Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning

Demet Sariyer; Elif Yildirim

doi:10.29233/sdufeffd.1783848

Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning

Abstract

Proton accelerators are facilities of critical importance for radiation safety, as interactions of high-energy proton beams with matter produce secondary neutrons. In this study, neutron dose distributions were calculated using FLUKA Monte Carlo simulations for three energy levels (50, 100 and 250 MeV) across different shielding and environmental configurations (soil-air and soil-shield; along the x- and y-axes). The resulting data were predicted using machine learning models, namely Linear Regression (LR), Random Forest (RF), Gradient Boosting Regressor (GBR) and K-Nearest Neighbors (KNN). Model performance was evaluated based on the coefficient of determination (R²) and normalized root mean square error (NRMSE). The results demonstrate that along the x-axis in the soil–air configuration, GBR (R² ≈ 0.906-0.987) and RF (R² ≈ 0.833-0.988) exhibited strong performance, while in the soil-shield x-axis configuration, GBR (R² ≈ 0.762-0.797) and RF (R² ≈ 0.810-0.896) also achieved reliable predictions. Along the y-axis, GBR and RF models showed high accuracy, with R² ≈ 0.843-0.912 and R² ≈ 0.823-0.853 for soil–air, and R² ≈ 0.844-0.981 and R² ≈ 0.887-0.972 for soil-shield, respectively. These findings confirm that RF and GBR models can rapidly and reliably predict secondary neutron doses under varying energy levels and environmental conditions. The proposed hybrid Monte Carlo-Machine learning approach reduces simulation times and provides a fast and reliable method for shielding design, emerging as an effective tool for radiation safety and shield optimization in proton accelerators.

Keywords

References

H. Wiedemann, Particle Accelerator Physics (4th ed.), Springer, 2015.
E. J. N. Wilson, An Introduction to Particle Accelerators, Oxford University Press. ISBN 978–0–19–850829–8, 2001.
S. Sheehy, Applications of Particle Accelerators. CERN Accelerator School Lecture Series. Available online: https://cas.web.cern.ch/previous-schools (Accessed: August 2025). arXiv:2407.10216 [physics.acc-ph], 2024.
D. Sarıyer, “Effects of Different Shielding Materials on Dose Distributions for Tunnel Design in Proton Accelerators”, Ph.D. Thesis, Manisa Celal Bayar University, Institute of Science, Manisa, 2017.
M. B. Paul, A. Dutta Ankan, H. Deb and M. M. Ahasan, “A Monte Carlo simulation model to determine the effective concrete materials for fast neutron shielding”, Radiation Physics and Chemistry, 202, 110476, 2023.
S. H. Rokni, J. D. Cossairt and J. C. Liu, “Radiation Shielding at High-Energy Electron and Proton Accelerators”, Stanford Linear Accelerator Center, 10 December 2007.
D. Sariyer and R. Küçer, “Effect of different materials to concrete as neutron shielding application”, Acta Physica Polonica A, 137(4), 477, 2020.
D. Sarıyer, R. Küçer and N. Küçer, “Neutron shielding properties of concretes containing boron carbide and ferro–Boron”, Procedia - Social and Behavioral Sciences, 195, 1752–1756, 2015.

D. Sarıyer, “Investigation of neutron attenuation through FeB, Fe₂B and concrete”, Acta Physica Polonica A, 137(4), 539–542, 2020.
W. H. Geist, P. A. Santi and M. T. Swinhoe, Nondestructive Assay of Nuclear Materials for Safeguards and Security (2nd ed.), Springer Nature. 2024.
D. Sarıyer and R. Küçer, “Determination of Concrete and Soil Shielding Thicknesses for 100-250 MeV Proton Accelerators Using FLUKA Monte Carlo Code”, SDU Journal of Science (E-Journal), 9(1), 117-124, 2014.
D. D. Di Julio, M. Eshraqi, W. Hees, Y. Hinrichsen, E. Klinky, A. Lundmark, G. Muhrer and D. Nolla, “Radiation transport calculations for the European Spallation Source accelerator environment”, arXiv preprint arXiv:2205.11070, 2022, https://arxiv.org/abs/2205.11070
I. L. Rakhno, N. V. Mokhov, I.S. Tropin and D. Ene, “Activation assessment of the soil around the ESS accelerator tunnel (Fermilab-Conf-17-378-APC)”, Fermi National Accelerator Laboratory; European Spallation Source ERIC, 2017.
D. Sarıyer and R. Küçer, “Determination of shielding thicknesses for different materials in proton accelerators using analytical method”, SDU Journal of Science (E-Journal), 8(1), 100-105, 2013.
T. A. Nahool, A. M. Abdelmonem, M. S. Ali and A. M. Yasser, “Using machine learning to predict gamma shielding properties: a comparative study”, New Journal of Physics, 26, 093035, 2024.
A. Hançerlioğulları, “Monte Carlo Simulation Method and MCNP Code System”, Kastamonu Education Journal, 14(2), 545–556, October 2006.
A. J. Jinia, S. D. Clarke, J. M. Moran and S. A. Pozzi, “Intelligent Radiation: A review of Machine learning applications in nuclear and radiological sciences”, Annals of Nuclear Energy, 201, 110444, 2024.
L.-F. Chen, “Machine Learning-Assisted optimization of modular neutron shielding based on Monte Carlo Simulations”, arXiv preprint, arXiv:2504.12345, April 24, 2025; last revised May 26, 2025. Available: https://arxiv.org/abs/2504.12345
S. Akkoyun, C. M. Yeşilkanat and T. Bayram, “Machine learning predictions for cross sections of 43,44Sc radionuclide production via alpha-induced reactions on Ca targets”, Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, 549, 165293, 2024.
H. Özdoğan, Y. A. Üncü, M. Şekerci and A. Kaplan, “Neural network predictions of reaction cross sections at 18.5 ± 3 MeV using Levenberg-Marquardt algorithm”, Applied Radiation and Isotopes, 204, 111115, 2024.
A. A. A. Alghamdi, “Machine learning for predicting neutron effective dose”, Applied Sciences, 14(13), 5740, 2024.
Y. A. Üncü and H. Özdoğan, “Estimation of production cross-sections of medical 61, 64, 67 Cu radioisotopes byusing reactions using Bayesian regularized artificial neural networks in (p, α) reactions”, Arabian Journal for Science and Engineering, 48, 8173–8179, 2023.
A. L. Edelen, S. G. Biedron, B. E. Chase, D. Edstrom Jr., S. V. Milton and P. Stabile, “Neural Networks for Modeling and Control of Particle Accelerators”, IEEE Transactions on Nuclear Science, 63(2), 878–897, 2016.
R. P, Chowdhury, J. Zamora, T. Ginter and G. Bollen, “Machine learning in accelerator shielding: Application using convolutional neural networks”, Transactions of the American Nuclear Society, 2024.
R. P. Chowdhury, J. C. Zamora, G. Bollen and G., T. Ginter, “Surrogate modeling of Monte Carlo radiation transport with convolutional neural networks for shielding optimization”, Nuclear Instruments and Methods in Physics Research Section B: Beam Interactions with Materials and Atoms, 570, 165909, 2026.
F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot and E. Duchesnay, “Scikit-learn: Machine learning in Python”, Journal of Machine Learning Research, 12, 2825-2830, 2011.
I. D. Rachmawati, N. Effendy and T. Taufik, “Machine learning application for particle accelerator optimization - a review”, IAES International Journal of Artificial Intelligence (IJ-AI), 14(4), 3014-3021, 2025.

Details

Primary Language

English

Subjects

Nuclear Physics, Synchrotrons

Journal Section

Research Article

Authors

Demet Sariyer ^*
0000-0002-7803-111X
Türkiye

Elif Yildirim This is me
0000-0002-1599-9473
Türkiye

Publication Date

May 28, 2026

Submission Date

September 14, 2025

Acceptance Date

November 25, 2025

Published in Issue

Year 2026 Volume: 21 Number: 1

DOI

https://doi.org/10.29233/sdufeffd.1783848

IZ

https://izlik.org/JA63RS78ZM

Cite

RIS / Bibtex

APA

Sariyer, D., & Yildirim, E. (2026). Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning. Süleyman Demirel University Faculty of Arts and Science Journal of Science, 21(1), 1-18. https://doi.org/10.29233/sdufeffd.1783848

AMA

1.Sariyer D, Yildirim E. Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning. Süleyman Demirel University Faculty of Arts and Science Journal of Science. 2026;21(1):1-18. doi:10.29233/sdufeffd.1783848

Chicago

Sariyer, Demet, and Elif Yildirim. 2026. “Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning”. Süleyman Demirel University Faculty of Arts and Science Journal of Science 21 (1): 1-18. https://doi.org/10.29233/sdufeffd.1783848.

EndNote

Sariyer D, Yildirim E (May 1, 2026) Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning. Süleyman Demirel University Faculty of Arts and Science Journal of Science 21 1 1–18.

IEEE

[1]D. Sariyer and E. Yildirim, “Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning”, Süleyman Demirel University Faculty of Arts and Science Journal of Science, vol. 21, no. 1, pp. 1–18, May 2026, doi: 10.29233/sdufeffd.1783848.

ISNAD

Sariyer, Demet - Yildirim, Elif. “Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning”. Süleyman Demirel University Faculty of Arts and Science Journal of Science 21/1 (May 1, 2026): 1-18. https://doi.org/10.29233/sdufeffd.1783848.

JAMA

1.Sariyer D, Yildirim E. Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning. Süleyman Demirel University Faculty of Arts and Science Journal of Science. 2026;21:1–18.

MLA

Sariyer, Demet, and Elif Yildirim. “Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning”. Süleyman Demirel University Faculty of Arts and Science Journal of Science, vol. 21, no. 1, May 2026, pp. 1-18, doi:10.29233/sdufeffd.1783848.

Vancouver

1.Demet Sariyer, Elif Yildirim. Rapid Secondary Neutron Dose Estimation in Proton Accelerators Using FLUKA and Machine Learning. Süleyman Demirel University Faculty of Arts and Science Journal of Science. 2026 May 1;21(1):1-18. doi:10.29233/sdufeffd.1783848