Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지

Spatial-Temporal Drought Analysis of South Korea Based On Neural Networks

신경망을 이용한 우리나라의 시공간적 가뭄의 해석

  • Published : 1999.02.01
Download PDF
⟨ Previous Next ⟩

Abstract

A new methodology to analyze and quantify regional meteorological drought based on annual precipitation data has been introduced in this paper In this study, based on posterior probability estimator and Bayesian classifier in Spatial Analysis Neural Network (SANN), point drought probabilities categorized as extreme, severe, mild, and non drought events has been defined, and a Bayesian Drought Severity Index (BPSI) has been introduced to classify the region of interest into four drought severities. In addition, to estimate the regional drought severity for the entire region, regional extreme, severe, mild, and non drought probabilities which are the areal averages of point drought probabilities over the region has been computed and applied. In this study, the proposed methodology has been applied to analyze the regional drought of South Korea during 1967-1996 years. The drought severity for the whole South Korea was defined spatially at each year and each year was classified in a drought severity criterion. The results may be useful for water manager to understand the South Korean drought with respect to the spatial and temporal variation.

본 연구에서는 공간적으로 분포되어 있는 연강우량 자료를 이용한 지역 기상학적인 가뭄을 정의하고 해석하는 모형을 제시하였다. 비선형. 비매개변수법에 기초한 공간 해석 신경망(Spatial Analysis Neural Network; SANN)모형을 이용하여, 각 년에 대하여 공간의 임의 점에서의 극심, 심 경심, 및 비 가뭄 확률을 전 대상 지역에 대하여 산출을 통하여 가뭄확률도를 작성하며, Bayesian 가뭄 심도 지수(BDSI)를 통하여 전 대상 지역을 가장 적적하게 극심, 심, 경심, 비 가뭄 지역으로 분류하는 방법을 제시하였다. 또한, 각 년의 대표적인 가뭄의 형태를 제시하여 줄 수 있는 지역 가뭄 확률과 지역 가뭄 확률 지수를 소개하였다. 이 모든 시공간적 가뭄 해석의 방법은 실제로 우리나라(남한) 전역에 대하여 실시하여, 과거 1967년부터 1996년 까지의 공간적이고 시간적인 가뭄의 발생 현황과 그 특징을 조사 하였다. 본 연구는 우리나라 장기 수자원 개발 및 유역 관리를 위한 공간적이고도 시간적인 가뭄 정보를 제공하였다는 데 그 의의가 있을 것이다.

Keywords

References

  1. Journal of Climate v.9 Evaluation of the Palmer drought index on the Canadian prairies Akinremi, O. O.;McGinn, S. M.;Barr, A. G.
  2. J. of Irrigation and Drainage Engineering v.117 no.6 Investigation of precipitation drought by use of Kriging method Chang, T. J.
  3. Journal of Hydrology v.173 Regional frequency analysis of annual maximum streamflow drought Clausen, B.;Pearson, C. P.
  4. Water Resour. Res. v.16 no.2 On the statistical characteristics of drought events Dracup, J. A.;Lee, K. S.;Paulson Jr., E. G.
  5. Rainfall deciles as drought indicators Gibbs, W. J.;Maher, J. V.
  6. Water Resources Bulletin v.28 no.6 Spatial comparability of the Palmer drought severity index Guttman, N. B.;Wallis, J. R.;Hosking, J. R. M.
  7. Monthly Weather Review v.109 no.10 The 1980 summer heat wave and drought in historical perspective Karl, T. R.;Quayle, R. G.
  8. M.S. thesis , Colo. State University A stochastic analysis of spatial droughts in Colorado Kingery Jr., R.K.
  9. 8th Con. on Applied Climatology The relationship of drought frequency and duration to time scales MacKee, T. B.;Doesken, N. J.;Kleist, J.
  10. Pattern Recognition v.25 no.10 A probabilistic model for evaluation of neural networks classifiers Musavi, M. T.;Chan, K. H.;Hummels, D. M.;Kalantri, K.;Ahmed, W.
  11. Meteorological drought Palmer, W. C.
  12. Water Resources Research Spatial analysis and neural network modeling for hydrological and environmental data Shin, H.-S.;Salas, J. D.
  13. J. of Environmental Hydrology v.5 no.4 Use of the spatial analysis neural network(SANN) method for regional groundwater contamination decision-making Shin, H.-S.
  14. International Journal of Climatology v.12 Spatial patterns of drought frequency and duration in the cintigous USA based on multiple drought event definitions Soule, P. T.
  15. Area-deficit-intensity chracteristics of drought Tase, N.
  16. Hydrology Paper 23 An objective approach to definitions and investigations of conditional hydrologic droughts Yevjevich, V.