Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size
We use ERA-Interim reanalysis data of 2 meter temperature to perform a pattern analysis of the Arctic temperatures exploiting an artificial neural network called Self Organizing-Map (SOM). The SOM method is used as a cluster analysis tool where the number of clusters has to be specified by the user....
Main Authors: | , |
---|---|
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
Universität Leipzig
2018
|
Subjects: | |
Online Access: | https://nbn-resolving.org/urn:nbn:de:bsz:15-qucosa2-317949 https://ul.qucosa.de/id/qucosa%3A31794 https://ul.qucosa.de/api/qucosa%3A31794/attachment/ATT-0/ |
id |
ftunivleipzig:oai:qucosa:de:qucosa:31794 |
---|---|
record_format |
openpolar |
spelling |
ftunivleipzig:oai:qucosa:de:qucosa:31794 2023-09-05T13:17:09+02:00 Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size Mewes, Daniel Jacobi, Ch. 2018 https://nbn-resolving.org/urn:nbn:de:bsz:15-qucosa2-317949 https://ul.qucosa.de/id/qucosa%3A31794 https://ul.qucosa.de/api/qucosa%3A31794/attachment/ATT-0/ eng eng Universität Leipzig urn:nbn:de:bsz:15-qucosa2-317623 qucosa:31762 urn:nbn:de:bsz:15-qucosa2-317949 https://ul.qucosa.de/id/qucosa%3A31794 https://ul.qucosa.de/api/qucosa%3A31794/attachment/ATT-0/ info:eu-repo/semantics/openAccess ERA-Interim Reanalysedaten Self Organizing- Map ERA-Interim reanalysis data Self Organizing-Map info:eu-repo/semantics/acceptedVersion doc-type:article info:eu-repo/semantics/article doc-type:Text 2018 ftunivleipzig 2023-08-11T13:58:34Z We use ERA-Interim reanalysis data of 2 meter temperature to perform a pattern analysis of the Arctic temperatures exploiting an artificial neural network called Self Organizing-Map (SOM). The SOM method is used as a cluster analysis tool where the number of clusters has to be specified by the user. The different sized SOMs are analyzed in terms of how the size changes the representation of specific features. The results confirm that the larger the SOM is chosen the larger will be the root mean square error (RMSE) for the given SOM, which is followed by the fact that a larger number of patterns can reproduce more specific features for the temperature. Wir benutzten das künstliche neuronale Netzwerk Self Organizing-Map (SOM), um eine Musteranalyse von ERA-Interim Reanalysedaten durchzuführen. Es wurden SOMs mit verschiedener Musteranzahl verglichen. Die Ergebnisse zeigen, dass SOMs mit einer größeren Musteranzahl deutlich spezifischere Muster produzieren im Vergleich zu SOMs mit geringen Musteranzahlen. Dies zeigt sich unter anderem in der Betrachtung der mittleren quadratischen Abweichung (RMSE) der Muster zu den zugeordneten ERA Daten. Article in Journal/Newspaper Arctic Universität Leipzig: Qucosa Arctic |
institution |
Open Polar |
collection |
Universität Leipzig: Qucosa |
op_collection_id |
ftunivleipzig |
language |
English |
topic |
ERA-Interim Reanalysedaten Self Organizing- Map ERA-Interim reanalysis data Self Organizing-Map |
spellingShingle |
ERA-Interim Reanalysedaten Self Organizing- Map ERA-Interim reanalysis data Self Organizing-Map Mewes, Daniel Jacobi, Ch. Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size |
topic_facet |
ERA-Interim Reanalysedaten Self Organizing- Map ERA-Interim reanalysis data Self Organizing-Map |
description |
We use ERA-Interim reanalysis data of 2 meter temperature to perform a pattern analysis of the Arctic temperatures exploiting an artificial neural network called Self Organizing-Map (SOM). The SOM method is used as a cluster analysis tool where the number of clusters has to be specified by the user. The different sized SOMs are analyzed in terms of how the size changes the representation of specific features. The results confirm that the larger the SOM is chosen the larger will be the root mean square error (RMSE) for the given SOM, which is followed by the fact that a larger number of patterns can reproduce more specific features for the temperature. Wir benutzten das künstliche neuronale Netzwerk Self Organizing-Map (SOM), um eine Musteranalyse von ERA-Interim Reanalysedaten durchzuführen. Es wurden SOMs mit verschiedener Musteranzahl verglichen. Die Ergebnisse zeigen, dass SOMs mit einer größeren Musteranzahl deutlich spezifischere Muster produzieren im Vergleich zu SOMs mit geringen Musteranzahlen. Dies zeigt sich unter anderem in der Betrachtung der mittleren quadratischen Abweichung (RMSE) der Muster zu den zugeordneten ERA Daten. |
format |
Article in Journal/Newspaper |
author |
Mewes, Daniel Jacobi, Ch. |
author_facet |
Mewes, Daniel Jacobi, Ch. |
author_sort |
Mewes, Daniel |
title |
Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size |
title_short |
Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size |
title_full |
Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size |
title_fullStr |
Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size |
title_full_unstemmed |
Analyzing Arctic surface temperatures with Self Organizing-Maps: Influence of the maps size |
title_sort |
analyzing arctic surface temperatures with self organizing-maps: influence of the maps size |
publisher |
Universität Leipzig |
publishDate |
2018 |
url |
https://nbn-resolving.org/urn:nbn:de:bsz:15-qucosa2-317949 https://ul.qucosa.de/id/qucosa%3A31794 https://ul.qucosa.de/api/qucosa%3A31794/attachment/ATT-0/ |
geographic |
Arctic |
geographic_facet |
Arctic |
genre |
Arctic |
genre_facet |
Arctic |
op_relation |
urn:nbn:de:bsz:15-qucosa2-317623 qucosa:31762 urn:nbn:de:bsz:15-qucosa2-317949 https://ul.qucosa.de/id/qucosa%3A31794 https://ul.qucosa.de/api/qucosa%3A31794/attachment/ATT-0/ |
op_rights |
info:eu-repo/semantics/openAccess |
_version_ |
1776198436383621120 |