Return to Colloquia & Seminar listing
Stochastic particle methods for the Navier-Stokes and Burgers equationsPDE and Applied Math Seminar
|Speaker: ||Gautam Iyer, Stanford|
|Location: ||1147 MSB|
|Start time: ||Wed, Jun 3 2009, 11:10AM|
I will introduce an exact stochastic representation for certain
non-linear transport equations (e.g. 3D-Navier-Stokes, Burgers)
based on noisy Lagrangian paths, and use this to construct a
(stochastic) particle system for the Navier-Stokes equations. On any
fixed time interval, this particle system converges to the
Navier-Stokes equations as the number of particles goes to infinity.
Curiously, a similar system for the (viscous) Burgers equations
shocks almost surely in finite time. This happens because these
particle systems exhibit a curious energy dissipation on long time
intervals. I will describe a resetting procedure by which these
shocks can (surprisingly!) be avoided, and thus obtain convergence
to the viscous Burgers equations on long time intervals.
Note special time.