Wind data mining by Kohonen Neural Networks.
Time series of Circulation Weather Type (CWT), including daily averaged wind direction and vorticity, are self-classified by similarity using Kohonen Neural Networks (KNN). It is shown that KNN is able to map by similarity all 7300 five-day CWT sequences during the period of 1975-94, in London, Unit...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2007-01-01
|
| Series: | PLoS ONE |
| Online Access: | http://europepmc.org/articles/PMC1790699?pdf=render |
| _version_ | 1811274513778737152 |
|---|---|
| author | José Fayos Carolina Fayos |
| author_facet | José Fayos Carolina Fayos |
| author_sort | José Fayos |
| collection | DOAJ |
| description | Time series of Circulation Weather Type (CWT), including daily averaged wind direction and vorticity, are self-classified by similarity using Kohonen Neural Networks (KNN). It is shown that KNN is able to map by similarity all 7300 five-day CWT sequences during the period of 1975-94, in London, United Kingdom. It gives, as a first result, the most probable wind sequences preceding each one of the 27 CWT Lamb classes in that period. Inversely, as a second result, the observed diffuse correlation between both five-day CWT sequences and the CWT of the 6(th) day, in the long 20-year period, can be generalized to predict the last from the previous CWT sequence in a different test period, like 1995, as both time series are similar. Although the average prediction error is comparable to that obtained by forecasting standard methods, the KNN approach gives complementary results, as they depend only on an objective classification of observed CWT data, without any model assumption. The 27 CWT of the Lamb Catalogue were coded with binary three-dimensional vectors, pointing to faces, edges and vertex of a "wind-cube," so that similar CWT vectors were close. |
| first_indexed | 2024-04-12T23:20:32Z |
| format | Article |
| id | doaj.art-82406ce7ed39456bb882e5cb5b675992 |
| institution | Directory Open Access Journal |
| issn | 1932-6203 |
| language | English |
| last_indexed | 2024-04-12T23:20:32Z |
| publishDate | 2007-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj.art-82406ce7ed39456bb882e5cb5b6759922022-12-22T03:12:32ZengPublic Library of Science (PLoS)PLoS ONE1932-62032007-01-0122e21010.1371/journal.pone.0000210Wind data mining by Kohonen Neural Networks.José FayosCarolina FayosTime series of Circulation Weather Type (CWT), including daily averaged wind direction and vorticity, are self-classified by similarity using Kohonen Neural Networks (KNN). It is shown that KNN is able to map by similarity all 7300 five-day CWT sequences during the period of 1975-94, in London, United Kingdom. It gives, as a first result, the most probable wind sequences preceding each one of the 27 CWT Lamb classes in that period. Inversely, as a second result, the observed diffuse correlation between both five-day CWT sequences and the CWT of the 6(th) day, in the long 20-year period, can be generalized to predict the last from the previous CWT sequence in a different test period, like 1995, as both time series are similar. Although the average prediction error is comparable to that obtained by forecasting standard methods, the KNN approach gives complementary results, as they depend only on an objective classification of observed CWT data, without any model assumption. The 27 CWT of the Lamb Catalogue were coded with binary three-dimensional vectors, pointing to faces, edges and vertex of a "wind-cube," so that similar CWT vectors were close.http://europepmc.org/articles/PMC1790699?pdf=render |
| spellingShingle | José Fayos Carolina Fayos Wind data mining by Kohonen Neural Networks. PLoS ONE |
| title | Wind data mining by Kohonen Neural Networks. |
| title_full | Wind data mining by Kohonen Neural Networks. |
| title_fullStr | Wind data mining by Kohonen Neural Networks. |
| title_full_unstemmed | Wind data mining by Kohonen Neural Networks. |
| title_short | Wind data mining by Kohonen Neural Networks. |
| title_sort | wind data mining by kohonen neural networks |
| url | http://europepmc.org/articles/PMC1790699?pdf=render |
| work_keys_str_mv | AT josefayos winddataminingbykohonenneuralnetworks AT carolinafayos winddataminingbykohonenneuralnetworks |