A first attempt to apply high speed spherical self-organizing map to huge climate datasets

Norihiko Sugimoto, Kanta Tachibana

Research output: Contribution to journalArticle

6 Citations (Scopus)

Abstract

We propose a use of high speed spherical selforganizing map (HSS-SOM) as a new visualization technique for huge climate datasets complementarily and alternatively to empirical orthogonal function (EOF) analysis. In order to reduce computational cost, we change the number and visible positions of neurons in our HSS-SOM method. This method allows us to use a large number of neurons and thus understand climate datasets better than conventional methods. We apply the HSS-SOM to a 4-times daily surface temperature dataset to check the accuracy. Then the HSS-SOM succeeds to map all data into 4 cluster regions in which each cluster region includes data of the same observational time. While 4 cluster regions are also classified by EOF analysis clearly, HSS-SOM locates several observational data points whose spatial patterns are similar to each other but observed at different time in a marginal area of different cluster regions. We also apply the HSSSOM to a huge climatology dataset which is not classified clearly in the EOF analysis. Then the HSS-SOM classifies observational data points of similar spatial patterns in the physical space closely, while those of different spatial patterns far away. These results show HSS-SOM extracts more detailed features than the EOF, and suggest that the HSS-SOM would be a useful tool to study future climate change and its assessment.

Original languageEnglish
Pages (from-to)41-44
Number of pages4
JournalScientific Online Letters on the Atmosphere
Volume4
Issue number1
DOIs
Publication statusPublished - 2008

Fingerprint

climate
speed
climatology
visualization
surface temperature
climate change
empirical orthogonal function analysis
cost
method

ASJC Scopus subject areas

  • Atmospheric Science

Cite this

A first attempt to apply high speed spherical self-organizing map to huge climate datasets. / Sugimoto, Norihiko; Tachibana, Kanta.

In: Scientific Online Letters on the Atmosphere, Vol. 4, No. 1, 2008, p. 41-44.

Research output: Contribution to journalArticle

@article{b1a562f3668642498a9491cf24b3236d,
title = "A first attempt to apply high speed spherical self-organizing map to huge climate datasets",
abstract = "We propose a use of high speed spherical selforganizing map (HSS-SOM) as a new visualization technique for huge climate datasets complementarily and alternatively to empirical orthogonal function (EOF) analysis. In order to reduce computational cost, we change the number and visible positions of neurons in our HSS-SOM method. This method allows us to use a large number of neurons and thus understand climate datasets better than conventional methods. We apply the HSS-SOM to a 4-times daily surface temperature dataset to check the accuracy. Then the HSS-SOM succeeds to map all data into 4 cluster regions in which each cluster region includes data of the same observational time. While 4 cluster regions are also classified by EOF analysis clearly, HSS-SOM locates several observational data points whose spatial patterns are similar to each other but observed at different time in a marginal area of different cluster regions. We also apply the HSSSOM to a huge climatology dataset which is not classified clearly in the EOF analysis. Then the HSS-SOM classifies observational data points of similar spatial patterns in the physical space closely, while those of different spatial patterns far away. These results show HSS-SOM extracts more detailed features than the EOF, and suggest that the HSS-SOM would be a useful tool to study future climate change and its assessment.",
author = "Norihiko Sugimoto and Kanta Tachibana",
year = "2008",
doi = "10.2151/sola.2008-011",
language = "English",
volume = "4",
pages = "41--44",
journal = "Scientific Online Letters on the Atmosphere",
issn = "1349-6476",
publisher = "Meteorological Society of Japan",
number = "1",

}

TY - JOUR

T1 - A first attempt to apply high speed spherical self-organizing map to huge climate datasets

AU - Sugimoto, Norihiko

AU - Tachibana, Kanta

PY - 2008

Y1 - 2008

N2 - We propose a use of high speed spherical selforganizing map (HSS-SOM) as a new visualization technique for huge climate datasets complementarily and alternatively to empirical orthogonal function (EOF) analysis. In order to reduce computational cost, we change the number and visible positions of neurons in our HSS-SOM method. This method allows us to use a large number of neurons and thus understand climate datasets better than conventional methods. We apply the HSS-SOM to a 4-times daily surface temperature dataset to check the accuracy. Then the HSS-SOM succeeds to map all data into 4 cluster regions in which each cluster region includes data of the same observational time. While 4 cluster regions are also classified by EOF analysis clearly, HSS-SOM locates several observational data points whose spatial patterns are similar to each other but observed at different time in a marginal area of different cluster regions. We also apply the HSSSOM to a huge climatology dataset which is not classified clearly in the EOF analysis. Then the HSS-SOM classifies observational data points of similar spatial patterns in the physical space closely, while those of different spatial patterns far away. These results show HSS-SOM extracts more detailed features than the EOF, and suggest that the HSS-SOM would be a useful tool to study future climate change and its assessment.

AB - We propose a use of high speed spherical selforganizing map (HSS-SOM) as a new visualization technique for huge climate datasets complementarily and alternatively to empirical orthogonal function (EOF) analysis. In order to reduce computational cost, we change the number and visible positions of neurons in our HSS-SOM method. This method allows us to use a large number of neurons and thus understand climate datasets better than conventional methods. We apply the HSS-SOM to a 4-times daily surface temperature dataset to check the accuracy. Then the HSS-SOM succeeds to map all data into 4 cluster regions in which each cluster region includes data of the same observational time. While 4 cluster regions are also classified by EOF analysis clearly, HSS-SOM locates several observational data points whose spatial patterns are similar to each other but observed at different time in a marginal area of different cluster regions. We also apply the HSSSOM to a huge climatology dataset which is not classified clearly in the EOF analysis. Then the HSS-SOM classifies observational data points of similar spatial patterns in the physical space closely, while those of different spatial patterns far away. These results show HSS-SOM extracts more detailed features than the EOF, and suggest that the HSS-SOM would be a useful tool to study future climate change and its assessment.

UR - http://www.scopus.com/inward/record.url?scp=77749342511&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=77749342511&partnerID=8YFLogxK

U2 - 10.2151/sola.2008-011

DO - 10.2151/sola.2008-011

M3 - Article

AN - SCOPUS:77749342511

VL - 4

SP - 41

EP - 44

JO - Scientific Online Letters on the Atmosphere

JF - Scientific Online Letters on the Atmosphere

SN - 1349-6476

IS - 1

ER -