Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

Korean Institute of Intelligent Systems (한국지능시스템학회)
권호 표지
DOI QR코드

DOI QR Code

Design of Summer Very Short-term Precipitation Forecasting Pattern in Metropolitan Area Using Optimized RBFNNs

최적화된 다항식 방사형 기저함수 신경회로망을 이용한 수도권 여름철 초단기 강수예측 패턴 설계

  • Kim, Hyun-Ki (Department of Electrical Engineering, The University of Suwon) ;
  • Choi, Woo-Yong (Department of Electrical Engineering, The University of Suwon) ;
  • Oh, Sung-Kwun (Department of Electrical Engineering, The University of Suwon)
  • 김현기 (수원대학교 공과대학 전기공학과) ;
  • 최우용 (수원대학교 공과대학 전기공학과) ;
  • 오성권 (수원대학교 공과대학 전기공학과)
  • Received : 2013.03.31
  • Accepted : 2013.09.05
  • Published : 2013.12.25
Download PDF
⟨ Previous Next ⟩

Abstract

The damage caused by Recent frequently occurring locality torrential rains is increasing rapidly. In case of densely populated metropolitan area, casualties and property damage is a serious due to landslides and debris flows and floods. Therefore, the importance of predictions about the torrential is increasing. Precipitation characteristic of the bad weather in Korea is divided into typhoons and torrential rains. This seems to vary depending on the duration and area. Rainfall is difficult to predict because regional precipitation is large volatility and nonlinear. In this paper, Very short-term precipitation forecasting pattern model is implemented using KLAPS data used by Korea Meteorological Administration. we designed very short term precipitation forecasting pattern model using GA-based RBFNNs. the structural and parametric values such as the number of Inputs, polynomial type,number of fcm cluster, and fuzzification coefficient are optimized by GA optimization algorithm.

최근 빈번히 일어나는 국지성 집중호우로 인해 피해가 급격히 증가하고 있다. 인구가 밀집한 수도권과 같은 경우 산사태와 토석류 및 홍수로 인해 인명 및 재산피해가 심각하다. 따라서 집중호우에 대한 예측의 중요성이 증가하고 있다. 우리나라 악천후 강수의 특징으로는 태풍과 집중호우로 구분된다. 이는 지속시간과 지역에 따라 차이를 보인다. 또한, 지역적인 강수는 계절에 따라 변동성이 크고 비선형적이기 때문에 강수를 예측하는데 어려움이 따른다. 본 논문에서는 기상청에서 현업으로 사용하는 초단기 기상 분석 및 예측시스템 (Korea Local Analysis and Prediction System; KLAPS)의 기상 관측 자료를 이용하여 초단기 호우 예측 패턴 모델을 구현한다. 그리고 악천후 시 피해가 큰 수도권을 중심으로 여름철 호우 특보를 예측한다. 유전자 알고리즘(Genetic Algorithm; GA) 기반 다항식 방사형 기저함수 신경회로망(Radial Basis Function Neural Networks; RBFNNs)을 이용하여 초단기 강수 예측 패턴 모델을 설계한다. 최적화된 분류기를 설계하기 위하여 유전자 알고리즘을 이용하여 주요 파라미터인 입력변수의 수, 다항식 차수, 퍼지화 계수, FCM(Fuzzy C-mean) 클러스터 수를 동조한다.

Keywords

References

  1. M. Hou, X. Han, "Constructive Approximation to Multivariate Function by Decay RBF Neural Network," IEEE Trans. on Neural Networks, Vol. 21, No. 9, pp. 1517-1523, 2010. https://doi.org/10.1109/TNN.2010.2055888
  2. M. Wallace, N. Tsapatsoulis, and S. Kollias, "Intelligent initialization of resource allocating RBF networks," Neural Networks, vol. 18, pp. 117-122, 2005. https://doi.org/10.1016/j.neunet.2004.11.005
  3. Y. Y. Fu, C. J. Wu, J. T. Jeng, and C. N. Ko, "Identification of MIMO systems using radial basis function networks with hybrid learning algorithm," Applied Mathematics and Computation, Vol. 213, pp.184-196, 2009. https://doi.org/10.1016/j.amc.2009.02.058
  4. S. K. Oh, W. D. Kim, and W. Pedrycz, ‟Polynomial based radial basis function neural networks(P-RBF NNs) realized with the aid of particle swarm opti mization," Fuzzy Sets and Systems, vol. 163, no. 1, pp. 54-77, 2011. https://doi.org/10.1016/j.fss.2010.08.007
  5. W. Pedrycz, "Conditional fuzzy clustering in the de sign of radial basis function neural networks",IEEE Trans. Neural Networks, vol.9, pp.601-612, July 1998. https://doi.org/10.1109/72.701174
  6. A. Aiyer, K. Pyun, Y. Z. Huang, D. B. O'Brien, and R. M. Gray, "Lloyd clustering of Gauss mixture models for image compression and classification," Signal Processing: Image Communication, vol. 20, pp. 459-485, 2005. https://doi.org/10.1016/j.image.2005.03.003
  7. H.-S. Park, W. Pedrycz and S.-K. Oh, "Granular Neural Networks and Their Development Through Context-Based Clustering and Adjustable Dimensionality of Receptive Fields", IEEE Trans. on Neural Networks, vol. 20, no. 10, pp. 1604-1616, 2009. https://doi.org/10.1109/TNN.2009.2027319
  8. A. Staiano. J. Tagliaferri, W. Pedrycz, "Improving RBF networks performance in regression tasks by means of a supervised fuzzy clustering"Automatic structure and parameter," Neurocomputing, Vol. 69, pp. 1570-1581, 2006 https://doi.org/10.1016/j.neucom.2005.06.014
  9. Z.Michalewicz, Genetic Algorithms+Data Structure =Evolution Programs, Springer-Verlag, 1992.
  10. D. E. Goldberg, Genetic Algorithm in search, Optimization & Machine Learning, Addison wesley, 1989.
  11. Holland, J. H., Adaptation In Natural and Artificial Systems. The University of Michigan Press, Ann Arbour. 1975.

Cited by

  1. Assessment of Typhoon Trajectories and Synoptic Pattern Based on Probabilistic Cluster Analysis for the Typhoons Affecting the Korean Peninsula vol.47, pp.4, 2014, https://doi.org/10.3741/JKWRA.2014.47.4.385
  2. Forecasting the Precipitation of the Next Day Using Deep Learning vol.26, pp.2, 2016, https://doi.org/10.5391/JKIIS.2016.26.2.093