ARCHETYPAL ANALYSIS OF SPATIOTEMPORAL DYNAMICS

A comparison is made between the principal component or Karhunen-Loeve decomposition of two sets of spatio-temporal data (one numerical, the other experimental) and a new procedure called archetypal analysis (C utler and Breiman, 1994). Archetypes characterize the convex hull of t he data set and the data set can be reconstructed in terms of these va lues. Archetypes may be more appropriate than KL when the data do not have elliptical distributions, and are often well-suited to studying r egimes in which the system spends a long time near a ''steady'' state, punctuated with quick excursions to outliers in the data set, which m ay represent intermittency. Other advantages and disadvantages of each method are discussed.