Deep Learning Application for Milne problem with linear anisotropic scattering

Year 2025, Early View, 1 - 1

R. Gökhan Türeci

https://doi.org/10.35378/gujs.1521834

Abstract

Using deep learning algorithms, which is a sub-branch of artificial intelligence, in this study, a deep learning model is developed according to both the number of secondary neutrons and the linear anisotropic scattering coefficient. These are independent variables that the dependent variable is the extrapolation distance. The training data set was calculated with HN method. ANN algorithm was written by TensorFlow and Keras which are the modules in Python programming language. The performance of the deep learning model for this problem has high performance so that the predicted new data which doesn’t be in the training data set is reliable according to the success of the model.

Keywords

Deep Learning, Milne problem, Linear anisotropic scattering, Artificial neural networks

References

• [1] Placzek, G., and W. Seidel., “Milne's Problem in Transport Theory”, Physical Review, 72: 550-555, (1947).
• [2] Noble, B., The Wiener-Hopf Technique, Pergamon Press, Oxford, (1958).
• [3] Case, K.M. and Zweifel, P.F., Linear Transport Theory, Massachusetts: Addition-Wesley, (1967).
• [4] McCormick, N.J., “One-Speed Neutron Transport Problems in Plane Geometry”, PhD thesis, The University of Michigan, (1964).
• [5] McCormick N. J., and Kuščer, I., “Half‐Space Neutron Transport with Linearly Anisotropic Scattering”, Journal of Mathematical Physics, 6 (12): 1939-1945, (1964).
• [6] Kavenoky, A., “The CN Method of Solving the Transport Equation: Application to Plane Geometry”, Nuclear Science and Engineering, 65, 209, (1978).
• [7] Sahni, D.C., and Kumar, V., “Numerical solution of singular integral equations of neutron transport problems”, Transport Theory and Statistical Physics, 16(7): 959-978, (1987).
• [8] Atalay, M. A., “Milne problem for linearly anisotropic scattering and a specularly reflecting boundary”, Annals of Nuclear Energy, 27(16): 1483-1504, (2000).
• [9] Atalay, M. A., “Milne problem for linearly anisotropic scattering and a specular and diffuse reflecting boundary”, Jornal of Quantative Spectroscopy and Radiative Transfer, 72(5): 589-606, (2002).
• [10] Hussein, A., and Selim, M.M., “A general analytical solution for the stochastic Milne problem using Karhunen–Loeve (K–L) expansion”, Journal of Quantitative Spectroscopy and Radiative Transfer, 125: 84-92, (2013).
• [11] Slama, H., El-Bedwhey, N.A., El-Depsy, A. and Selim, M. M., “Solution of the finite Milne problem in stochastic media with RVT Technique”, The European Physical Journal Plus, 132: 505, (2017).
• [12] Hussein. A., and Selim, M. M., “A complete probabilistic solution for a stochastic Milne problem of radiative transfer using KLE-RVT technique”, J Jornal of Quantative Spectroscopy and Radiative Transfer, 232: 54-65, (2019).
• [13] Sahni, D. C., Türeci, R. G., and Bozkir, A. Z. “Partial Range Completeness of Case Eigenfunctions and Numerical Solution of Singular Integral Equations of Particle Transport Problems”, Journal of Computational and Theoretical Transport. 49(7): 349–367, (2020).
• [14] Ganapol, B. D., “The Ln/Ln0 Method for 1D Neutron Transport in a Slab Medium”, Journal of Computational and Theoretical Transport, 51(5): 239-264, (2022).
• [15] Ganapol , B. D., “Numerical Caseology by Lagrange Interpolation for the 1D Neutron Transport Equation in a Slab”, Nuclear Science and Engineering, 197(1): 1-13, (2023).
• [16] Siewert, C. E., “The FN method for solving radiative-transfer problems in plane geometry”, Astrophysical Space Science. 58 (1): 131–7, (1978).
• [17] Tezcan, C., Kaşkaş, A., and Güleçyüz, M. Ç., 2003. “The HN method for solving linear transport equation: Theory and applications”, Jornal of Quantative Spectroscopy and Radiative Transfer, 78 (2): 243-254, (2003).
• [18] Gülderen, D., Sahni, D. C., Türeci, R. G., and Aydιn, A.,“The Milne Problem for Linear-Triplet Anisotropic Scattering with HN Method”, Journal of Computational and Theoretical Transport, 51(6): 329-353, (2022).
• [19] Türeci, R. G., “The Milne Problem with the Anlı-Güngör Scattering”, Journal of Computational and Theoretical Transport, 51(6): 354-371, (2022).
• [20] Numpy, https://numpy.org/. Access date: 22.07.2024
• [21] Pandas, https://pandas.pydata.org/. Access date: 22.07.2024
• [22] Seaborn, https://seaborn.pydata.org/. Access date: 22.07.2024
• [23] Matplotlib, https://matplotlib.org/. Access date: 22.07.2024
• [24] Yeo, I. K., and Richard A. J., “A New Family of Power Transformations to Improve Normality or Symmetry”, Biometrika, 87 (4): 954–959, (2000).
• [25] Sklearn, https://scikit-learn.org/stable/. Access date: 22.07.2024
• [26] Nair, V., and Hinton, G. E., “Rectified Linear Units Improve Restricted Boltzmann Machines”, Conference: Proceedings of the 27th International Conference on Machine Learning (ICML-10), June 21-24, Haifa, Israel, (2010).
• [27] Keras, https://keras.io/. Access date: 22.07.2024
• [28] Diederik P. K., Jimmy B.,“Adam: A Method for Stochastic Optimization”, Computer Science > Machine Learning, arXiv:1412.6980, (2014).
• [29] Zheng C., Liub L., and Muc L., “Solving the linear transport equation by a deep neural network approach”, Journal of Discrete and Continuous Dynamical System-S, 15(4): 669-686, (2021).
• [30] Xie Y., Wang Y., Ma Y., and Wu Z., “Neural Network Based Deep Learning Method for Multi-Dimensional Neutron Diffusion Problems with Novel Treatment to Boundary”, Journal of Nuclear Engineering, 2: 533-552, (2021).
• [31] Whewell, B., and McClarren, R. G., “Data reduction in deterministic neutron transport calculations using machine learning”, Annals of Nuclear Energy, 176, 109276, (2022).
• [32] Zolfaghari M., Masoudi S. F., Rahmani F., Fathi A., “Thermal neutron beam optimization for PGNAA applications using Q-learning algorithm and neural network”, Scientific Reports, 12, 8635, (2022). [33] Türeci R. G., “Machine Learning Applications to the One-speed Neutron Transport Problems”, Cumhuriyet Science Journal, 43(4): 726-738. (2022).