| Title: |
Experimental data-driven modeling and prediction of (γ,n) cross-sections with Physics-Informed Neural Networks and Gradient Boosted Decision Trees |
| Authors: |
Besnard Vauterin, Clement; Besnard, Quentin; Blideanu, Valentin; Al Khouri, Khalil; Bony, Mathis |
| Contributors: |
Laboratoire National Henri Becquerel (CEA, LIST) (LNHB (CEA, LIST)); Département d'instrumentation Numérique (CEA, LIST) (DIN (CEA, LIST)); Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)); Direction de Recherche Technologique (CEA) (DRT (CEA)); Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Direction de Recherche Technologique (CEA) (DRT (CEA)); Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay-Laboratoire d'Intégration des Systèmes et des Technologies (LIST (CEA)); Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Commissariat à l'énergie atomique et aux énergies alternatives (CEA)-Université Paris-Saclay; Laboratoire d'Informatique Fondamentale et Appliquée de Tours (LIFAT); Université de Tours (UT)-Institut National des Sciences Appliquées - Centre Val de Loire (INSA CVL); Institut National des Sciences Appliquées (INSA)-Institut National des Sciences Appliquées (INSA); French National Laboratory of Metrology and Testing |
| Source: |
ISSN: 0168-583X ; EISSN: 1872-9584 ; Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms. |
| Publisher Information: |
CCSD; Elsevier |
| Publication Year: |
2025 |
| Collection: |
Université François-Rabelais de Tours: HAL |
| Subject Terms: |
actinides; ionizing radiation; stable isotopes; Gradient Boosted Decision Tree; Giant Dipole Resonance; Lorentzian resonance behavior; energy threshold; neural network; simulation; modeling; artificial intelligence; machine learning; metrology; [PHYS.HEXP]Physics [physics]/High Energy Physics - Experiment [hep-ex]; [INFO.INFO-MO]Computer Science [cs]/Modeling and Simulation |
| Description: |
International audience ; In this study, we present a hybrid machine learning framework for modeling and predicting (γ,n) reaction cross sections across the nuclear chart, combining physical interpretability with predictive power. The first stage uses a Physics-Informed Neural Network (PINN) to fit experimental data from EXFOR while enforcing domain-specific constraints, such as energy thresholds, Lorentzian resonance behavior, and monotonicity beyond the Giant Dipole Resonance (GDR). These high-quality fits are then used to train a Gradient Boosted Decision Tree (GBDT) model on a broad set of nuclear features including mass, shell effects, separation energies, and deformation parameters. The resulting model agrees well with both experimental and evaluated data for known isotopes and extrapolates plausibly to exotic nuclides lacking measurements. Case studies on stable isotopes, actinides, and neutron-rich nuclei demonstrate the model’s robustness. This approach illustrates the complementarity of physics-informed and data-driven modeling for improving cross-section coverage in nuclear physics, simulation, and security applications. |
| Document Type: |
article in journal/newspaper |
| Language: |
English |
| DOI: |
10.1016/j.nimb.2025.165771 |
| Availability: |
https://cea.hal.science/cea-05115470; https://cea.hal.science/cea-05115470v1/document; https://cea.hal.science/cea-05115470v1/file/Data-Driven%20Mod%20and%20Pred%20of%20XS.pdf; https://doi.org/10.1016/j.nimb.2025.165771 |
| Rights: |
info:eu-repo/semantics/OpenAccess |
| Accession Number: |
edsbas.89E76BD2 |
| Database: |
BASE |