BEGIN:VCALENDAR
VERSION:2.0
CALSCALE:GREGORIAN
PRODID:UW-Madison-Physics-Events
BEGIN:VEVENT
SEQUENCE:1
UID:UW-Physics-Event-9195
DTSTART:20250428T170000Z
DTEND:20250428T181500Z
DTSTAMP:20260413T151415Z
LAST-MODIFIED:20250423T140741Z
LOCATION:1227 Engineering Hall
SUMMARY:A Generative Artificial Intelligence framework for long-time p
 lasma turbulence simulations\, Plasma Physics (Physics/ECE/NE 922) Sem
 inar\, Diego Del-Castillo-Negrete\, University of Texas at Austin
DESCRIPTION:Generative artificial intelligence methods are employed fo
 r the first time to construct a surrogate model for plasma turbulence 
 that enables long-time transport simulations [1]. The proposed GAIT (G
 enerative Artificial Intelligence Turbulence) framework is based on th
 e coupling of a convolutional variational autoencoder that encodes pre
 computed turbulence data into a reduced latent space\, and a recurrent
  neural network and decoder that generate new turbulence states 400 ti
 mes faster than the direct numerical integration. The model is applied
  to the Hasegawa-Wakatani (HW) plasma turbulence model\, which is clos
 ely related to the quasi-geostrophic model used in geophysical fluid d
 ynamics. Very good agreement is found between the GAIT and the HW mode
 ls in the spatiotemporal Fourier and Proper Orthogonal Decomposition s
 pectra\, and the flow topology characterized by the Okubo-Weiss decomp
 osition. The GAIT model also reproduces Lagrangian transport including
  the probability distribution function of particle displacements and t
 he effective turbulent diffusivity.
\n
\n[1] B. Clavier\, D. Zarzoso\,
  D. del-Castillo-Negrete and E. Frenod\, Phys. Rev. E Letters 111\, L0
 13202 (2025).
URL:https://www.physics.wisc.edu/events/?id=9195
END:VEVENT
END:VCALENDAR