2nd International Conference on Data Driven Plasma Science

Mon. 13

Tue. 14

Wed. 15

Thu. 16

Fri. 17

08:00

09:00

10:00

11:00

12:00

13:00

14:00

15:00

16:00

17:00

18:00

19:00

20:00

21:00

22:00

Registration

Welcome

Plenary 1 : T. Artières, An overview of Deep Learning Research and Results, T. Artières

Coffee break

V. J. Schwanitz, Data-driven energy system research – recent advances and future directions

Z. Wang, Microparticle cloud diagnostic (MCD) for data-driven plasma experiments

J. Trieschmann, Coupling sputtering and transport simulations through a machine learning plasma-surface interface

J. Morales, First WEST experimental data analysis using machine learning algorithms

Lunch

D. Morvay, Utilizing Big Data Methods within the Semiconductor Industry

K. van de Plassche, Surrogate modelling using feed forward neural networks for turbulent transport in fusion plasmas

J. Mlynar, Development and comparative tests of tomography at JET

Coffee break

Poster Session 1

Welcome Cocktail

Plenary 2 : A. Bailey, Equipment Intelligence™: Plasma Science Driven by Semiconductor Data

H. Kino, Prediction ability and importance of descriptors of single-element physical sputtering yields based on sparse modeling

Coffee break

S. Park, Control of the HARC Etching Processes in OLED Display Manufacturing Fab by Using the PI-VM Algorithm

H. Nakada, Data-driven Development of Plasma Process: Time-series Optimization of Etching Conditions Based on Reinforcement Learning

A. Solov’yov, MBN Explorer and Studio case studies with irradiation driven molecular dynamics

Lunch

Boat Tour to the Calanques

Plenary 3 : H. Ihssen, New Material Discovery Activities in the Framework of the European Energy Research Alliance

J. Shinagawa, Pairing plasma diagnostics, theory and simulations with machine learning to overcome the limitations of big data analytics in complex plasma processes

Coffee break

K. Kamataki, Predictive insight based on grey box analysis of plasma process data

K. Wende, From numbers to decisions - data processing in omics-driven approaches

E. Kolemen, Machine Learning Control for fusion devices

R. A. Guinee, A Novel Kalman Filter Bank Methodology For Time Series Prediction In Forecasting Applications

Lunch

M. Becker, Reuse of research data for plasma processes and applications with Plasma-MDS and INPTDAT

M. Boyer, Accelerated predictive models for scenario optimization and control of tokamaks

M. R. Churchill, Deep Convolutional Neural Networks for Long Time Series Classification

Coffee break

Poster Session 2

Conference Dinner

Plenary 4 : R. Yoshida, Machine learning for materials design and discovery: how do we learn from little?

A. Mesbah, Machine Learning for Process Monitoring and Control of Low-temperature Plasmas

Coffee break

J. Kates-Harbeck, Disruption Prediction in Tokamak Fusion Reactors via Deep Learning at Scale

M. Blatzheim, Deep Neural Network Based Reconstruction of Plasma Properties for Wendelstein 7-X

A. Ho, Application of Gaussian process regression techniques to experimental plasma profile fitting and model validation

Lunch

B. Spears, Learning-based predictive models: a new approach to integrating large-scale simulations and experiments

O. Agullo, Prediction of magnetic island dynamics with neural networks

P. Rodriguez-Fernandez, Surrogate-Based Optimization Techniques for the Validation of Plasma Transport Models

Coffee break

Round Table

Plenary 5 : C. S. Chang, Federated Data-Science for Accelerated Fusion Research: Why do we need it and how do we achieve it?

F. Matos, Plasma State Classification and ELM detection using Convolutional Long Short-Term Memory Neural Networks

Coffee break

T. Cartier-Michaud, PoPe method for code verification and model reduction: Focus on numerical diffusion

Closing ceremony