FSD Science Coordination Meeting / KoM AI&ML projects

Tuesday 21 May 2024, 09:00 → 12:30 Europe/Berlin

Following the endorsement by the General Assembly of the 15 AI&ML projects, we are eager to kick off these activities with the FSD Science Coordination Meeting. 

• The objectives of the meeting are: 
• To provide an overview of the endorsed projects to the broader community; 
• To identify the “home” Work Package (WP) for each project; 
• To establish a communication platform among AI&ML projects implemented in different WPs through the creation of an additional Thrust; 
• To clarify the roles and responsibilities of the various individuals and bodies involved (PIs, WP PLs, E-TASC SB, PMU). 

In practical terms, we expect a brief presentation from each PI (5 minutes) followed by short discussions.

ZOOM: https://us02web.zoom.us/j/88220481379?pwd=RGRiYzQ2UmRPYmNwdU5LM3hoeC9hQT09 

1 INTRODUCTION

Objectives of the meeting

Speaker: Dr Denis Kalupin (EUROfusion PMU)

PrIO - hosted projects

Convener: Xavier Litaudon

2 CEA-03

Towards Tokamak operations Conversational AI Interface Using Multimodal Large Language Models

Speaker: Feda Almuhisen

3 DIFFER-01

Machine learning accelerated SOL simulations: SOLPS-NN

Speaker: Dr Sven Wiesen (DIFFER)

4 EPFL-01

AI-assisted Plasma State Monitoring for Control and Disruption-free Operations in Tokamaks

Speaker: Alessandro Pau (EPFL)

5 LPP-ERM-KMS-01

Identification and confinement scaling of hybrid scenarios across multiple devices

Speaker: Prof. Geert Verdoolaege (Ghent University)

6 VTT-03

Machine learning accelerated pedestal MHD stability simulations

Speaker: Aaro Järvinen (VTT)

7 VTT-02

Applying AI/ML for NBI ionization and slowing-down simulations using ASCOT/BBNBI

Speaker: Antti Snicker (VTT (FinnFusion))

PWIE - hosted projects

Convener: Sebastijan Brezinsek (FZJ)

8 CEA-02

AI-augmented SOL modelling for capturing impact of filaments on transport and PWI in mean field codes simulations.

Speaker: David Zarzoso

9 IPPLM-05

LIBS data-processing with Deep Neural Networks and Convolutional Neural Networks for chemical composition quantification in the wall of the next step-fusion reactors

Speaker: Pawel Gasior (IPPLM)

TE - hosted projects

Convener: Marco Wischmeier (IPP Garching)

10 ENEA-03

AI-assisted Causality Detection and Modelling of Plasma Instabilities for Tokamak Disruption Prediction and Control

Speaker: Riccardo Rossi (ENEA)

11 ENEA-04

Development of Physics Informed Neural Networks (PINNs) for Modelling and Prediction of Data in the Form of Time Series

Speaker: Michela Gelfusa (ENEA)

12 IST-01

Deep Learning for Spectrogram Analysis of Reflectometry Data

Speaker: Jose Vicente (Instituto Superior Técnico (IST))

W7X - hosted projects

Convener: Marcin Jakubowski (IPP)

13 CIEMAT-03

Testing cutting-edge AI research to increase pattern recognition and image classification in nuclear fusion databases

Speaker: Augusto Pereira

14 DTU-01

Surrogate modelling of ray-tracing and radiation transport code for faster real-time plasma profile inference in a magnetic confinement device

Speaker: Jan-Matthias Braun (DTU)

15 EK-CER-01

Fast inference methods of advanced diagnostics for real-time control

Speaker: Gergo Pokol (Wigner RCP)

DISCUSSIONS

Convener: Volker Naulin (EUROfusion)

16 Coordination of AI&ML knowledge development (THRUST#6)

Speaker: Frank Jenko

17 Wrapping Up and closure of the meeting

Speaker: Dr Denis Kalupin (EUROfusion PMU)