Multiple scattering simulation via physics-informed neural networks

被引:2
作者
Nair, Siddharth [1 ]
Walsh, Timothy F. [2 ]
Pickrell, Greg [2 ]
Semperlotti, Fabio [1 ]
机构
[1] Purdue Univ, Sch Mech Engn, Ray W Herrick Labs, W Lafayette, IN 47907 USA
[2] Sandia Natl Labs, Albuquerque, NM 87185 USA
关键词
Physics-informed neural network (PINN); Multiple scattering; Superposition principle; Wave propagation; DEEP LEARNING FRAMEWORK; INVERSE PROBLEMS; BRILLOUIN-SCATTERING; FIELDS;
D O I
10.1007/s00366-024-02038-3
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
This work presents a physics-driven machine learning framework for the simulation of acoustic scattering problems. The proposed framework relies on a physics-informed neural network (PINN) architecture that leverages prior knowledge based on the physics of the scattering problem as well as a tailored network structure that embodies the concept of the superposition principle of linear wave interaction. The framework can also simulate the scattered field due to rigid scatterers having arbitrary shape as well as high-frequency problems. Unlike conventional data-driven neural networks, the PINN is trained by directly enforcing the governing equations describing the underlying physics, hence without relying on any labeled training dataset. Remarkably, the network model has significantly lower discretization dependence and offers simulation capabilities akin to parallel computation. This feature is particularly beneficial to address computational challenges typically associated with conventional mesh-dependent simulation methods. The performance of the network is investigated via a comprehensive numerical study that explores different application scenarios based on acoustic scattering.
引用
收藏
页码:31 / 50
页数:20
相关论文
共 55 条
[1]   Robust solutions of inverse problems in electromagnetic non-destructive evaluation [J].
Altpeter, I ;
Becker, R ;
Dobmann, G ;
Kern, R ;
Theiner, W ;
Yashan, A .
INVERSE PROBLEMS, 2002, 18 (06) :1907-1921
[2]   Review of particle physics [J].
Amsler, C. ;
Doser, M. ;
Antonelli, M. ;
Asner, D. M. ;
Babu, K. S. ;
Baer, H. ;
Band, H. R. ;
Barnett, R. M. ;
Bergren, E. ;
Beringer, J. ;
Bernardi, G. ;
Bertl, W. ;
Bichsel, H. ;
Biebel, O. ;
Bloch, P. ;
Blucher, E. ;
Blusk, S. ;
Cahn, R. N. ;
Carena, M. ;
Caso, C. ;
Cecccci, A. ;
Chakraborty, D. ;
Chen, M. -C. ;
Chivukula, R. S. ;
Cowan, G. ;
Dahl, O. ;
D'Ambrosio, G. ;
Damour, T. ;
de Gouvea, A. ;
DeGrand, T. ;
Dobrescu, B. ;
Drees, M. ;
Edwards, D. A. ;
Eidelman, S. ;
Elvira, V. D. ;
Erler, J. ;
Ezhela, V. V. ;
Feng, J. L. ;
Fetscher, W. ;
Fields, B. D. ;
Foster, B. ;
Gaisser, T. K. ;
Garren, L. ;
Gerber, H. -J. ;
Gerbier, G. ;
Gherghetta, T. ;
Giudice, G. F. ;
Goodman, M. ;
Grab, C. ;
Gritsan, A. V. .
PHYSICS LETTERS B, 2008, 667 (1-5) :1-+
[3]   A new meshless local Petrov-Galerkin (MLPG) approach in computational mechanics [J].
Atluri, SN ;
Zhu, T .
COMPUTATIONAL MECHANICS, 1998, 22 (02) :117-127
[4]   Inverse Designed Metalenses with Extended Depth of Focus [J].
Bayati, Elyas ;
Pestourie, Raphael ;
Colburn, Shane ;
Lin, Zin ;
Johnson, Steven G. ;
Majumdar, Arka .
ACS PHOTONICS, 2020, 7 (04) :873-878
[5]   ELEMENT-FREE GALERKIN METHODS [J].
BELYTSCHKO, T ;
LU, YY ;
GU, L .
INTERNATIONAL JOURNAL FOR NUMERICAL METHODS IN ENGINEERING, 1994, 37 (02) :229-256
[6]  
Bertero M., 2006, COMPL SYST BIOM, DOI 10.1007/88-470-0396-2_1
[7]   Application of Light Scattering Techniques to Nanoparticle Characterization and Development [J].
Carvalho, Patricia M. ;
Felicio, Mario R. ;
Santos, Nuno C. ;
Goncalves, Sonia ;
Domingues, Marco M. .
FRONTIERS IN CHEMISTRY, 2018, 6
[8]   Physics-informed neural networks for imaging and parameter retrieval of photonic nanostructures from near-field data [J].
Chen, Yuyao ;
Dal Negro, Luca .
APL PHOTONICS, 2022, 7 (01)
[9]   Physics-informed neural networks for inverse problems in nano-optics and metamaterials [J].
Chen, Yuyao ;
Lu, Lu ;
Karniadakis, George Em ;
Dal Negro, Luca .
OPTICS EXPRESS, 2020, 28 (08) :11618-11633
[10]   SOLVING THE INVERSE PROBLEMS FOR SOIL-MOISTURE AND TEMPERATURE PROFILES BY SEQUENTIAL ASSIMILATION OF MULTIFREQUENCY REMOTELY-SENSED OBSERVATIONS [J].
ENTEKHABI, D ;
NAKAMURA, H ;
NJOKU, EG .
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING, 1994, 32 (02) :438-448