Name: AI/ML for Particle Accelerator, X-Ray Beamlines and Electron Microscopy
Start: 2021-11-01T10:00:00-05:00
End: 2021-11-03T16:00:00-05:00
Location: Virtual

AI/ML for Particle Accelerator, X-Ray Beamlines and Electron Microscopy

from Monday, 1 November 2021 (10:00) to Wednesday, 3 November 2021 (16:00)

Monday, 1 November 2021
10:00 Tuning and Control
Tuning and Control
10:00 - 12:15
Contributions

10:00 Opening Remarks - Brahim Mustapha (Argonne National Laboratory) Olle Heinonen (Argonne National Laboratory)

10:05 Online tuning of particle accelerators with reinforcement learning and comprehensive surrogate models - Auralee Edelen (SLAC)

10:30 Automated Experiments, Machine Learning and Reinforcement Learning for tuning and control applications in microscopy - Rama Vasudevan (Oak Ridge National Laboratory)

10:55 Bayesian Techniques for Accelerator Characterization and Control - Ryan Roussel (University of California Los Angeles)

11:20 Simultaneous online optimization of dynamic acceptance and lifetime for APS - Yipeng Sun (Argonne National Laboratory)

11:40 Open / Speaker Panel Discussion
12:15 Lunch Break
Lunch Break
12:15 - 13:30
13:30 Data Analytics
Data Analytics
13:30 - 15:45
Contributions

13:30 Accelerating atomic-scale characterization by combining theory and AI/ML - Maria Chan (Argonne National Laboratory)

13:55 Solving X-ray and Cryo-EM Inverse Problems with Deep Learning - Daniel Ratner (SLAC)

14:20 Supervised and Unsupervised Machine Learning for Large, Noisy STEM Data - Paul Voyles (University of Wisconsin - Madison )

14:45 Automated x-ray PDF analysis and ML modeling - Chris Benmore (Argonne National Laboratory)

15:10 Open / Speaker Panel Discussion
Tuesday, 2 November 2021
10:00 Failure Detection, Virtual Diagnostics & Digital Twin
Failure Detection, Virtual Diagnostics & Digital Twin
10:00 - 12:30
Contributions

10:00 Applications of Neural Networks for Anomaly Detection in Particle Accelerators - Jonathan Edelen (RadiaSoft LLC)

10:25 Data-Driven Detection, Isolation, Identification, and Prediction of Accelerator Fault Events - Chris Tennant (Jefferson Lab)

10:50 Adaptive Machine Learning for Control and Virtual Diagnostics of Time-Varying Particle Accelerator Systems and Beams - Alexander Scheinker (Los Alamos National Laboratory)

11:15 A Digital Twin for Spatiotemporal Experiments - Subramanian Sankaranarayanan (Argonne National Laboratory)

11:40 Uncertainty aware anomaly detection to predict errant beam pulses in the SNS accelerator - Malachi Schram (Thomas Jefferson National Accelerator Facility)

11:55 Open / Speaker Panel Discussion
12:30 Lunch Break
Lunch Break
12:30 - 13:30
13:30 Imaging and Data Processing
Imaging and Data Processing
13:30 - 15:45
Contributions

13:30 Using automated image analysis to understand nanoparticle coarsening, ripening and evaporation at the nanoscale - Eric Stach (University of Pennsylvania)

13:55 Phase retrieval with deep learning network and automatic differentiation - Tao Zhou (Argonne National Laboratory)

14:20 Overview of AI/ML@APS beamlines - Mathew Cherukara (Argonne National Laboratory)

14:45 Accelerated Data Analysis Workflows for Ptychography using Remote Leadership Computing Resources - Tekin Bicer (Argonne National Laboratory)

15:10 Open / Speaker Panel Discussion
Wednesday, 3 November 2021
10:00 Autonomous Discovery
Autonomous Discovery
10:00 - 12:15
Contributions

10:00 Imaging 2D materials, atom by atom, on the million-atom scale - Pinshane Huang (University of Illinois Urbana-Champaign)

10:25 Recent Progress in Autonomous X-ray Scattering - Kevin Yager (Brookhaven National Laboratory)

10:50 Domain-Aware Gaussian Processes and High-Performance Mathematical Optimization for Stochastic Function Approximation and Autonomous Data Acquisition - Marcus Noack (Lawrence Berkeley National Laboratory)

11:15 Advanced Robotics and Software Defined Automation to Speed Materials Discovery - Ben Blaiszik (University of Chicago)

11:40 Open / Speaker Panel Discussion
12:15 Lunch Break
Lunch Break
12:15 - 13:30
13:30 Data, Computing and Modeling
Data, Computing and Modeling
13:30 - 15:45
Contributions

13:30 Programmatic and Deep Learning Analysis Pipelines for 4D-STEM Materials Science Experiments - Colin Ophus (Lawrence Berkeley National Laboratory)

13:55 MLExchange, bringing machine learning to the beamline - Alexander Hexemer (Lawrence Berkeley National Laboratory)

14:20 The FNAL accelerator complex initial ML efforts and a conceptual AI roadmap for operations - Tia Miceli (NMSU)

14:45 Surrogate Models for Beam Transport and Particle Tracking - Jose Martinez (Argonne National Laboratory)

15:05 Open / Speaker Panel Discussion

15:40 Closing Remarks - Brahim Mustapha (Argonne National Laboratory) Olle Heinonen (Argonne National Laboratory)