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:20260421T090512Z
LOCATION:Bldg. 6 - Room 003
DTSTART;TZID=Europe/Stockholm:20260629T140000
DTEND;TZID=Europe/Stockholm:20260629T143000
UID:submissions.pasc-conference.org_PASC26_sess103_msa182@linklings.com
SUMMARY:Pedestal Inference Engine (PIE): ML facilitated simulation-based i
 nference framework for tokamak pedestals
DESCRIPTION:Aaro Järvinen, Amanda Bruncrona, Daniel Jordan, Adam Kit, and 
 Anna Niemelä (VTT); Laurent Chone (CSC - IT Center for Science); Lorenzo F
 rassinetti and Arnaud Lafay (KTH Royal Institute of Technology); Alex Pane
 ra-Alvarez, Sven Wiesen, Taweesak Jitsuk, and MJ Pueschel (DIFFER); 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\nT
 he increase of readily available computing resources and advancement of si
 mulations-based inference (SBI) algorithms is opening a pathway to bring s
 tatistical inference to the forefront in model validation, discovery, and 
 prediction in science and technology [1]. In the context of tokamak fusion
  plasmas, the multiscale/physics nature of the system requires an integrat
 ed modeling approach, where the overall prediction is established via inte
 gration of individual models for the interconnected physical mechanisms. S
 ince these models are not built for statistical inference, the uncertainty
  quantification (UQ) becomes intractable through traditional sampling-base
 d approaches. The standard reactor scenarios in tokamaks are based on the 
 formation of an edge pedestal, which is an example of a multiscale/physics
  system that is very challenging for theoretical and numerical predictive 
 approaches. Pedestal Inference Engine (PIE) is a EUROfusion project focuse
 d on harnessing the latest development of the SBI capabilities to overcome
  these UQ challenges. By building around the present pedestal paradigms, t
 he approach establishes a statistical inference framework accelerated with
  machine learning approaches to facilitate model development, validation, 
 and prediction. Generative AI is investigated to compress the large experi
 mental databases to allow more efficient connection to the inference frame
 work.\n\n[1] K. Cranmer, et al. PNAS 117 (48) (2020) 30055-30062.\n\nDomai
 n: Physics, Computational Methods and Applied Mathematics\n\nSession Chair
 s: Stephan Brunner (EPFL), Eric Sonnendruecker (Max Planck Institute for P
 lasma Physics), and Florian Hindenlang (Max Planck Institute for Plasma Ph
 ysics)\n\n
END:VEVENT
END:VCALENDAR