American Geophysical Union Become an AGU Member
Subscribe to AGU Journals
AGU Home AGU Publications

Subscriber Access to Full Article (Nonsubscribers may purchase for $9.00, Includes print PDF, file size: 1031612 bytes)

JOURNAL OF GEOPHYSICAL RESEARCH, VOL. 111, C05018, doi:10.1029/2005JC003117, 2006

Performance evaluation of the self-organizing map for feature extraction

Yonggang Liu

College of Marine Science, University of South Florida, St. Petersburg, Florida, USA


Robert H. Weisberg

College of Marine Science, University of South Florida, St. Petersburg, Florida, USA


Christopher N. K. Mooers

Rosenstiel School of Marine and Atmospheric Science, University of Miami, Miami, Florida, USA


Abstract

Despite its wide applications as a tool for feature extraction, the Self-Organizing Map (SOM) remains a black box to most meteorologists and oceanographers. This paper evaluates the feature extraction performance of the SOM by using artificial data representative of known patterns. The SOM is shown to extract the patterns of a linear progressive sine wave. Sensitivity studies are performed to ascertain the effects of the SOM tunable parameters. By adding random noise to the linear progressive wave data, it is demonstrated that the SOM extracts essential patterns from noisy data. Moreover, the SOM technique successfully chooses among multiple sets of patterns in contrast with an Empirical Orthogonal Function method that fails to do this. A practical way to apply the SOM is proposed and demonstrated using several examples, including long time series of coastal ocean currents from the West Florida Shelf. With improved SOM parameter choices, strong current patterns associated with severe weather forcing are extracted separate from previously identified asymmetric upwelling/downwelling and transitional patterns associated with more typical weather forcing.

Received 22 June 2005; accepted 3 February 2006; published 25 May 2006.

Keywords: self-organizing map; performance evaluation; feature extraction.

Index Terms: 0555 Computational Geophysics: Neural networks, fuzzy logic, machine learning; 0520 Computational Geophysics: Data analysis: algorithms and implementation; 3252 Mathematical Geophysics: Spatial analysis (0500); 3270 Mathematical Geophysics: Time series analysis (1872, 4277, 4475); 4219 Oceanography: General: Continental shelf and slope processes (3002).


Subscriber Access to Full Article (Nonsubscribers may purchase for $9.00, Includes print PDF, file size: 1031612 bytes)

Citation: Liu, Y., R. H. Weisberg, and C. N. K. Mooers (2006), Performance evaluation of the self-organizing map for feature extraction, J. Geophys. Res., 111, C05018, doi:10.1029/2005JC003117.