Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Neural Networks-Genetic Algorithm Model for Modeling of Nonlinear Evaporation and Evapotranpiration Time Series. 2. Optimal Model Construction by Uncertainty Analysis

비선형 증발량 및 증발산량 시계열의 모형화를 위한 신경망-유전자 알고리즘 모형 2. 불확실성 분석에 의한 최적모형의 구축

  • Kim, Sung-Won (Dept. of Rail. and Civil Engr., Dongyang University) ;
  • Kim, Hung-Soo (School of Civil and Environ. Engr., Inha University)
  • 김성원 (동양대학교 철도토목학과) ;
  • 김형수 (인하대학교 환경토목공학부)
  • Published : 2007.01.31
Download PDF
⟨ Previous Next ⟩

Abstract

Uncertainty analysis is used to eliminate the climatic variables of input nodes and construct the model of an optimal type from COMBINE-GRNNM-GA(Type-1), which have been developed in this issue(2007). The input variable which has the lowest smoothing factor during the training performance, is eliminated from the original COMBINE-GRNNM-GA (Type-1). And, the modified COMBINE-GRNNM-GA(Type-1) is retrained to find the new and lowest smoothing factor of the each climatic variable. The input variable which has the lowest smoothing factor, implies the least useful climatic variable for the model output. Furthermore, The sensitive and insensitive climatic variables are chosen from the uncertainty analysis of the input nodes. The optimal COMBINE-GRNNM-GA(Type-1) is developed to estimate and calculate the PE which is missed or ungaged and the $ET_r$ which is not measured with the least cost and endeavor Finally, the PE and $ET_r$. maps can be constructed to give the reference data for drought and irrigation and drainage networks system analysis using the optimal COMBINE-GRNNM-GA(Type-1) in South Korea.

본 논문에서는 본 연구논제(2007)에서 개발된 COMBINE-GRNNM-GA(Type-1)으로부터 최적형태의 구조를 가진 모형을 구성하고, 입력층노드의 기상인자를 제거하기 위하여 불확실성 분석을 실시하였다. 훈련과정중에 가장 최소의 평활인자를 가진 입력층변수는 COMBINE-GRNNM-GA(Type-1)에서 제거되었으며, 변형된 COMBINE-GRNNM-GA(Type-1)은 기상학적 변수의 새로운 최소 평활인자를 구하기 위하여 재훈련된다. 최소 평활인자를 가지는 입력층 노드는 모형결과치에 대하여 가장 유용하지 않는 기상인자인 것을 암시하고 있다. 게다가, 민감하거나 민감하지 않은 기상인자들이 불확실성 분석을 통하여 선택되어진다. 최적 COMBINE-GRNNM-GA(Type-1)은 최소 비용과 노력으로 결측 혹은 미계측 증발접시 증발량과 계측되고 있지 않은 알팔파 기준증발산량을 산정하기 위하여 개발되었다 마지막으로 치적 COMBINE-GRNNM-GA(TyPe-1)을 이용하여 우리나라에서 전반적인 가뭄해석 및 관개배수 시스템 구축을 위한 참고자료를 제공할 수 있는 증발접시 증발량 지도 및 알팔파 기준증발산량 지도도 구축되어질 수 있다.

Keywords

References

  1. 김성원 (2003). '추계학적모형과 신경망모형을 연계한 병렬저수지군의 유입량산정.' 한국수자원학회 논문집, 한국수자원학회, 제36권, 제2호, pp. 195-209
  2. 김성원, 김형수 (2007). '비선형 증발량 및 증발산량 시계열의 모형화를 위한 신경망 유전자알고리즘 모형 1. 모형의 이론과 적용.' 한국수자원학회 논문집, 한국수자원학회, 제40권, 제 l호, pp. 73-88 https://doi.org/10.3741/JKWRA.2007.40.1.073
  3. Ayyub, B.M.(1998). Uncertainty modeling and analysis in civil engineering, CRC Press LLC, Salem, MA
  4. Ayyub, B.M., and Gupta, M.M. (1997). Uncertainty analysis in engineering and sciences : Fuzzy logic, statistics and neural network approach, Kluwer Academic, Boston, MA
  5. Ayyub, B.M., and McCuen, R.H. (1997). Probability, Statistics, and Reliability for Engineers and Statistics. Chapman & Hall/CRC, New York, NY
  6. Beck, M.B. (1987). 'Water quality modeling : A review of the analysis of uncertainty.' Water Resour. Res., Vol. 23, No.5, pp. 1393-1441 https://doi.org/10.1029/WR023i008p01393
  7. Food and Agriculture Organization(FAO). (1990). Report on the expert consultation on revision of FAD methodologies for crop water requirement. Land and Water Devel. Div., Rome, Italy
  8. Gardner, R.H., O'Neill, R.V., Mankin, J.B., and Carney, J.H. (1981). 'A comparison of sensitivity and error analysis based on a stream ecosystem model.' Ecological Modeling, Vol. 12, pp. 173-190 https://doi.org/10.1016/0304-3800(81)90056-9
  9. Guyonnet, D., Come, B., Perrochet, P., and Parriaux, A. (1999). 'Comparing two methods for addressing uncertainty in risk assesment.' J. Environ. Engr., ASCE, Vol. 125, No.6, pp. 660-666 https://doi.org/10.1061/(ASCE)0733-9372(1999)125:7(660)
  10. Hornberger, G.M., and Spear, R.C. (1981). 'An approach to the preliminary analysis of environmental systems.' J. Envir. Mgmt., Vol. 12, pp. 7-18
  11. Jaffe, P.R., and Ferrara, R.A. (1984). 'Modeling sediment and water column interactions for hydrophobic pollutants : Parameter discrimination and model response to input uncertainty.' Water Res., Vol. 18, No.9, pp. 1169-1174 https://doi.org/10.1016/0043-1354(84)90234-3
  12. Johnson, P.A., and Ayyub, B.M. (1996). 'Modeling uncertainty in prediction of pipe scour.' J. Hydrau. Engr., ASCE, Vol. 122, No.2, pp. 66-72 https://doi.org/10.1061/(ASCE)0733-9429(1996)122:2(66)
  13. Kim, S., and Cho, J.S. (2003). 'Uncertainty analysis of flood stage forecasting using time-delayed patterns in the small catchment.' Intr. Symp. on Disaster Mitigation and Basin-Wide Water Management Niigata 2003, IAHR/AIRH, Niigata, Japan, pp. 465-474
  14. Kim, S., and Kim, H.S. (2006). 'Reliability analysis of hydrological time series using neural networks model 2. Uncertainty analysis of input data information.' Submitted to J. of American Water Resources Association
  15. Melching, C.S. (1992). 'An improved first-order reliability approach for assessing uncertainties in hydrologic modeling.' J. Hydrol., Vol. 132, pp. 157-177 https://doi.org/10.1016/0022-1694(92)90177-W
  16. Moore, R.E. (1979). Method and applications of interval analysis. SIAM, PA
  17. McCuen, R.H. (1993). Microcomputer applications in statistical hydrology. Prentice Hall, NJ
  18. Neuroshell 2 (1993). Ward systems group. Inc., MD
  19. Pedrycz, W., and Gomide, F.(1998). An introduction to fuzzy sets : Analysis and design Cambridge, MA
  20. Salas, J.D., Smith, R.A., Tabios III, G.Q., and Heo, J.H. (2001). Statistical computing techniques in water resources and environmental engineering. Unpublished book in CE622, Colorado State University, Fort Collins, CO
  21. Yeh, K.C., and Tung, Y.K. (1993). 'Uncertainty and sensitivity analyses of pit-migration model.' J. of Hydrau. Engr., ASCE, Vol. 119, No.2, pp. 262-283 https://doi.org/10.1061/(ASCE)0733-9429(1993)119:2(262)