Journal of Korean Society for Atmospheric Environment (한국대기환경학회지)

Korean Society for Atmospheric Environment (한국대기환경학회)
권호 표지

Development of Neural Network Model for Pridiction of Daily Maximum Ozone Concentration in Summer

하계의 일 최고 오존농도 예측을 위한 신경망모델의 개발

  • Published : 1994.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

A new neural network model has been developed to predict short-term air pollution concentration. In addition, a multiple regression model widely used in statistical analysis was tested. These models were applied for prediction of daily maximum ozone concentration in Seoul during the summer season of 1991. The time periods between May and September 1989 and 1990 were utilized to train set of learning patterns in neural network model, and to estimate multiple regression model. To evaluate the results of the different models, several Performance indices were used. The results indicated that the multiple regression model tended to underpredict the daily maximum ozone concentration with small r$^{2}$(0.38). Also, large errors were found in this model; 21.1 ppb for RMSE, 0.324 for NMSE, and -0.164 for MRE. On the other hand, the results obtained from the neural network model were very promising. Thus, we can know that this model has a prominent efficiency in the adaptive control for the non-linear multi- variable systems such as photochemical oxidants. Also, when the recent new information was added in the neural network model, prediction accuracy was increased. From the new model, the values of RMSE, NMSE and r$^{2}$ were 13.2ppb, 0.089, 0.003 and 0.55 respectively.

Keywords

References

  1. 뉴로 컴퓨터 박민용;최항식
  2. 제3회 인공지능,신경망 및 퍼지시스템 종합학술대회 논문집 신경회로망을 이용한 오존농도의 예측에 관한 연구 이상점;김용국;이종호
  3. 인하대학교 석사논문집 신경회로망을 이용한 기상자료의 분석 및 예측에 관한 연구 이상점
  4. 기상연구논문집 v.8 no.1 서울지역의 광화학 오염농도 추정을 위한 중회귀모델 개발 이선기;이종범
  5. 한국대기보전학회지 v.7 no.1 중부지방 각지의 대기오염잠재력에 관한 연구 이종범
  6. 강원대학교 석사논문집 수도권 대기오염 물질이 풍하 지역의 오존농도에 미치는 영향예측을 위한 광화학 라그란지안 모델의 적용 이태형
  7. 한국대기보전학회지 v.9 no.4 다변량해석을 이용한 서울시 하계 스모그의 형태분류 홍낙기;이종범;김용국
  8. Atmospheric Environment v.20 Some Chracteristics of ozone formation in the urban plume of St.Louis, Mo. Altshuller, A. P.
  9. Atmospheric Environment v.27B no.2 A neural network-based method for short-term predictions of ambient SO₂concentrations in highly polluted industrial areas of complex terrain Boznar,M.;M.Lesjak;p.mlakar
  10. Atmospheric Environment v.26A no.5 An intercomparison of semiempirical diffusion models under low wind speed, stable conditions Cirillo,M.C.;A.A.Poli
  11. Clean Air Act Amendments National Acid Precitipation Assessment Progran Report 5:Evaluation of regional acidic deposition models PartⅡ DennisR.L.(et al.)
  12. 85th annual A&WMA meeting Simulation of ozone reduction strategies for Mexico City utilizing the Urban Airshed Model Greenfield,S.M.;G.Z.Witten;T.C. Myers;S.G. Douglas;J.F. Fieber
  13. Atmospheric Environment v.24A no.10 Observational evidence of ozone depletion by nitricoxide at 40km downwind of a medium size city Leahey,D.M.;M.C.Hansen
  14. Springer Patten analysis and understanding(2nd ed.) Niemann,H.
  15. J.Air & Waste Manage. Assoc. v.43 Atmospheric chemistry of tropospheric ozone formation:Scientific and regulatory implications Pitts,F.B.
  16. MIT Press, Cambridge, MA Parellel distributed processing 1, 2. Rumelhart,D.E.;J.L.McClelland
  17. Fundamentals of air pollution(2nd ed.) Stern,A.C.;R.W.Boubel;D.B. Turner;D.L. Fox