This project, Machine Learning Approaches for Accelerating Scientific Discovery in Nuclear Physics, enables collaboration between theoretical and experimental nuclear physicists and computer scientists to aid in scientific discoveries using state-of-the-art machine learning methods at the Facility for Rare Isotope Beams, the Compact Muon Solenoid experiment at CERN, Thomas Jefferson National Accelerator Facility, and the upcoming Electron Ion Collider. This NSF-funded project is an integral part of the ALPhA group (Algorithms for Learning in Physics Applications), an ongoing research collaboration headed by Professors Michelle Kuchera and Raghu Ramanujan at Davidson College.
This project has three goals:
GOAL 1: To improve data analysis methods for experiments at the Facility for Rare Isotope Beams (FRIB) by increasing analysis speed and accuracy, with special attention towards the Active-Target Time Projection Chamber, the most data-intensive of the detector systems at FRIB. and .
- Machine Learning Methods for Track Classification in the AT-TPC, M.P. Kuchera, R. Ramanujan, J.Z. Taylor, R.R. Strauss, D. Bazin, J. Bradt, R. Chen. Nucl. Instr. Meth. A. (2019) https://doi.org/10.1016/j.nima.2019.05.097
- Unsupervised Learning for Identifying Events in Active Target Experiments R. Solli, D. Bazin, M.P. Kuchera, R.R. Strauss, Morten Hjorth-Jensen, submitted for review, 2020.
GOAL 2: To create novel implementations of theoretical models using generative methods informed by experimental data for use at the Thomas Jefferson National Accelerator Facility, the Electron-Ion Collider, and CERN.
- cFAT-GAN: Conditional Simulation of Electron-Proton Scattering Events with Variate Beam Energies by a Feature Augmented and Transformed Generative Adversarial Network L. Velasco, E. McClellan, N. Sato, P. Ambrozewicz, T. Liu, W. Melnitchouk, M.P. Kuchera, Yasir Alanazi, Yaohang Li, accepted for publication, ICMLA, 2020.
- [TensorBNN papers]
- AI-based Monte Carlo event generator for electron-proton scattering Y. Alanazi, P. Ambrozewicz, M.P. Kuchera, Y. Li, T. Liu, R.E. McClellan, W. Melnitchouk, E. Pritchard, M. Robertson, N. Sato, R. Strauss, L. Velasco, submitted for review, 2020.
GOAL 3: To optimize beam delivery techniques at FRIB and Argonne National Laboratory by investigating reinforcement learning for automatic beam tuning.
- NSF PHY-2012865
- DOE LDRD-19-13