DOI QR코드

DOI QR Code

Prediction of fine dust PM10 using a deep neural network model

심층 신경망모형을 사용한 미세먼지 PM10의 예측

  • Received : 2018.02.05
  • Accepted : 2018.03.14
  • Published : 2018.04.30

Abstract

In this study, we applied a deep neural network model to predict four grades of fine dust $PM_{10}$, 'Good, Moderate, Bad, Very Bad' and two grades, 'Good or Moderate and Bad or Very Bad'. The deep neural network model and existing classification techniques (such as neural network model, multinomial logistic regression model, support vector machine, and random forest) were applied to fine dust daily data observed from 2010 to 2015 in six major metropolitan areas of Korea. Data analysis shows that the deep neural network model outperforms others in the sense of accuracy.

본 연구에서는 미세먼지 $PM_{10}$의 4가지 분류 등급인 '좋음, 보통, 나쁨, 매우 나쁨' 그리고 2가지 분류 등급인 '좋음 혹은 보통, 나쁨 혹은 매우 나쁨'을 예측하기 위해서 심층 신경망모형을 사용하였다. 2010년부터 2015년까지 국내 6개 대도시 지역에서 관측한 일별 미세먼지 데이터에 대하여 기존 분류기법인 신경망모형, 다항 로지스틱 회귀모형, Support Vector Machine, Random Forest을 적용했을 때에 비해서 심층 신경망모형의 정확도는 더 높아졌다.

Keywords

References

  1. Arno, C., Jessica, L., Erin, L., Viraj, P., and Anisha, A. (2015). Deep Learning with H2O (3rd ed), H2O.ai, Inc. California.
  2. Koo, Y. S., Yun, H. Y., Kwon, H. Y., and Yu, S. H. (2010). A development of $PM_{10}$ forecasting system, Journal of Korean Society for Atmospheric Environment, 26, 666-682. https://doi.org/10.5572/KOSAE.2010.26.6.666
  3. Korean Ministry of Environment (2016). If you know right now, it is seen. What on the earth is the fine dust? Korean Ministry of Environment.
  4. Kwon, J. H., Lim, Y. J., and Oh, H. S. (2015). Particulate Matter prediction using Quantile boosting, The Korean Journal of Applied Statistics, 28, 83-92. https://doi.org/10.5351/KJAS.2015.28.1.083
  5. Lee, H. J. (2011). Analysis of $PM_{10}$ concentration using auto-regressive error model at Pyeongtaek City in Korea, Journal of Korean Society for Atmospheric Environment, 27, 358-366. https://doi.org/10.5572/KOSAE.2011.27.3.358
  6. Lee, J. H., Kim, Y. M., and Kim, Y. K. (2017). Spatial panel analysis for PM2.5 concentrations in Korea, Journal of Korean Society for Atmospheric Environment, 27, 358-366.
  7. Lee, W. S. and Baek, C. R. (2014). The sparse vector autoregressive model for $PM_{10}$ in Korea, Journal of the Korean Data and Information Science Society, 25, 807-817. https://doi.org/10.7465/jkdi.2014.25.4.807
  8. National Institute of Environmental Research (2016). Annual report of air quality in Korea 2015, Korean Ministry of Environment.
  9. The H2O.ai team (2017). R Interface for H2O, CRAN.