Journal of the Korea Institute of Information and Communication Engineering (한국정보통신학회논문지)

The Korea Institute of Information and Commucation Engineering (한국정보통신학회)
권호 표지
DOI QR코드

DOI QR Code

Separation Prediction Model by Concentration based on Deep Neural Network for Improving PM10 Forecast Accuracy

PM10 예보 정확도 향상을 위한 Deep Neural Network 기반 농도별 분리 예측 모델

  • Cho, Kyoung-woo (Department of Electrical, Electronics & Communication Engineering, Korea University of Technology and Education(KOREATECH)) ;
  • Jung, Yong-jin (Department of Electrical, Electronics & Communication Engineering, Korea University of Technology and Education(KOREATECH)) ;
  • Lee, Jong-sung (Department of Electrical, Electronics & Communication Engineering, Korea University of Technology and Education(KOREATECH)) ;
  • Oh, Chang-heon (Department of Electrical, Electronics & Communication Engineering, Korea University of Technology and Education(KOREATECH))
  • Received : 2019.09.29
  • Accepted : 2019.10.14
  • Published : 2020.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

The human impact of particulate matter are revealed and demand for improved forecast accuracy is increasing. Recently, efforts is made to improve the accuracy of PM10 predictions by using machine learning, but prediction performance is decreasing due to the particulate matter data with a large rate of low concentration occurrence. In this paper, separation prediction model by concentration is proposed to improve the accuracy of PM10 particulate matter forecast. The low and high concentration prediction model was designed using the weather and air pollution factors in Cheonan, and the performance comparison with the prediction models was performed. As a result of experiments with RMSE, MAPE, correlation coefficient, and AQI accuracy, it was confirmed that the predictive performance was improved, and that 20.62% of the AQI high-concentration prediction performance was improved.

미세먼지의 인체 영향이 밝혀지며 예보정확도 개선에 대한 요구가 증가하고 있다. 이에 기계 학습 기법을 도입하여 예측 정확성을 높이려는 노력이 수행되고 있으나, 저농도 발생 비율이 매우 큰 미세먼지 데이터로 인해 전체 예측 성능이 떨어지는 문제가 있다. 본 논문에서는 PM10 미세먼지 예보 정확도 향상을 위해 농도별 분리 예측 모델을 제안한다. 이를 위해 천안 지역의 기상 및 대기오염 인자를 활용하여 저, 고농도별 예측 모델을 설계하고 전 영역 예측 모델과의 성능 비교를 수행하였다. RMSE, MAPE, 상관계수 및 AQI 정확도를 통한 성능 비교 결과, 전체 기준에서 예측 성능이 향상됨을 확인하였으며, AQI 고농도 예측 성능의 경우 20.62%의 성능 향상이 나타났음을 확인하였다.

Keywords

References

  1. K. Kuklinska, L. Wolska, and J. Namiesnik, "Air quality policy in US and the EU-A review," Atmospheric Pollution Research, vol. 6, no. 1, pp.129-137, Jan. 2015. https://doi.org/10.5094/APR.2015.015
  2. J. Y. Ye, "Global environment institution and middle power : The case of the convention on long-range transboundary air pollution (CLTAP)," Journal of International Politics, vol. 14, no. 1, pp.33-57, Mar. 2009.
  3. J. Y. Choi, "The convention on long-range transboundary air pollution (CLRTAP) and international cooperation for the resolution of particulate matters," National Assembly Reaearch Service, Issues and Perspectives, vol. 1296, Apr. 2017.
  4. J. Y. Moon, E. M. Kim, and E. H. Choi, "International responses to transboundary air pollution and there implications," Korea Institute for International Economic Policy, Research paper 17-11, Dec. 2017.
  5. A. Valavanidis, K. Fiotakis, and T. Vlachogianni, "Airborne particulate matter and human health: Toxicological assessment and importance of size and composition of particles for oxidative damage and carcinogenic mechanisms," Journal of Environmental Science and Health, Part C, vol. 26, no. 4, pp. 339-362, 2008. https://doi.org/10.1080/10590500802494538
  6. J. O. Anderson, J. G. Thundiyil, and A. Stolbach, "Clearing the air: A review of the effects of particulate matter air pollution on human health," Journal of Medical Toxicology, vol. 8, no. 2, pp. 166-175, 2012. https://doi.org/10.1007/s13181-011-0203-1
  7. K. H. Kim, E. Kabir, and S. Kabir, "A review on the human health impact of airborne particulate matter," Environment international, vol. 74, pp. 136-143, 2015. https://doi.org/10.1016/j.envint.2014.10.005
  8. N. J. Hime, G. B. Marks, and C. T. Cowie, "A comparison of the health effects of ambient particulate matter air pollution from five emission sources," International Journal of Environmental Research and Public Health, vol. 15, no. 6, 2018.
  9. World Health Organization (WHO), "Health effects of particulate matter: Policy implications for countries in eastern europe, caucasus and central asia," Regional Office for Europe, 2013.
  10. National Institude of Environmental Research, "A study of data accuracy improvement for national air quality forecasting(III)," Research paper 11-1480523-002809-01, 2016.
  11. A. Chaloulakou, G. Grivas, and N. Spyrellis, "Neural network and multiple regression models for PM10 prediction in Athens: A comparative assessment," Journal of the Air & Waste Management Association, vol. 53, no. 10, pp. 1183-1190, 2003. https://doi.org/10.1080/10473289.2003.10466276
  12. M. M. Dedovic, S. Avadakovic, I. Turkovic, N. Dautbasic, and T. Konjic, "Forecasting PM10 concentrations using neural networks and system for improving air quality," in proceeding of 2016 XI International Symposium on Telecommunications (BIHTEL), Sarajevo, pp. 1-6, 2016.
  13. J. W. Cha, and J. Y. Kim, "Development of data mining algorithm for implementation of fine dust numerical prediction model," Journal of the Korea Institute of Information and Communication Engineering, vol. 22, no. 4, pp. 595-601, 2018. https://doi.org/10.6109/JKIICE.2018.22.4.595
  14. K. W. Cho, J. S. Lee, and C. H. Oh, "Particulate matter AQI index prediction using multi-layer perceptron network," in Proceeding Conference on Korea Information and Communication Engineering, Daejeon, vol. 23, no. 1, pp. 540-541, May. 2019.
  15. K. W. Cho, Y. J. Jung, J. S. Lee, and C. H. Oh, "Separation prediction model by concentration based on multi-layer perceptron for improving particulate matters accuracy," in Proceeding Conference on Korea Information and Communication Engineering, Daejeon, vol. 23, no. 2, pp. 658-660, Oct. 2019.
  16. Ministry of Environment, If you know right away. Fine dust, what is it?, Apr. 2016.
  17. G. N. Bae, "Scientific understanding and reasonable judgment of particulate matter pollution," The Board of Audit and Inspection of Korea, Inspection, vol. 131, pp.20-27, Jul. 2016.
  18. J. M. Han, J. G. Kim, and K. H. Cho, "Verify a causal relationship between fine dust and air condition-weather data in selected area by contamination factors," The Korea Journal of BigData, vol. 2, no. 1, pp.17-26, Feb. 2017. https://doi.org/10.36498/kbigdt.2017.2.2.17
  19. M. K. Shin, C. D. Lee, H. S. Ha, C. S. Choe, and Y. H. Kim, "The influence of meteorological factors on PM10 concentration in Incheon," Journal of Korean Society for Atmospheric Environment, vol. 23, no. 3, pp.322-331, Jun. 2007. https://doi.org/10.5572/KOSAE.2007.23.3.322
  20. X. Zhou, "Statistical characteristics of meteorological factors and particulate matters(PM10, PM2.5) in Seoul," M.S. dissertation, Seoul National University of Science and Technology, 2014.
  21. K. W. Cho, Y. J. Jung, C. G. Kang, and C. H. Oh, "Conformity assessment of machine learning algorithm for particulate matter prediction," Journal of the Korea Institute of Information and Communication Engineering, vol. 23, no. 1, pp. 20-26, Jan. 2019. https://doi.org/10.6109/JKIICE.2019.23.1.20