Abstract
Analysis of the possibilities of physics-informed neural networks intended for solution of boundary-value problems for partial differential equations is carried out. The possibilities of using radial basis-function networks as physics-informed neural networks are shown. Networks of radial basis functions for solving forward and inverse problems describing processes in piecewise homogeneous media have been proposed and investigated on model problems.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
REFERENCES
E. Lagaris, A. Likas, and D. I. Fotiadis, IEEE Trans. Neural Networks 9 (5), 987 (1998).
N. Yadav, A. Yadav, and M. Kumar, An Introduction to Neural Network Methods for Differential Equations (Springer, Dordrecht, 2015).
G. Cybenko, Math. Control, Signals Syst. 2, 303 (1989).
K. Hornik, Neural Networks 4 (2), 251 (1991). https://doi.org/10.1016/0893-6080(91)90009-T
B. Hanin, Universal function approximation by deep neural nets with bounded width and ReLU activations (2017). https://arxiv.org/abs/1708.02691v2
M. Raissi, P. Perdikaris, and G. E. Karniadakis, Physics informed deep learning (Part I): Data-driven solutions of nonlinear partial differential equations (2017). https://arxiv.org/abs/1711.10561
M. Raissi, P. Perdikaris, and G. E. Karniadakis, Physics informed deep learning (Part II): Data-driven discovery of nonlinear partial differential equations (2017). https://arxiv.org/abs/1711.10566
M. Raissi, P. Perdikaris, and G. E. Karniadakis, J. Comput. Phys. 378, 686 (2019).
G. E. Karniadakis, I. G. Kevrekidis, L. Lu, and L. Yang, Nat. Rev. Phys. 3, 422 (2021).
A. G. Bavdin, B. A. Pearlmutter, A. A. Radul, and J. M. Siskind, J. Mach. Learn. Res. 18 (1), 1 (2018).
S. Cuomo, V. S. D. Cola, F. Giampaolo, G. Rozza, M. Raissi, and F. Piccialli, J. Sci. Comput. 92, 88 (2022).
M. J. Kochenderfer and T. A. Wheeler, Algorithms for Optimization (MIT Press, Cambridge, 2019).
V. Lakshmanan, S. Robinson, and M. Munn, Machine Learning Design Patterns: Solutions to Common Challenges in Data Preparation, Model Building, and MLOps (O’Reilly Media, 2020).
D. Tarkhov and A. Vasilyev, Semi-Empirical Neural Network Modeling and Digital Twins Development (Academic, Cambridge, 2019).
A. A. Ramabathiran and P. Ramachandran, J. Comput. Phys. 445, 110600 (2021).
M. M. Alqezweeni, R. A. Glumskov, V. I. Gorbachenko, and D. A. Stenkin, Solving partial differential equations on radial basis functions networks and on fully connected deep neural networks, in Proc. in Adaptation, Learning and Optimization: Proc. Int. Conf. on Intelligent Vision and Computing (ICIVC 2021) (Springer, Cham, 2022), Vol. 15, p. 240. https://doi.org/10.1007/978-3-030-97196-0_20
C. C. Aggarwal, Neural Networks and Deep Learning: A Textbook (Springer, Cham, 2018). https://doi.org/10.1007/978-3-319-94463-0
P. Niyogi and F. Girosi, Neural Comput. 8 (4), 819 (1996).
V. I. Gorbachenko and M. V. Zhukov, Comput. Math. Math. Phys. 57, 145 (2017). https://doi.org/10.1134/S0965542517010079
M. M. Alqezweeni and V. I. Gorbachenko, Modeli, Sist., Seti Ekon., Tekh., Prirode O-ve, No. 3 (23), 123 (2017). https://mss.pnzgu.ru/mss11317
D. W. Marquardt, J. Soc. Ind. Appl. Math. 11 (2), 431 (1963).
H. S. Carslaw, Introduction to the Mathematical Theory of the Conduction of Heat in Solids (Franklin Classic, Blackweel, 2018).
J. H. Abou-Kassem, M. Rafiqul Islam, and S. M. Farouq-Ali, Petroleum Reservoir Simulation: The Engineering Approach (Gulf Professional, Houston, 2020).
M. P. Anderson, W. W. Woessner, and R. J. Hunt, Applied Groundwater Modeling: Simulation of Flow and Advective Transport (Academic, Cambridge, 2015).
D. A. Stenkin and V. I. Gorbachenko, Solving equations describing processes in a piecewise homogeneous medium on radial basis functions networks, in Advances in Neural Computation, Machine Learning, and Cognitive Research IV. NEUROINFORMATICS 2020. Studies in Computational Intelligence (Springer, Cham, 2021), Vol. 925, p. 412. https://doi.org/10.1007/978-3-030-60577-3_49
V. I. Gorbachenko and D. A. Stenkin, Solving of inverse coefficient problems on networks of radial basis functions, in Advances in Neural Computation, Machine Learning, and Cognitive Research V. NEUROINFORMATICS 2021. Studies in Computational Intelligence (Springer, Cham, 2022), Vol. 1008, p. 230. https://doi.org/10.1007/978-3-030-91581-0_31
A. A. Samarskii and P. N. Vabishchevich, Numerical Methods for Solving Inverse Problems of Mathematical Physics (Walter de Gruyter, Berlin, 2007).
V. A. Morozov, Methods for Solving Incorrectly Posed Problems (Springer-Verlag, New York, 1984). https://doi.org/10.1007/978-1-4612-5280-1
Funding
This work was supported by ongoing institutional funding. No additional grants to carry out or direct this particular research were obtained.
Author information
Authors and Affiliations
Corresponding authors
Ethics declarations
The authors of this work declare that they have no conflicts of interest.
Additional information
Translated by M. Drozdova
Publisher’s Note.
Pleiades Publishing remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Gorbachenko, V.I., Stenkin, D.A. Physics-Informed Radial Basis-Function Networks. Tech. Phys. 68, 151–157 (2023). https://doi.org/10.1134/S1063784223050018
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1134/S1063784223050018