BEGIN:VCALENDAR
VERSION:2.0
PRODID:Linklings LLC
BEGIN:VTIMEZONE
TZID:Europe/Stockholm
X-LIC-LOCATION:Europe/Stockholm
BEGIN:DAYLIGHT
TZOFFSETFROM:+0100
TZOFFSETTO:+0200
TZNAME:CEST
DTSTART:19700308T020000
RRULE:FREQ=YEARLY;BYMONTH=3;BYDAY=-1SU
END:DAYLIGHT
BEGIN:STANDARD
TZOFFSETFROM:+0200
TZOFFSETTO:+0100
TZNAME:CET
DTSTART:19701101T020000
RRULE:FREQ=YEARLY;BYMONTH=10;BYDAY=-1SU
END:STANDARD
END:VTIMEZONE
BEGIN:VEVENT
DTSTAMP:20260605T154543Z
LOCATION:Bldg. 6 - Room 003
DTSTART;TZID=Europe/Stockholm:20260629T133000
DTEND;TZID=Europe/Stockholm:20260629T153000
UID:submissions.pasc-conference.org_PASC26_sess103@linklings.com
SUMMARY:MS1B - Applications of AI and ML Towards Addressing Magnetic Fusio
 n Challenges
DESCRIPTION:Organizer(s): Stephan Brunner (Swiss Plasma Center, EPFL), Eri
 c Sonnendruecker, and Florian Hindenlang (Max Planck Institute for Plasma 
 Physics, Garching)\n\nNuclear fusion is increasingly seen as a credible co
 mplement to renewable energy, driven today by both public and growing priv
 ate investments. The leading fusion concepts, tokamaks and stellarators, r
 ely on magnetic confinement. Fusion plasmas exhibit multiscale electromagn
 etic instabilities, from machine-scale disruptions to microscopic turbulen
 ce. The development of these systems thus requires extensive high-performa
 nce computing to understand their complex physics and to address the engin
 eering challenges. Fully kinetic models are prohibitively expensive, so hi
 erarchies of reduced models are needed. Machine learning has therefore bec
 ome a powerful tool, enabling for example fast surrogate models for plasma
  equilibrium solvers and transport modules. Such models are also developed
  for building sub-system modules integrated into comprehensive physics-eng
 ineering digital twin environments. In some cases, optimization is such th
 at these models can be integrated into real-time control systems. These di
 fferent applications of machine learning to magnetic fusion challenges wil
 l be addressed in this minisymposium. The talks will provide an overview o
 f the advanced ML techniques applied and should thus be of interest to a b
 road audience.\n\nSurrogate Models of Nonlinear Gyrokinetics and High-Fide
 lity Fluid-Kinetic Edge Plasma Codes\n\nHigh-fidelity gyrokinetic turbulen
 ce modelling and scrape-off layer modelling are crucial for scenario devel
 opment, but they not included in integrated models due to the associated p
 rohibitive computational cost. Firstly, this talk will present surrogate m
 odels of nonlinear gyrokinetics (operating i...\n\n\nLorenzo Zanisi (UKAEA
 )\n---------------------\nScaling and Scarcity: Developing Robust ML Surro
 gates for Next-Generation Fusion Workflows\n\nSurrogate modelling is emerg
 ing as a key paradigm in fusion research. It provides fast, reliable softw
 are components to accelerate high-fidelity plasma simulators and digital t
 wins. However, their development is intrinsically linked to data availabil
 ity and parameterization. This work explores data-...\n\n\nSamy Kerboua-Be
 nlarbi (EPFL); Christoph Angerer (NVIDIA Inc.); Florian Cabot and Francesc
 o Carpanese (EPFL); Jonathan Citrin (DeepMind); Hammam Elaian (EPFL); Cyri
 lle Favreau (NVIDIA Inc.); Federico Felici (DeepMind); Davide Fransos (NVI
 DIA Inc.); Philippe Hamel (DeepMind); Holger Reimerdes, Cristian Sommariva
 , and Elena Tonello (EPFL); Felix Yang (NVIDIA Inc.); and Alessandro Pau a
 nd Olivier Sauter (EPFL)\n---------------------\nPedestal Inference Engine
  (PIE): ML Facilitated Simulation-Based Inference Framework for Tokamak Pe
 destals\n\nThe increase of readily available computing resources and advan
 cement of simulations-based inference (SBI) algorithms is opening a pathwa
 y to bring statistical inference to the forefront in model validation, dis
 covery, and prediction in science and technology [1]. In the context of to
 kamak fusion pl...\n\n\nAaro Järvinen, Amanda Bruncrona, Daniel Jordan, Ad
 am Kit, and Anna Niemelä (VTT); Laurent Chone (CSC - IT Center for Science
 ); Lorenzo Frassinetti and Arnaud Lafay (KTH Royal Institute of Technology
 ); Alex Panera-Alvarez, Sven Wiesen, Taweesak Jitsuk, and MJ Pueschel (DIF
 FER); Vlado Menkovski and Kiet Bennema ten Brinke (Technical University of
  Eindhoven); Samuli Saarelm and Lorenzo Zanisi (UKAEA); Tobias Görler (IPP
  Garching); Michele Marin (EPFL); and David Hatch (University of Texas at 
 Austin)\n---------------------\nThe PORTALS Workflow: Accelerating Core Tr
 ansport Predictions with Surrogate-Based Optimization Methods\n\nPredictin
 g core performance in magnetic confinement fusion devices requires accurat
 ely modeling the balance between heating sources and transport mechanisms.
  However, the nonlinear electromagnetic turbulence in tokamak and stellara
 tor plasmas makes such modeling computationally demanding, as capturi...\n
 \n\nP. Rodriguez-Fernandez and N.T. Howard (MIT Plasma Science and Fusion 
 Center) and J. Candy (General Atomics)\n\nDomain: Physics, Computational M
 ethods and Applied Mathematics\n\nSession Chair: Stephan Brunner (EPFL)
END:VEVENT
END:VCALENDAR