DOI QR코드

DOI QR Code

Prediction of Daily Maximum SO2 Concentrations Using Artificial Neural Networks in the Urban-industrial Area of Ulsan

인공신경망 모형을 이용한 울산공단지역 일 최고 SO2 농도 예측

  • Lee, So-Young (Forecast Research Laboratory, National Institute of Meteorological Research, KMA) ;
  • Kim, Yoo-Keun (Division of Earth Environmental System, Pusan National University) ;
  • Oh, In-Bo (Division of Earth Environmental System, Pusan National University) ;
  • Kim, Jung-Kyu (Tae-hwa River Managing Agency, Ulsan metrocity)
  • 이소영 (국립기상연구소 예보연구팀) ;
  • 김유근 (부산대학교 지구환경시스템학부) ;
  • 오인보 (부산대학교 지구환경시스템학부) ;
  • 김정규 (울산시 태화강관리단)
  • Published : 2009.02.28

Abstract

Development of an artificial neural network model was presented to predict the daily maximum $SO_2$ concentration in the urban-industrial area of Ulsan. The network model was trained during April through September for 2000-2005 using $SO_2$ potential parameters estimated from meteorological and air quality data which are closely related to daily maximum $SO_2$ concentrations. Meteorological data were obtained from regional modeling results, upper air soundings and surface field measurements and were then used to create the $SO_2$ potential parameters such as synoptic conditions, mixing heights, atmospheric stabilities, and surface conditions. In particular, two-stage clustering techniques were used to identify potential index representing major synoptic conditions associated with high $SO_2$ concentration. Two neural network models were developed and tested in different conditions for prediction: the first model was set up to predict daily maximum $SO_2$ at 5 PM on the previous day, and the second was 10 AM for a given forecast day using an additional potential factors related with urban emissions in the early morning. The results showed that the developed models can predict the daily maximum $SO_2$ concentrations with good simulation accuracy of 87% and 96% for the first and second model. respectively, but the limitation of predictive capability was found at a higher or lower concentrations. The increased accuracy for the second model demonstrates that improvements can be made by utilizing more recent air quality data for initialization of the model.

Keywords

$SO_2$;Urban-industrial area;Potential parameters;Artificial neural network;Cluster analysis

References

  1. 구윤서, 2005, 지역대기환경용량평가 및 배출허용 기준의 효율적인 적용방안, 울산지역환경기술개발센터, 225pp
  2. Oanh N. T., Chutimon P., Ekbordin W., Supat W., 2005, Meteorological pattern classification and application for forecasting air pollution episode potential in a mountain-valley area, Atmos. Environ., 39(7), 1211-1225 https://doi.org/10.1016/j.atmosenv.2004.10.015
  3. 김유근, 이화운, 전병일, 홍정혜, 1996, 부산연안역의 오존 농도에 미치는 해풍의 영향, 한국환경과학회지, 5(3), 265-275
  4. 김용준, 1997, 현업운영 가능한 서울지역의 일 최고 대기오염도 예보모델 개발 연구, 한국대기보전학회지, 13(1), 79-89
  5. 김유근, 이소영, 임윤규, 송상근, 2007, 중회귀 모형을 이용한 울산지역 오존 포텐셜 모형의 설계 및 평가, 한국대기환경학회지, 23(1), 14-28 https://doi.org/10.5572/KOSAE.2007.23.1.014
  6. 환경부, 2004, 대기환경월보 2004년 6월, 60pp
  7. Davis R. E., Kalkstein L. S., 1990, Development of an automated spatial synoptic climatological classification, Int. J. Climatol., 10(8), 769-794 https://doi.org/10.1002/joc.3370100802
  8. 손건태, 2001, 전산통계개론(개정판), 자유아카데미, 330pp
  9. Dudhia J., 1993, A nonhydrostatic version of the penn statelNCAR mesoscale model: variation tests an simulation of an Atlantic cyclone and cold front, Mon. Wea. Rev., 121(5), 1493-1513 https://doi.org/10.1175/1520-0493(1993)121<1493:ANVOTP>2.0.CO;2
  10. Brain S. E., 1993, Cluster analysis, 3rd ed., Halsted Press, 170pp
  11. Potts W. J. E., 2000, Neural network modeling course notes, SAS Institutes Inc., 240-259
  12. 허정숙, 김동술, 1993, 다변량 통계분석을 이용한 서울시 고농도 오존의 예측에 관한 연구 한국대기보전학회지, 9(3), 207-215
  13. 이영준, 2004, 고정오염원에서 발생하는 SO_2 배출량 저간을 위한 효율적인 환경정책수단의 연구, 한국환경과학회지, 339-347 https://doi.org/10.5322/JES.2004.13.4.339
  14. 전병일, 김유근, 1998, 부산연안에서 관측된 저층대기의 특성에 관한 연구, 한국환경과학회지, 7(2), 195-201
  15. Berlyand M. E., 1991, Prediction and regulation of air pollution, Kluwer Academic Pub., 312pp
  16. 김용국, 이종범, 1994, 하계의 일 최고 오존농도 예측을 위한 신경망모델의 개발, 한국대기보전학회지, 10(4), 224-232
  17. 이종범, 1991, 중부지방 각지의 대기오염 잠재력에 관한 연구, 한국대기보전학회지, 7(1), 41-47
  18. Eder B. K., Davis J. M., Bloomfield P., 1994, An automated classification scheme designed to better elucidate the dependence of ozone on meteorology, J. Appl. Meteo., 33(10), 1182-1199 https://doi.org/10.1175/1520-0450(1994)033<1182:AACSDT>2.0.CO;2
  19. Ioannis C. Z., Dimitrios M., Christos S. Z., Alkiviadis F. B., 1995, Forecasting peak pollutant levels from meteorological variables., Atmos. Environ., 29(24), 3703-371l https://doi.org/10.1016/1352-2310(95)00131-H
  20. 김유근, 2003, 울산의 대기오염 기상조건과 기상여건에 따른 대기오염실태조사, 울산지역환경기술개발센터, 244pp
  21. 박정균, 이동규, 1998, 군집분석에 의한 아시아 동안에서 급격히 발달하는 저기압의 분류와 그 발달기구, 한국기상학회지, 34(4), 523-537
  22. 이화운, 원경미, 정우식, 오은주, 김민선, 도우곤, 2002, 해륙풍을 고려한 대기오염물질농도의 수치 모의, 한국환경학회지, 11(7), 933-943
  23. 이보람, 박순웅, 1997, 종관 기상 상태를 고려한 한반도 대기 오염 퍼텐셜 예측법, 한국기상학회지, 33(4), 641-656
  24. Cheng S., Lam K. C., 2000, Synoptic typing and its application to the assessment of climatic impact on concentrations of sulfur dioxide and nitrogen oxides in Hong Kong, Atmos. Environ., 34(4), 585-594 https://doi.org/10.1016/S1352-2310(99)00194-6
  25. 전병일, 김유근, 이화운, 황수진, 1996, 해풍효과에 의한 저층대기구조 변화의 측정, 한국환경과학회지, 5(4), 441-451