Engineering Papers⌕ Search
Home/Archive/DOE OSTI

DOE OSTI · 3024877

AI for nuclear physics: the EXCLAIM project

Liuti, S. [University of Virginia, Charlottesville, VA (United States)]·Adams, D. [University of Virginia, Charlottesville, VA (United States)]·Boër, M. [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)]·Chern, G. W. [University of Virginia, Charlottesville, VA (United States)]·Cuic, M. [University of Virginia, Charlottesville, VA (United States)]·Engelhardt, M. [New Mexico State University (NMSU), Las Cruces, NM (United States)]·Goldstein, G. R. [Tufts University, Medford, MA (United States)]·Kriesten, B. [Argonne National Laboratory (ANL), Argonne, IL (United States)]·Li, Y. [Old Dominion University, Norfolk, VA (United States)]·Lin, H. W. [Michigan State University, East Lansing, MI (United States)]·Sievert, M. [New Mexico State University (NMSU), Las Cruces, NM (United States)]·Sivers, D. [University of Michigan, Ann Arbor, MI (United States)]
View original source ↗Read source document ↗Export metadata ↓

Abstract

An overview of the recent activity of the newly funded EXCLusives with AI and Machine learning (EXCLAIM) collaboration is presented. The main goal of the collaboration is to develop a framework to implement AI and machine learning techniques in problems emerging from the phenomenology of high energy exclusive scattering processes from nucleons and nuclei, maximizing the information that can be extracted from various sets of experimental data, while implementing theoretical constraints from lattice QCD. A specific perspective embraced by EXCLAIM is to use the methods of theoretical physics to understand the working of ML, beyond its standardized applications to physics analyses which most often rely on industrially provided tools, in an automated way.

Explore related subjects

Analysis and statistical methodsData processing methodsSimulation methods and programsSoftware architectures (event data models, frameworks and databases)

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Liuti, S. [University of Virginia, Charlottesville, VA (United States)], Adams, D. [University of Virginia, Charlottesville, VA (United States)], Boër, M. [Virginia Polytechnic Inst. and State Univ. (Virginia Tech), Blacksburg, VA (United States)], Chern, G. W. [University of Virginia, Charlottesville, VA (United States)], Cuic, M. [University of Virginia, Charlottesville, VA (United States)], Engelhardt, M. [New Mexico State University (NMSU), Las Cruces, NM (United States)], Goldstein, G. R. [Tufts University, Medford, MA (United States)], Kriesten, B. [Argonne National Laboratory (ANL), Argonne, IL (United States)], Li, Y. [Old Dominion University, Norfolk, VA (United States)], Lin, H. W. [Michigan State University, East Lansing, MI (United States)], Sievert, M. [New Mexico State University (NMSU), Las Cruces, NM (United States)], Sivers, D. [University of Michigan, Ann Arbor, MI (United States)]. 2025-08-13. AI for nuclear physics: the EXCLAIM project. https://doi.org/10.1088/1748-0221%2F20%2F08%2Fc08011

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related reports

DOE OSTI2026

Neural posterior unfolding

Differential cross section measurements are the currency of scientific exchange in particle and nuclear physics. A key challenge for these analyses is the correction for detector distortions, known as deconvolution or unfolding. Binned unfolding of cross section measurements traditionally rely on the regularized inversion of the response matrix that represents the detector response, mapping pre-detector (`particle level') observables to post-detector (`detector level') observables. In this paper we introduce Neural Posterior Unfolding, a modern, Bayesian approach that leverages normalizing flows for unfolding. By using normalizing flows for neural posterior estimation, NPU offers several key advantages including implicit regularization through the neural network architecture, fast amortized inference that eliminates the need for repeated retraining, and direct access to the full uncertainty in the unfolded result. In addition to introducing NPU, we implement a classical Bayesian unfolding method called Fully Bayesian Unfolding (FBU) in modern Python so it can also be studied. These tools are validated on simple Gaussian examples and then tested on simulated jet substructure examples from the Large Hadron Collider (LHC). We find that the Bayesian methods are effective and worth additional development to be analysis ready for cross section measurements at the LHC and beyond.

Analysis and statistical methods↗
DOE OSTI2026

Beam-beam backgrounds for the Cool Copper Collider

In this paper, we present a comprehensive characterization of beam-beam backgrounds for the Cool Copper Collider (C 3 ), a proposed linear e + e - collider designed for precision Higgs studies at center-of-mass energies of 250 and 550 GeV. Using a simulation pipeline based on the Key4hep framework, we evaluate incoherent pair production and hadron photoproduction backgrounds through the SiD detector for baseline, power-efficiency, and high-luminosity C 3 operating scenarios. The occupancy induced by the beam-beam background is evaluated for each scenario, validating the compatibility of the existing SiD detector design with operations at C 3 without substantial modifications. Furthermore, at the same time, the modular simulation framework and analysis methodology presented in this paper offer a versatile toolkit for background studies in future collider proposals, contributing to a common platform for different machine designs.

Analysis and statistical methods↗