Fourth Conference on Artificial Intelligence Applications to Environmental Science


Sea surface temperature patterns on the West Florida Shelf using Growing Hierarchical Self-Organizing Maps

Yonggang Liu, University of South Florida, St. Petersburg, FL; and R. H. Weisberg and R. He

Neural network analyses based on the self-organizing map (SOM) and the growing hierarchical self-organizing map (GHSOM) are used to examine characteristic patterns of the sea surface temperature (SST) variability on the West Florida Shelf from time series of daily SST maps that span the five-year interval 1998 to 2002. Four characteristic SST patterns are extracted in the first layer GHSOM array: characteristic winter and summer season patterns, and two seasonal transition patterns. Three of these are further expanded in the second layer yielding a more detailed pattern structure in all seasons. The winter pattern is one of cold SST, with isotherms aligned approximately along isobaths and with the coldest water located along the coast in the shallow Florida Big Bend region and the warmest water located seaward of shelf break associated with the Gulf of Mexico Loop Current. Contrasting with winter the summer pattern is one of warm SST distributed in a horizontally uniform manner. The spring transition includes a mid shelf cold tongue. Similar analyses performed on SST anomaly data provide further details on the seasonally varying patterns.

extended abstract  Extended Abstract (2.5M)

wrf recording  Recorded presentation

Supplementary URL:

Session 2, General Interest AI Applications
Monday, 10 January 2005, 1:30 PM-2:45 PM

Previous paper  

Browse or search entire meeting

AMS Home Page