollution Instrumentation. (2018). User manual model T640 PM mass monitor. Teledyne API [Online], http://www.teledyne-api.com/
  6. Grimm Aerosol. (2012). GRIMM EDM 180 dust monitor, NAQC-EPA Monitoring Conference Denver. Colorado May 14th.
  7. D. S. Kang, J. E. Oh, S. Y. Lee, H. J. Shin, H. K. Bong & D. S. Kim. (2018). Development and performance evaluation of a real-time PM monitor based on optical scattering method, Particle and Aerosol Research, 14, 107-119. DOI : 10.11629/jpaar.2018.14.4.107
  8. S. Son. & J. Kim, (2020). Evaluation and Predicting PM 10 Concentration Using Multiple Linear Regression and Machine Learning. Korean Journal of Remote Sensing, 36(6_3), 1711-1720. DOI : 10.7780/kjrs.2020.36.6.3.7
  9. K. S. Harishkumar, K. M. Yogesh & I. Gad. (2020). Forecasting air pollution particulate matter (PM2. 5) using machine learning regression models. Procedia Computer Science, 171, 2057-2066. DOI : 10.1016/j.procs.2020.04.221
  10. S. Abdullah, N. N. L. M. Napi, A. N. Ahmed, W. N. W. Mansor, A. A. Mansor, M. Ismail & Z. T. A. Ramly. (2020). Development of multiple linear regression for particulate matter (PM10) forecasting during episodic transboundary haze event in Malaysia. Atmosphere, 11(3), 289. DOI : 10.3390/atmos11030289
  11. L. A. Diaz-Robles, J. C. Ortega, J. S. Fu, G. D. Reed, J. C. Chow, J. G. Watson & J. A. Moncada-Herrera, (2008). A hybrid ARIMA and artificial neural networks model to forecast particulate matter in urban areas: The case of Temuco, Chile. Atmospheric Environment, 42(35), 8331-8340. DOI : 10.1016/j.atmosenv.2008.07.020
  12. M. D. Mallet. (2021). Meteorological normalisation of PM10 using machine learning reveals distinct increases of nearby source emissions in the Australian mining town of Moranbah. Atmospheric pollution research, 12(1), 23-35. DOI : 10.1016/j.apr.2020.08.001
  13. J. M. Lim. (2019). An Estimation Model of Fine Dust Concentration Using Meteorological Environment Data and Machine Learning. Journal of Information Technology Services, 18(1), 173-186. DOI : 10.9716/KITS.2019.18.1.173
  14. A. Ibrir, Y. Kerchich, N. Hadidi, H. Merabet & M. Hentabli. (2021). Prediction of the concentrations of PM1, PM2. 5, PM4, and PM10 by using the hybrid dragonfly-SVM algorithm. Air Quality, Atmosphere & Health, 14(3), 313-323. DOI: 10.1007/s11869-020-00936-1
  15. S. H. Sani, A. Rony, F. I. Karim, M. F. Mridha & M. A. Hamid, (2021). Evaluate and Predict Concentration of Particulate Matter (PM 2.5) Using Machine Learning Approach. In International Conference on Innovative Computing and Communications. Springer, Singapore. 771-785. DOI: 10.1007/978-981-15-5148-2_67
  16. K. Yoo, H. Yoo, J. M. Lee, S. K. Shukla & J. Park. (2018). Classification and regression tree approach for prediction of potential hazards of urban airborne bacteria during Asian dust events. Scientific reports, 8(1), 1-11. DOI : 10.1038/s41598-018-29796-7
  17. Y. Chun, J. Kim, J. C. Choi, K. O. Boo, S. N. Oh & M. Lee. (2001). Characteristic number size distribution of aerosol during Asian dust period in Korea. Atmospheric Environment, 35(15), 2715-2721. DOI : 10.1016/S1352-2310(00)00404-0
  18. W. Chueinta & P. K. Hopke. (2001). Beta gauge for aerosol mass measurement. Aerosol Science & Technology, 35(4), 840-843. DOI : 10.1080/027868201753227398
  19. D. S. Kim, Y. K. Cho & Y. H. Yoon. (2014). Development of a real-time monitoring device for measuring particulate matter, Particle and Aerosol Research, 10, 1-8. DOI : 10.11629/jpaar.2014.10.1.001
  20. M. Abadi, P. Barham, J. Chen, Z. Chen, A. Davis, J. Dean & X. Zheng. (2016). Tensorflow: A system for large-scale machine learning. In 12th USENIX symposium on operating systems design and implementation (OSDI 16) , 265-283.
  21. Environmental Protection Agency. (2007). Test procedure for class II and class III methods for PM 2.5 and PM, Legal Information Institute, 2007.