Data Science
Experimental Nuclear Physics
News
The integration of Deep Learning (DL) into experimental nuclear and particle physics has driven significant progress in simulation and reconstruction workflows. However, traditional simulation frameworks such as Geant4 remain computationally intensive, especially for Cherenkov detectors, where simulating optical photon transport through complex geometries and reflective surfaces introduces a major bottleneck. To address this, we present an open, standalone fast simulation tool for Detection of Internally Reflected Cherenkov Light (DIRC) detectors, with a focus on the High-Performance DIRC (hpDIRC) at the future Electron-Ion Collider (EIC). Our framework incorporates a suite of generative models tailored to accelerate particle identification (PID) tasks by offering a scalable, GPU-accelerated alternative to full Geant4-based simulations. Designed with accessibility in mind, our simulation package enables both DL researchers and physicists to efficiently generate high-fidelity large-scale datasets on demand, without relying on complex traditional simulation stacks. This flexibility supports the development and benchmarking of novel DL-driven PID methods. Moreover, this fast simulation pipeline represents a critical step toward enabling EIC-wide PID strategies that depend on virtually unlimited simulated samples, spanning the full acceptance of the hpDIRC.
Awarded NSF Career Award for Advancing Precision Nucleon Tomography through Deep Learning and Uncertainty Quantification.
This project investigates the internal structure of protons and neutrons—collectively known as nucleons—with the aim of creating a three-dimensional map of how quarks and gluons move and interact within them. Drawing on experimental data from Jefferson Lab and preparing for future measurements at the Electron-Ion Collider, our team employs advanced deep learning and statistical methods to achieve precision measurements and rigorously quantify uncertainties in complex datasets.
We organized the second AI4Fusion Summer School at W&M.
Material is publicly available at the following Git Book link:
https://ai4fusion-wmschool.github.io/summer2025
An intensive 2-week summer school focused on undergraduate students with backgrounds in physics, engineering, computer science, applied mathematics and data science. This summer course includes a close to equal distribution of traditional instruction and active projects. The traditional instruction provides daily instruction in morning classes with a focus on computing, applied mathematics, machine learning and fusion energy. These classes are based on existing classes offered in data science at W&M, such as databases, applied machine learning and deep learning, Bayesian reasoning in data science. These classes will be supplemented with a class focused on fusion energy for the applications the students tackle during the hands-on component and for students’ summer research.
Abstract:
We introduce the first method of uncertainty quantification in the domain of Kolmogorov-Arnold Networks, specifically focusing on (Higher Order) Re- LUKANs to enhance computational efficiency given the computational demands of Bayesian methods. The method we propose is general in nature, providing access to both epistemic and aleatoric uncertainties. It is also capable of generalization to other various basis functions. We validate our method through a series of closure tests, including simple one-dimensional functions and application to the domain of (Stochastic) Partial Differential Equations. Referring to the latter, we demon- strate the method’s ability to correctly identify functional dependencies introduced through the inclusion of a stochastic term.
The code supporting this work can be found at https://github.com/wmdataphys/Bayesian-HR-KAN.
Link to the paper:
https://arxiv.org/pdf/2410.01687
This work is the result of a collaboration with Prof. A. Nwala and his team at Data Science, W&M. We utilized our network ELUQuant, originally developed for event-level uncertainty quantification in DIS, for bot detection with uncertainty quantification
Link to the paper: https://arxiv.org/pdf/2407.13929
Abstract:
Social bots remain a major vector for spreading disinformation on social media and a menace to the public. Despite the progress made in developing multiple sophisticated social bot detection algorithms and tools, bot detection remains a challenging, unsolved problem that is fraught with uncertainty due to the heterogeneity of bot behaviors, training data, and detection algorithms. Detection models often disagree on whether to label the same account as bot or human-controlled. However, they do not provide any measure of uncertainty to indicate how much we should trust their results. We propose to address both bot detection and the quantification of uncertainty at the account level — a novel feature of this research. This dual focus is crucial as it allows us to leverage additional information related to the quantified uncertainty of each prediction, thereby enhancing decision-making and improving the reliability of bot classifications. Specifically, our approach facilitates targeted interventions for bots when predictions are made with high confidence and suggests caution (e.g., gathering more data) when predictions are uncertain
AI-assisted Design Bootcamp: it has been really nice to host this bootcamp at W&M, and wonderful interaction with all the attendees. Below a link to the Git Book of this experience, and a picture with the participants
https://aid2e.github.io/boot-camp-2024/intro.html
ArXiv link: https://arxiv.org/pdf/2407.07376
Imaging Cherenkov detectors are crucial for particle identification (PID) in nuclear and particle physics experiments. Fast reconstruction algorithms are essential for near real-time alignment, calibration, data quality control, and efficient analysis. At the future Electron-Ion Collider (EIC), the ePIC detector will feature a dual Ring Imaging Cherenkov (dual-RICH) detector in the hadron direction, a
Detector of Internally Reflected Cherenkov (DIRC) in the barrel, and a proximity focus RICH in the electron direction. This paper focuses on the DIRC detector, which presents complex hit patterns and is also used for PID of pions and kaons in the GlueX experiment at JLab. We present Deep(er)RICH, an extension of the seminal DeepRICH work, offering improved and faster PID compared to traditional methods and, for the first time, fast and accurate simulation. This advancement addresses a major bottleneck in Cherenkov detector simulations involving photon tracking through complex optical elements. Our results leverage advancements in Vision Transformers, specifically hierarchical Swin Transformer and normalizing flows. These methods enable direct learning from real data and the reconstruction of complex topologies. We conclude by discussing the implications and future extensions of this work, which can offer capabilities for PID for multiple cutting- edge experiments like the future EIC.
Dr. Karthik Suresh, a current postdoctoral researcher in Data Science at William & Mary has been awarded the prestigious JSA Ph.D. Thesis Prize for his outstanding doctoral thesis at Jefferson Lab. Dr. Suresh completed his Ph.D. at the University of Regina, where he was co-supervised by Professor Zisis Papandreou and W&M Assistant Professor of Data Science, Cristiano Fanelli. He then transitioned to William & Mary to collaborate with Dr. Fanelli on a grant-funded project focused on AI-assisted Detector Design for the Electron Ion Collider.
M. Diefenthaler, C. Fanelli, L. O. Gerlach, W. Guan, T. Horn, A. Jentsch, M. Lin, K. Nagai, H. Nayak, C. Pecar, K. Suresh, A. Vossen, T. Wang, T. Wenaus (AID (2) E collaboration)
Cristiano Fanelli, James Giroux, Patrick Moran, Hemalata Nayak, Karthik Suresh, Eric Walter
https://arxiv.org/pdf/2404.05752.pdf [2404.05752v1 physics.data-an]
Information on the corresponding hackathon event can be found at https://eic.ai/hackathons
K. Suresh, N. Kackar, L. Schleck, C. Fanelli, arXiv:2403.15729v1 [cs.CL] https://arxiv.org/pdf/2403.15729.pdf
The app can be accessed through https://rags4eic-ai4eic.streamlit.app/
Link to 2023 Hackathon: Physics Event Classification Using Large Language Models (organized by C. Fanelli, J. Giroux, P. Moran, K. Suresh)
Our paper has been accepted to the NeurIPS 2023 workshop on Machine Learning and the Physical Sciences
Our Data Science team will collaborate in this project with W&M co-PI (Prof. Mordijck) to organize a yearly summer school on AI/ML for fusion energy at William & Mary.
Prof. Fanelli at W&M will be lead PI of the project AIDE (AI-assisted Detector design at the Electron Ion Collider). EIC is an accelerator project under construction at Brookhaven National Laboratory (BNL) that will probe the internal structure and forces of protons and neutrons that compose the atomic nucleus. This collaborative project involves co-PIs of national labs at Brookhaven National Lab and Jefferson Lab, as well as of other universities, Catholic University of America, and Duke University.
Prof. Fanelli will be co-PI of the project AI-Optimized Polarization, led by Jefferson Lab. W&M will collaborate to provide a continuous AI/ML control for the polarized beam at the GlueX experiment in Hall D.
More info at:
https://content.govdelivery.com/accounts/USDOEOS/bulletins/36b5803
Lectures on AI/ML for Nuclear Physics and the Electron Ion Collider
More info at:
https://www.jlab.org/conference/hugs2023
https://cfteach.github.io/HUGS23/intro.html
