Spatial Information Research

Korea Spatial Information Society (대한공간정보학회)
권호 표지
DOI QR코드

DOI QR Code

Identifying the Optimal Number of Homogeneous Regions for Regional Frequency Analysis Using Self-Organizing Map

자기조직화지도를 활용한 동일강수지역 최적군집수 분석

  • Kim, Hyun Uk (High Impact Weather Research Center, National Institute of Meteorological Research) ;
  • Sohn, Chul (Dept. of Urban Planning and Real Estate, Gangneung-Wonju National University) ;
  • Han, Sang-Ok (High Impact Weather Research Center, National Institute of Meteorological Research)
  • Received : 2012.06.11
  • Accepted : 2012.12.06
  • Published : 2012.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

In this study, homogeneous regions for regional frequency analysis were identified using rainfall data from 61 observation points in Korea. The used data were gathered from 1980 to 2010. Self organizing map and K-means clustering based on Davies-Bouldin Index were used to make clusters showing similar rainfall patterns and to decide the optimum number of the homogeneous regions. The results from this analysis showed that the 61 observation points can be optimally grouped into 6 geographical clusters. Finally, the 61 observations points grouped into 6 clusters were mapped regionally using Thiessen polygon method.

우리나라의 동일강수지역에 대한 구분은 기상학적으로 의미를 지닐 뿐만 아니라 장기예보를 위한 자료로 활용된다. 또한 최근 들어 수문학에서는 확률강수량을 산정하기 위해 지금까지 사용되어 온 지점빈도해석의 단점을 보완한 지역빈도해석방법의 활용이 적극 제시되고 있다. 이에 따라 동일강수지역의 군집화에 대한 연구의 필요성이 증가하게 되었다. 본 연구에서는 1980년부터 2010년까지 61개 지상관측지점의 자료를 이용하여 자기조직화지도 군집기법으로 동일강수 지역을 군집화하고 K-means Clustering과 Davies-Bouldin Index를 적용하여 우리나라의 동일강수지역에 대해 6개의 최적 군집 개수를 산출하였다. 그리고 최종적으로 GIS에 기반한 Thiessen Polygon을 활용하여 동질지역의 지역화 하였다.

Keywords

References

  1. Agarwal, P; Andre, S, 2008, Self Organizing Maps:Applications in Geographic Information Science, West Sussex, England : Wiley
  2. Heo, J. H; Lee, Y. S; Shin H. J; Kim, K. D. 2007, Application of regional Rainfall Frequency Analysis in South Korea(I):Rainfall Quantile Estimation, Korean Society of Civil Engineers, 27(2B):101-111
  3. Hosking, J. R. M; Walliis, J. R. 1997, Regional Frequency Analysis : An Approach Based on L -Moments, Cambridge University Press, Cambridge
  4. Jeong, J. C. 2005, The Temporal and Spatial Distribution Analysis of Red Tide using GIS, The Journal of GIS Association of Korea, 14(3):253-260
  5. Korea Meteorological Administration, 2012, http://www.kma.go.kr
  6. Ko, J. W; Baek, H. J; Kwon, W.T. 2005, The Characteristics of Precipitation and Regionalization during Rainy Season in Korea, Asia-Pacific Journal of Atmospheric Science, 41(1):101-114.
  7. Lee, D. K; Park, J. G. 1999, Regionalization of Summer Rainfall in South Korea Using Cluster Analysis, Asia-Pacific Journal of Atmospheric Science, 35(4):511-518.
  8. Lee, S. S; Chang, E. M. 2009, Application of GIS to Typhoon Risk Assessment, The Journal of GIS Association of Korea, 17(2):243-249
  9. Lin, G. F; Chen, L. H. 2006, Identification of homogeneous regions for regional frequency analysis using the self-organizing map, Journal of Hydrology, 324:1-9. https://doi.org/10.1016/j.jhydrol.2005.09.009
  10. Lu, H. C; Chang, C. L; Hsieh, J. C. 2006, Classification of $PM_{10}$ distributions in Taiwan, Atmospheric Environment, 40: 1452-1463 https://doi.org/10.1016/j.atmosenv.2005.10.051
  11. Moon, Y. S. 1990, Division of Precipitation Regions in Korea through the Cluster Analysis, Asia-Pacific Journal of Atmospheric Science, 26(4):203-215.
  12. Nishiyama, K; Endo, S; Jinno, K; Bertacchi Uvo, C; Olsson, J; Berndtsson, R. 2007, Identification of typical synoptic patterns causing heavy rainfall in the rainy season in Japan by a Self-Organizing Map, Atmospheric Research, 83:185-200. https://doi.org/10.1016/j.atmosres.2005.10.015
  13. Park, H, W; Ryu, C. S. 2005, The Variation Patterns over a Period of 10 Days and Precipitation Regions of Summer Precipitation in Korea, The Korean Earth Science Society, 26(5):417-428.
  14. Park, K. G; Lee, S. M. 1993, A Regionalization of Annual Precipitation over South Korea, Asia-Pacific Journal of Atmospheric Science, 29(2):117-126.
  15. Sohn, C. 2011, Identification of Spatial Housing Submarkets in the Capital Region Using Self Organizing Map and Chow Test, The Korea Spatial Review, 70: 151-166 https://doi.org/10.15793/kspr.2011.70..009
  16. Um, M. J; Jeong, C. S; Nam, W. S; Jung, Y. H; Heo, J. H. 2011, The Analysis of Optimal Cluster Number of Precipitation Region with Dunn Undex, Korea Water Resources Association, EXCO, May 19-20
  17. Vesanto, J; Alhoniemi, E. 2000, Clustering of the Self-Organizing Map, IEEE Transactions on Neural Networks, 11(3): 586-600. https://doi.org/10.1109/72.846731
  18. Yao, X, 2007, Where are Public Transit Needed Examining Potential Demand for Public Transit for Commuting Trips, Computers, Enviroment and Urban Systems, 31: 535-550 https://doi.org/10.1016/j.compenvurbsys.2007.08.005
  19. Yoon, Y, N, 2007, Hydrology basic and applcations( 수문학 기초와 응용), Cheong Moon Gak, p. 949.

Cited by

  1. Urban Growth Prediction each Administrative District Considering Social Economic Development Aspect of Climate Change Scenario vol.21, pp.2, 2013, https://doi.org/10.7319/kogsis.2013.21.2.053
  2. Analysis on Rainfall Pattern During Typhoons Using Self-Organizing Map vol.17, pp.4, 2017, https://doi.org/10.9798/kosham.2017.17.4.55
  3. Classification of Homogeneous Regions of Strong Wind and Gust Wind in Korea vol.16, pp.None, 2020, https://doi.org/10.2151/sola.2020-024
  4. Study on the Association of Casualties and Classification of Heat Wave Weather Patterns in South Korea Using K-Means Clustering Analysis vol.20, pp.3, 2012, https://doi.org/10.9798/kosham.2020.20.3.11
  5. Regional classification of total suspended matter in coastal areas of South Korea vol.254, pp.None, 2012, https://doi.org/10.1016/j.ecss.2021.107339