Weather data mining using independent component analysis

In this article, we apply the independent component analysis technique for mining spatio-temporal data. The technique has been applied to mine for patterns in weather data using the North Atlantic Oscillation (NAO) as a specific example. We find that the strongest independent components match the ob...

Full description

Bibliographic Details
Main Authors: Jayanta Basak, Anant Sudarshan, Deepak Trivedi, M. S. Santhanam, Te-won Lee, Erkki Oja
Other Authors: The Pennsylvania State University CiteSeerX Archives
Format: Text
Language:English
Published: 2004
Subjects:
North Atlantic Oscillation
ICA
spatio-temporal pattern mining
North Atlantic
North Atlantic oscillation
Online Access:http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.138.5521
http://www.informatik.uni-freiburg.de/~ml/teaching/ss07/MLDMApps/papers/spacialMining/p239-basak.pdf
Description
Summary:In this article, we apply the independent component analysis technique for mining spatio-temporal data. The technique has been applied to mine for patterns in weather data using the North Atlantic Oscillation (NAO) as a specific example. We find that the strongest independent components match the observed synoptic weather patterns corresponding to the NAO. We also validate our results by matching the independent component activities with the NAO index.

Similar Items