Journal of the Korean Institute of Intelligent Systems (한국지능시스템학회논문지)

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

DOI QR Code

Design of Meteorological Radar Echo Classifier Using Fuzzy Relation-based Neural Networks : A Comparative Studies of Echo Judgement Modules

FNN 기반 신경회로망을 이용한 기상 레이더 에코 분류기 설계 : 에코판단 모듈의 비교 분석

  • Ko, Jun-Hyun (Dept of Electrical Engineering, The University of Suwon) ;
  • Song, Chan-Seok (Dept of Electrical Engineering, The University of Suwon) ;
  • Oh, Sung-Kwun (Dept of Electrical Engineering, The University of Suwon)
  • Received : 2014.03.09
  • Accepted : 2014.09.23
  • Published : 2014.10.25
Download PDF
⟨ Previous Next ⟩

Abstract

There exist precipitation echo and non-precipitation echo in the meteorological radar. It is difficult to effectively issue the right weather forecast because of a difficulty in determining these ambiguous point. In this study, Data is extracted from UF data of meteorological radar used. Input and output data for designing two classifier were built up through the analysis of the characteristics of precipitation and non-precipitation. Selected input variables are considered for better performance and echo classifier is designed using fuzzy relation-based nueral network. Comparative studies on the performance of echo classifier are carried out by considering both echo judgement module 1 and module 2.

기상레이더에는 강수에코와 비강수 에코가 섞여 존재한다. 이런 모호한 지점의 판단이 난해함으로 정확한 일기 예보를 하기는 매우 어려운 일이다. 본 논문에서는 기상청 레이더의 UF 데이터로부터 데이터를 추출하였다. 설계하는 두 분류기의 입출력 데이터는 강수 에코와 비 강수 에코의 특성분석을 통해 구성된다. 더 좋은 성능을 나타나는 입력변수를 사용 하였으며, 에코분류기는 퍼지 뉴럴 네트워크를 기반으로 설계한다. 에코 판단모듈 1과 판단모듈 2를 고려하여 에코분류기의 성능 비교연구를 수행 한다.

Keywords

References

  1. Kessinger, C. S. Ellis, and J. VanAndel, "Radar Echo Classification Scheme for the WSR-88D," A Fuzzy Logic, 29th Int. Conf. on Radar Meteorology, Montreal, Canada, Amer. Meteor. Soc, pp.576-579, 1999.
  2. Cho. Y. H., G. Lee, K. E. Kim, and I. Zawadzki, "Identification and removal of ground echoes and anomalous propagation using the characteristics of radar echoes," J. Atmos. Oceanic Technol., Vol. 23, pp.1206-1222, 2006. https://doi.org/10.1175/JTECH1913.1
  3. Berenguer. M., Sempere-Torres, D., Corral., C., and Sanchez-Diezma. R, "A fuzzy logic technique for identifying nonprecipitating echoes in radar scans," Journal of Atmospheric and Oceanic Technology, Vol. 23, no.9, pp. 1157-1180. 2006. https://doi.org/10.1175/JTECH1914.1
  4. Kilambi, A., A. Bellon, A. Singh, I. Zawadzki, and F. Fabry, "1997: RAPID, a Radar data Analysis, Processing and Interactive Display sysem." 28th Int Conf. on Radar Meteorology, AMS, Vol 220-221, pp. 153-167, 1997
  5. S. Horlcawa, et al., "Composition Methods of Fuzzy Nueral Networks(III)". The 7th Fuzzy System Symposium, pp. 493-496, 1991
  6. R. O. Duda, P. E. Hart, and D. H. Stork, Pattern Classification, Wiley Interscience 2nd, 2000.
  7. Tanvir Islam, Miguel A. Rico-Ramirez, Dawei Han, and Prashant K. Srivastava, "Artificial intelligence techniques for clutter identification with polarimetric radar signatures," Atmospheric Research, Vol. 109-110, June, pp. 95-113, 2012. https://doi.org/10.1016/j.atmosres.2012.02.007
  8. Walther. A, Schroder. M, Fischer. J, and Bennartz. R, Comparison of precipitation in the regional climate model BALTIMOS to radar observations. Theoretical and Applied Climatology, 2009.