SavedAdd your journal

Journals / International Journal of 3D Printing Technologies and Digital Industry / 2026 / Cilt: 10 Sayı: 2

MULTIDIRECTIONAL NEUTRON TRANSPORT AND DOSE COMPLIANCE IN MULTILAYER IRON-CONCRETE SHIELDING FOR A 50 MEV PROTON ACCELERATOR: A MONTE CARLO-MACHINE LEARNING APPROACH

Mustafa Emre Erbil(MANİSA CELAL BAYAR ÜNİVERSİTESİ HASAN FERDİ TURGUTLU TEKNOLOJİ FAKÜLTESİ)0009-0003-9394-8588
Demet Sariyer(MANİSA CELAL BAYAR ÜNİVERSİTESİ TURGUTLU MESLEK YÜKSEKOKULU)0000-0002-7803-111X
Pages
402–424
Publication Date
2026-08-31
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results demonstrate that tree-based ensemble models can accurately capture nonlinear dose distributions spanning a wide dynamic range (RF: R² = 0.9999 / 0.9992; GBR: R² = 0.9997 / 0.9988), whereas the performance of the LR model remains limited.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study, the multidirectional transport and dose compliance of secondary neutron fields generated by the interaction of 50 MeV protons with a copper target were investigated within a multilayer iron-concrete hybrid shielding system using a hybrid Monte Carlo (MC)-Machine Learning (ML) approach.
📊
Key Findings & Data:High-accuracy FLUKA MC simulations were employed to compute the ambient dose equivalent H*(10) distributions along both horizontal (±x) and vertical (±y) directions in a realistic tunnel-type accelerator geometry.
💡
Conclusion & Impact:The results demonstrate that tree-based ensemble models can accurately capture nonlinear dose distributions spanning a wide dynamic range (RF: R² = 0.9999 / 0.9992; GBR: R² = 0.9997 / 0.9988), whereas the performance of the LR model remains limited.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Hybrid Monte Carlo-Machine Learning · Surrogate Modeling · Random Forest

Abstract

In this study, the multidirectional transport and dose compliance of secondary neutron fields generated by the interaction of 50 MeV protons with a copper target were investigated within a multilayer iron-concrete hybrid shielding system using a hybrid Monte Carlo (MC)-Machine Learning (ML) approach. High-accuracy FLUKA MC simulations were employed to compute the ambient dose equivalent H*(10) distributions along both horizontal (±x) and vertical (±y) directions in a realistic tunnel-type accelerator geometry. Based on the resulting dose-distance dataset, Linear Regression (LR), Random Forest (RF), and Gradient Boosting Regressor (GBR) models were developed. During the data preprocessing stage, log(1+y) transformation and min-max normalization were applied. Model performances were evaluated using an 80% training – 20% testing split, 5-fold cross-validation, and GridSearch-based hyperparameter optimization. The results demonstrate that tree-based ensemble models can accurately capture nonlinear dose distributions spanning a wide dynamic range (RF: R² = 0.9999 / 0.9992; GBR: R² = 0.9997 / 0.9988), whereas the performance of the LR model remains limited. From a radiation protection perspective, the analysis indicates that dose levels along the horizontal direction and particularly in the upward (+y) region exceed international regulatory limits. In contrast, a significant attenuation is observed in the downward direction due to the combined moderating and absorbing effects of the concrete floor and surrounding soil. In conclusion, the proposed MC-ML framework provides a reliable and scalable methodology for the rapid analysis and optimization of multilayer shielding systems by significantly reducing the computational cost associated with conventional MC-based dose predictions.

Özet

In this study, the multidirectional transport and dose compliance of secondary neutron fields generated by the interaction of 50 MeV protons with a copper target were investigated within a multilayer iron-concrete hybrid shielding system using a hybrid Monte Carlo (MC)-Machine Learning (ML) approach. High-accuracy FLUKA MC simulations were employed to compute the ambient dose equivalent H*(10) distributions along both horizontal (±x) and vertical (±y) directions in a realistic tunnel-type accelerator geometry. Based on the resulting dose-distance dataset, Linear Regression (LR), Random Forest (RF), and Gradient Boosting Regressor (GBR) models were developed. During the data preprocessing stage, log(1+y) transformation and min-max normalization were applied. Model performances were evaluated using an 80% training – 20% testing split, 5-fold cross-validation, and GridSearch-based hyperparameter optimization. The results demonstrate that tree-based ensemble models can accurately capture nonlinear dose distributions spanning a wide dynamic range (RF: R² = 0.9999 / 0.9992; GBR: R² = 0.9997 / 0.9988), whereas the performance of the LR model remains limited. From a radiation protection perspective, the analysis indicates that dose levels along the horizontal direction and particularly in the upward (+y) region exceed international regulatory limits. In contrast, a significant attenuation is observed in the downward direction due to the combined moderating and absorbing effects of the concrete floor and surrounding soil. In conclusion, the proposed MC-ML framework provides a reliable and scalable methodology for the rapid analysis and optimization of multilayer shielding systems by significantly reducing the computational cost associated with conventional MC-based dose predictions.

🔖

Cite This Article

Erbil, M. E., Sariyer, D. (2026). MULTIDIRECTIONAL NEUTRON TRANSPORT AND DOSE COMPLIANCE IN MULTILAYER IRON-CONCRETE SHIELDING FOR A 50 MEV PROTON ACCELERATOR: A MONTE CARLO-MACHINE LEARNING APPROACH. International Journal of 3D Printing Technologies and Digital Industry, Cilt: 10 Sayı: 2, 402–424. https://doi.org/10.46519/ij3dptdi.1944437

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (49)

  1. International Atomic Energy Agency, “Radiation Protection and Safety of Radiation Sources: International Basic Safety Standards”, IAEA Safety Standards Series No. GSR Part 3, Vienna, 2014.
  2. National Council on Radiation Protection and Measurements, “Radiation Protection for Particle Accelerator Facilities”, NCRP Report No. 144, Bethesda, MD, 2003.
  3. International Commission on Radiological Protection, “The 2007 Recommendations of the International Commission on Radiological Protection”, ICRP Publication 103, Elsevier, Oxford, 2007.
  4. Sarıyer, D., Erbil, M.E., “Comparative analysis of secondary particle production and spatial dose distributions in multilayer concrete-iron shielding systems for a 50 MeV proton accelerator using FLUKA”, International Journal of Computational and Experimental Science and Engineering, Vol. 12, Issue 1, Pages 1485-1495, 2026.
  5. International Atomic Energy Agency, “Radiation Protection in the Design of Radiotherapy Facilities”, IAEA Safety Reports Series No. 47, Vienna, 2006.
  6. Agosteo, S., Magistris, M., Mereghetti, A., Silari, M., Zajacova, Z., “Shielding data for 100-250 MeV proton accelerators”, Nuclear Instruments and Methods in Physics Research B, Vol. 265, Pages 581-598, 2007.
  7. Yani, S., Rahma, W., Sumaryada, T., Haryanto, F., Tai, D. T., Omer, H., Tamam N. Nuraeni, N., “Optimization of proton radiation shielding using multilayer concrete-iron-polyethylene barriers: A PHITS Monte Carlo study”, Radiation Physics and Chemistry, Vol. 240, Article No. 113422, 2026.
  8. Aliyah, F., “Multi-layer Radiation Shielding Design for Compact Proton Therapy System Using Monte Carlo Simulation”, M.Sc. Thesis, Universiti Sains Malaysia, 2024.
  9. Sarıyer, D., Küçer, R., “Double-layer neutron shield design as neutron shielding application”, AIP Conference Proceedings, Vol. 1935, Article No. 180004, 2018.
  10. Emikönel, S., Akkurt, İ., “Radiation Shielding Properties of B₂O₃-Bi₂O₃ Glass”, International Journal of Computational and Experimental Science and Engineering, Vol. 11, Issue 2, Article No. 2157, 2025.
  11. OECD, “Shielding Aspects of Accelerators, Targets and Irradiation Facilities (SATIF-10)”, OECD Nuclear Energy Agency, Paris, 2010.
  12. Sarıyer, D., “Hybrid machine learning-Monte Carlo approach for neutron shielding in high-energy proton facilities”, Journal of Subatomic Particles and Cosmology, Vol. 5, Article No. 100309, 2026.
  13. Sarıyer, D., Yıldırım, E., “A hybrid Monte Carlo-machine learning framework for high-energy neutron shielding using boron-enhanced concrete”, International Journal of Computational and Experimental Science and Engineering, Vol. 12, Issue 1, Pages 447-461, 2026.
  14. Gökcan, A.O., Sarıyer, D., “High-energy neutron shielding analysis using curve fitting and machine learning: A Monte Carlo-based study in concrete and ferro-boron configurations”, Annals of Nuclear Energy, Vol. 232, Article No. 112244, 2026.
  15. Sarıyer, D., Yıldırım, E., “Multidirectional neutron shielding analysis and surrogate-based optimization of multilayer ferroboron for a 1000 MeV proton accelerator”, Annals of Nuclear Energy, Vol. 238, Article No. 112537, 2026.
  16. Sarıyer, D., Gökcan, A.O., “A hybrid Monte Carlo-machine learning framework for neutron dose attenuation modeling in layered iron-concrete shields of a 1000 MeV proton accelerator”, Annals of Nuclear Energy, Vol. 238, Article No. 112572, 2026.
  17. Sarıyer, D., Küçer, R., “Determination by FLUKA Monte Carlo code of shield thicknesses of concrete and soil for 100-250 MeV proton accelerators”, SDU Journal of Science, Vol. 9, Issue 1, Pages 117-124, 2014.
  18. Sarıyer, D., Küçer, R., “Determination of shielding thicknesses by using analytical method for different materials in proton accelerators”, SDU Journal of Science, Vol. 8, Issue 1, Pages 100-105, 2013.
  19. Aydın, H., Süsoy Doğan, G., Tekin, H.O., Şen Baykal, D., İltuş, Y.C., “Examining the Neutron and Gamma Attenuation Characteristics of Various Amorphous Structures with Bioactive Properties”, International Journal of Computational and Experimental Science and Engineering, Vol. 11, Issue 3, Article No. 2176, 2025.
  20. Hamad, M.Kh., “Synergistic Evaluation of Ionizing Radiation Shielding in Novel Lead-Free Alloys Using the Geant4 MC Toolkit”, International Journal of Applied Sciences and Radiation Research, Vol. 2, Issue 1, Article No. 47, 2025.
  21. Ferrari, A., Sala, P.R., Fasso, A., Ranft, J., “FLUKA: A Multi-Particle Transport Code”, CERN-2005-010, 2005.
  22. Böhlen, T. T., Cerutti, F., Chin, M. P. W., Fassò, A., Ferrari, A., Ortega, P. G., Mairani, A., Vlachoudis, V., “The FLUKA code: Developments and challenges for high energy and medical applications”, Nuclear Data Sheets, Vol. 120, Pages 211-214, 2014.
  23. Battistoni, G., Boehlen, T., Cerutti, F., Chin, P. W., Esposito, L. S., Fasso, A., Ferrari, A., Smirnov, G., “Overview of the FLUKA code”, Annals of Nuclear Energy, Vol. 82, Pages 10-18, 2015.
  24. Hançerlioğulları, A., “Monte Carlo simulation method and MCNP code system”, Kastamonu Education Journal, Vol. 14, Issue 2, Pages 545-556, 2006.
  25. Sarıyer, D., “Investigation of neutron attenuation through FeB, Fe₂B and concrete”, Acta Physica Polonica A, Vol. 137, Issue 4, Pages 539-542, 2020.
  26. Sarıyer, D., “Effects of Different Shielding Materials on Dose Distributions for Tunnel Design in Proton Accelerators”, Ph.D. Thesis, Manisa Celal Bayar University, 2017.
  27. Sarıyer, D., Küçer, R., Küçer, N., “Neutron shielding properties of concrete and ferro-boron”, Acta Physica Polonica A, Vol. 128, Issue 2, Pages B201-B203, 2015.
  28. Sarıyer, D., “FLUKA Monte Carlo assessment of Fe₂B-based shielding materials for secondary neutrons in a 1000 MeV proton accelerator”, International Journal of Computational and Experimental Science and Engineering, Vol. 11, Issue 4, Pages 9864-9869, 2025.
  29. Chowdhury, R. P., Zamora, J. C., Bollen, G., Ginter, T., “Surrogate modeling of Monte Carlo radiation transport with convolutional neural networks for shielding optimization”, Nuclear Instruments and Methods in Physics Research B, Vol. 570, Article No. 165909, 2026.
  30. Chowdhury, R. P., Zamora, J., Ginter, T., Bollen, G., “Machine learning in accelerator shielding: Application using convolutional neural networks”, Transactions of the American Nuclear Society, 2025.
  31. Chen, L.F., “Machine learning-assisted optimization of modular neutron shielding based on Monte Carlo simulations”, arXiv preprint, 2025.
  32. Erdem, O. F., Broughton, D. P., Svoboda, J., Huang, C., Radaideh, M. I., “On the impact of Monte Carlo statistical uncertainty on surrogate-based design optimization”, arXiv preprint, 2025.
  33. Edelen, A. L., Biedron, S. G., Chase, B. E., Edstrom, D., Milton, S. V., Stabile, P., “Neural networks for modeling and control of particle accelerators”, IEEE Transactions on Nuclear Science, Vol. 63, Issue 2, Pages 878-897, 2016.
  34. Antonsanti, P. L., Daniel, G., Bachoc, F., Le Loirec, C., “Dynamic dose equivalent rate estimation in dismantling: Physic-informed surrogate modeling”, Nuclear Engineering and Design, Vol. 436, Article No. 113971, 2025.
  35. Fang, P.W., Hsieh, Y.I., Shiau, A.C., Sheu, R.J., “Studies on Shielding and Activation Levels in a Concrete-Iron-Concrete Sandwich Structure Wall in the CMUH Proton Therapy Facility”, Health Physics, Vol. 129, Issue 4, Pages 307-314, 2025.
  36. ICRU, “Quantities and Units in Radiation Protection Dosimetry”, ICRU Report 51, 1993.
  37. Sarıyer, D., Küçer, R., “Development of neutron shielding concrete containing iron content materials”, AIP Conference Proceedings, Vol. 1935, Article No. 100003, 2018.
  38. Ene, D., “Radioprotection studies for the ESS superconducting linear accelerator”, ESS Technical Note, 2010.
  39. Alhazmi, N.K., Alanazi, S.D., Alrowily, H.S.A., Alkhamsan, K.F., Al-Rashidi, F.A.D., Mohammed, A.S.S., Khalaf, A.M., Alshammari, S.F.N., Alzaidi, A.A., AlQusayri, A.A., “Radiation Safety Compliance and Protective Practices Among Radiologic Technologists”, International Journal of Computational and Experimental Science and Engineering, Vol. 10, Issue 4, Article No. 4664, 2024.
  40. Montgomery, D. C., Peck, E. A., Vining, G. G., “Introduction to Linear Regression Analysis”, Wiley, 2021.
  41. Breiman, L., “Random forests”, Machine Learning, Vol. 45, Issue 1, Pages 5-32, 2001.
  42. Friedman, J.H., “Greedy function approximation: A gradient boosting machine”, Annals of Statistics, Vol. 29, Issue 5, Pages 1189-1232, 2001.
  43. Natekin, A., Knoll, A., “Gradient boosting machines: A tutorial”, Frontiers in Neurorobotics, Vol. 7, Issue 21, 2013.
  44. Pedregosa, F., Varoquaux G., Gramfort A., Michel V., Grisel O., Blondel M., Prettenhofer P., Weiss R., Dubourg V., “Scikit-learn: Machine learning in Python”, Journal of Machine Learning Research, Vol. 12, Pages 2825-2830, 2011.
  45. Hastie, T., Tibshirani, R., Friedman, J. H., Friedman, J. H., “The Elements of Statistical Learning”, Vol. 2, Pages 1-758, Springer, 2009.
  46. Browne, M.W., “Cross-validation methods”, Journal of Mathematical Psychology, Vol. 44, Issue 1, Pages 108-132, 2000.
  47. Jinia, A.J., et al., “Intelligent radiation: A review of machine learning applications in nuclear and radiological sciences”, Annals of Nuclear Energy, Vol. 201, Article No. 110444, 2024.
  48. Zheng, Y., Newhauser, W., Klein, E., Low, D., “Monte Carlo simulation of the neutron spectral fluence and dose equivalent for use in shielding a proton therapy vault”, Physics in Medicine & Biology, Vol. 54, Issue 22, Pages 6943-6957, 2009.
  49. Wang, J.-L., Cruz, L.A., Wu, Q.-B., Wang, Q., Wei, Y., Wang, H.-K., “Radiation shielding design of a compact single-room proton therapy based on synchrotron”, Nuclear Science and Techniques, Vol. 31, Issue 1, 2020.