Meteorological field patterns classified using self-organizing map (SOM)

Koji Nishiyama, Shinichi Endo, Kenji Jinno

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

In order to systematically and visually understand well-known but qualitative and relatively complicated relationships between synoptic fields in the BAIU season and heavy rainfall events in Japan, these synoptic fields were classified using the Self-Organizing Map (SOM) algorithm. This algorithm can convert complex nonlinear features into simple two-dimensional relationships, and was followed by the application of the clustering techniques of the U-matrix and the K-means. It was assumed that the meteorological field patterns be simply expressed by the spatial distribution of wind components at the 850 hPa level and Precipitable Water (PW) in the southwestern area including Kyushu in Japan. Consequently, the synoptic fields could be divided into eight kinds of patterns (clusters). One of the clusters has the notable spatial feature represented by high PW accompanied by strong wind components known as Low-Level Jet (LLJ). The features of this cluster indicate a typical meteorological field pattern that frequently causes disastrous heavy rainfall in Kyushu in the rainy season. From these results, the SOM technique may be an effective tool for the classification of complicated non-linear synoptic fields.

Original languageEnglish
Title of host publication31st IAHR Congress 2005
Subtitle of host publicationWater Engineering for the Future, Choices and Challenges
EditorsJun Byong-Ho, Il Lee Sang, Seo Il Won, Choi Gye-Woon
PublisherKorea Water Resources Association
Pages3709-3718
Number of pages10
ISBN (Electronic)8987898245, 9788987898247
Publication statusPublished - 2005
Event31st IAHR Congress 2005: Water Engineering for the Future, Choices and Challenges - Seoul, Korea, Republic of
Duration: Sep 11 2005Sep 16 2005

Publication series

Name31st IAHR Congress 2005: Water Engineering for the Future, Choices and Challenges

Conference

Conference31st IAHR Congress 2005: Water Engineering for the Future, Choices and Challenges
CountryKorea, Republic of
CitySeoul
Period9/11/059/16/05

All Science Journal Classification (ASJC) codes

  • Engineering (miscellaneous)
  • Environmental Science (miscellaneous)
  • Water Science and Technology

Fingerprint Dive into the research topics of 'Meteorological field patterns classified using self-organizing map (SOM)'. Together they form a unique fingerprint.

Cite this