BEGIN:VCALENDAR
VERSION:2.0
PRODID:-//wp-events-plugin.com//7.2.3.1//EN
TZID:America/New_York
X-WR-TIMEZONE:America/New_York
BEGIN:VEVENT
UID:0-6405@eng.ufl.edu
DTSTART;TZID=America/New_York:20240125T135500
DTEND;TZID=America/New_York:20240125T145500
DTSTAMP:20240124T214328Z
URL:https://www.eng.ufl.edu/news-events/events/ne-seminar-a-physics-constr
 ained-deep-learning-description-of-fusion-plasmas/
SUMMARY:NE Seminar: "A Physics-constrained Deep Learning Description of Fus
 ion Plasmas"
DESCRIPTION:Abstract\nDeep learning methods offer the promise of drasticall
 y reducing the computational cost of evaluating a diverse range of plasma 
 physics models. The application of deep learning methods to several plasma
  applications is\, however\, hindered by the often sparse experimental and
  computational data sets available.\n\nPhysics-informed machine learning m
 ethods\, whereby physical constraints are embedded in the training of a ne
 ural network\, offer a path through which the quantity of data required to
  train a neural network can be drastically reduced. The present work emplo
 ys a physics-informed neural network (PINN) to predict relativistic electr
 on formation in a magnetic fusion plasma in the absence of any experimenta
 l or simulation data. Such electrons\, which are often observed to achieve
  energies of several mega electron volts\, pose an immediate threat to tok
 amak devices due to their high energy and often localized impact on plasma
 -facing components.\n\nIn this seminar\, a PINN trained on the adjoint to 
 the relativistic Fokker-Planck equation will be shown to accurately predic
 t the rate at which such relativistic electrons are generated across a bro
 ad range of plasma conditions\, thus providing an efficient surrogate for 
 identifying tokamak regimes where such relativistic electrons can be expec
 ted to emerge.\nBio\nChris McDevitt\, Ph.D.\nAssociate Professor\, Nuclear
  Engineering\nUniversity of Florida\nDr. Chris McDevitt is an associate p
 rofessor in the Nuclear Engineering Program at the University of Florida w
 here his research is focused on the theory and simulation of fusion plasma
 s. Prior to joining UF in Fall 2019\, he completed his B.S. in physics at 
 the University of California at Santa Cruz and subsequently completed his 
 Ph.D. in physics at the University of California at San Diego\, where he f
 ocused on the description of turbulence in magnetic fusion plasmas. After 
 a short stint as a visiting scientist at Ecole Polytechnique\, he moved to
  Los Alamos National Laboratory where he worked as a staff scientist.
CATEGORIES:Seminars
LOCATION:Rhines Hall Room 125\, 549 Gale Lemerand Drive\, Gainesville\, FL\
 , 32611\, United States
GEO:29.644403;-82.350403
X-APPLE-STRUCTURED-LOCATION;VALUE=URI;X-ADDRESS=549 Gale Lemerand Drive\, G
 ainesville\, FL\, 32611\, United States;X-APPLE-RADIUS=100;X-TITLE=Rhines 
 Hall Room 125:geo:29.644403,-82.350403
END:VEVENT
BEGIN:VTIMEZONE
TZID:America/New_York
X-LIC-LOCATION:America/New_York
BEGIN:STANDARD
DTSTART:20231105T010000
TZOFFSETFROM:-0400
TZOFFSETTO:-0500
TZNAME:EST
END:STANDARD
END:VTIMEZONE
END:VCALENDAR