Machine Learning for Nuclear Physics

Back to the ESNT page

8-9 December 2025

 

PROGRAM    ProjectESNTnuclPhysML8dec2025.pdf

 

Machine Learning in Nuclear Physics: Integrative Approaches Across Disciplinary Boundaries

Organizers: D. Regnier (CEA DAM DIF, contact [at] cea.fr), J.-P. Ebran (CEA DAM, DIF), A. Pastore (CEA DES IRESNE)

 

 

Nuclear physics research confronts increasingly complex computational and analytical challenges characterized by (i) high-dimensional, non-linear systems, (ii) massive experimental datasets, (iii) computational limitations in traditional modeling approaches and (iv) increasing complexity of theoretical frameworks.

Machine learning (ML) and artificial intelligence (AI) represent a paradigm shift in addressing these fundamental challenges, offering transformative methodological innovations across multiple research domains.

This workshop will focus on fostering collaborations between experts from the CEA DAM, DRF, and DES, as well as external specialists in AI and nuclear physics. By uniting diverse expertise, we aim to identify key challenges in nuclear physics where AI can provide transformative solutions, establish methodological frameworks for integrating AI into existing research pipelines and define a strategic roadmap for future research and collaborations in this field.

In summary, the goal of the workshop is to bring together practitioners of machine learning in nuclear physics to explore:
• Nuclear structure modeling
• Fission dynamics
• Nuclear data evaluation
• Experimental data analysis

 

 

Talks

 

Alice Bernard (CEA, DAM, DIF) Learning smooth ensembles of Bogoliubov vacua

 

David Regnier (CEA, DAM, DIF)  An overview of machine learning for nuclear physics

 

Chlöe Fougères (CEA, DAM, DIF) On the use of genetic algorithms towards prompt emission properties in fission

 

Enzo Thiriont-Bernolle (CEA, DAM, DIF) Eigenvector continuation of PGCM states for nuclear structure

 

Stavros Bofos (CEA, DES, IRESNE, DER, SPRC) Emulating the PGCM approach to nuclear structure

 

Christophe Bobin (CEA DRT, LIST, LNHB)
Automatic identification and quantification of y-emitting radionuclides with spectral variability using a hybrid Machine, Learning unmixing method

[Jérôme Bobin (CEA DRF, IRFU, Dedip) ] 

 

Antoine Lemasson (GANIL)
Particle identification at VAMOS++ with machine learning techniques

 

Khalil Al Khouri (CEA LIST LNE-LNHB)
Experimental data-driven modeling and prediction of (γ,n) cross-sections with physics-informed neural networks and gradient boosted decision trees

 

Mathieu Thevenin (CEA IRAMIS SPEC)  ESNTdec2025_MThevenin.pdf
A methodology for alpha particles identification in liquid scintillation using a cost-efficient Artificial Neural Network

 

 

Guillaume Scamps (CNRS L2IT-IN2P3) Machine learning time-dependent mean-field simulations of heavy-ion collisions

 

Denis Lacroix (CNRS/IN2P3, IJCLab) Re-inforcement learning on quantum computers

 

Olivier Stezowski (CNRS/IN2P3, IP2I Lyon) Machine learning approaches for signal processing at IP2I

 

 

For discussions

 

Dunstan Becht (CEA, DAM, DIF) Accelerating full CI calculations with ML

 

Emilien Schroeder (ULB, Brussels) Parameter adjustment of large-scale models of nuclear structure with machine learning

 

 

Program

 

	Monday  8th Dec.	Tuesday 9
9h30	D. Regnier	M. Thevenin
10h15	O. Stezowski	Ch. Bobin
11h	Break	Break
11h30	A. Lemasson	C. Fougères
12h15	Lunch	Lunch
13h30	E. Thiriont-Bernolle	K. Al Khouri
14h15	S. Bofos	D. Lacroix
15h	Break	End
15h30	A. Bernard
16h15	G. Scamps
17h	End

 

 

 

Retour accueil ESNT      Back to the ESNT page

 

Création-contact Web ESNT : Valérie Lapoux