Nonlinear Processes in Geophysics www.nonlin-processes-geophys.net 1023-5809 1607-7946 10 4/5 2003 10.5194/npg-10-363-2003 http://www.nonlin-processes-geophys.net/10/363/2003/ http://www.nonlin-processes-geophys.net/10/363/2003/npg-10-363-2003.html http://www.nonlin-processes-geophys.net/10/363/2003/npg-10-363-2003.pdf 363 371 0000-00-00 Substorm classification with the WINDMI model W. Horton R. S. Weigel D. Vassiliadis I. Doxas The University of Texas at Austin, Austin, TX 78712, USA NRC at NASA/GSFC, Greenbelt, MD 20771, USA USRA at NASA/GSFC, Greenbelt, MD 20771, USA Department of Physics, University of Colorado, Boulder, CO 80309, USA The results of a genetic algorithm optimization of the WINDMI model using the Blanchard-McPherron substorm data set is presented. A key result from the large-scale computations used to search for convergence in the predictions over the database is the finding that there are three distinct types of <i>v_xB_s -AL </i>waveforms characterizing substorms. Type I and III substorms are given by the internally-triggered WINDMI model. The analysis reveals an additional type of event, called a type II substorm, that requires an external trigger as in the northward turning of the IMF model of Lyons (1995). We show that incorporating an external trigger, initiated by a fast northward turning of the IMF, into WINDMI, a low-dimensional model of substorms, yields improved predictions of substorm evolution in terms of the <i>AL</i> index. Intrinsic database uncertainties in the timing between the ground-based <i>AL </i>electrojet signal and the arrival time at the magnetopause of the IMF data measured by spacecraft in the solar wind prevent a sharp division between type I and II events. However, within these timing limitations we find that the fraction of events is roughly 40% type I, 40% type II, and 20% type III.