Continual Learning for Particle Accelerators
Unfortunately, I could not travel to the conference, thanks to Malachi Schram for presenting this spotlight Talk on our paper "Continual Learning for Particle Accelerators"
admin
Professional Summary
Staff Computer Scientist II at Thomas Jefferson National Accelerator Facility (Jefferson Lab). Specializing in machine learning for particle accelerators and nuclear physics applications, with expertise in reinforcement learning and uncertainty quantification.
Interests
Artificial Intelligence
Machine Learning
Reinforcement Learning
Continual Learning
Anomaly Prediction / Detection
Optimization and Control
Particle Accelerator Applications
📚 My Research
I am a Staff Computer Scientist at Thomas Jefferson National Accelerator Facility (Jefferson Lab) in Newport News, VA. I specialize in developing advanced machine learning solutions for Science and Engineering.
Current Leadership:
- JLab PI: Towards Higher Brightness Beam for BNL with AI ($700K JLab)
- JLab PI: Hardware Aware Artificial Intelligence for HEP ($0.6M JLab / $2M total)
- Jlab PI: Self-driving NP Scientific User Facilities ($700K JLab / $2M total)
- Team Lead / Co-PI: ML for SNS Accelerator Performance ($600K JLab / $2.2M total)
I mentor junior scientists, postdocs, and graduate students in machine learning development and research methodologies. I’m passionate about making AI practical and trustworthy for high-impact scientific applications.
Recent Publications
(2025).
Continual learning for particle accelerators.
NeurIPS 2025 Machine Learning for Physical Science Workshop.
(2025).
Uncertainty based online ensemble on non-stationary data for fusion science.
NeurIPS 2025 Machine Learning for Physical Science Workshop.
(2025).
Decode the workload: Training deep learning models for efficient compute cluster representation.
EPJ Web of Conferences, Volume 337, Article 01120.
(2025).
Hydra: An AI-Based Framework for Interpretable and Portable Data Quality Monitoring.
EPJ Web of Conferences, Vol. 337, 01227.
(2025).
Towards continual machine learning for particle accelerators.
IBIC 2025.
Professional Service
I am actively involved in peer review, mentoring, and conference organization to advance the scientific community.
Recent & Upcoming Talks
•
December 6, 2025 12:00 AM — 12:00 AM
•
1 min read
Towards a Robust Adaptive Digital Twin for Fusion Applications
Talk Talk on developing robust adaptive digital twins with uncertainty awareness for fusion science applications.
admin
Differential and Explainable Reinforcement Learning for Multi-objective Optimization in Particle Accelerators
Invited Talk Explainable and Differential Reinforcement Learning for Multi-objective Optimization in Particle Accelerators
admin
Towards continual machine learning for your ever-changing accelerators
Invited Talk Continual/Lifelong machine learning for ever drifting particle accelerator data at IBIC 2025, University of Liverpool, UK.
admin
Harnessing the Power of Gradient Based Simulations for Multi-Objective Optimization in Particle Accelerators
Invited Talk Talk on applying fast optimization and control with differential reinforcement learning leveraging differential simulations.
admin
Recent Blogs