Neural Operator-Based Surrogate Solver for Free-Form Electromagnetic Inverse Design

被引：25

作者：

Augenstein, Yannick ^{[1
]}

Repan, Taavi ^{[3
]}

Rockstuhl, Carsten ^{[1
,2
]}

机构：

[1] Karlsruhe Inst Technol, Inst Theoret Solid State Phys, D-76131 Karlsruhe, Germany

[2] Karlsruhe Inst Technol, Inst Nanotechnol, D-76021 Karlsruhe, Germany

[3] Univ Tartu, Inst Phys, EE-50411 Tartu, Estonia

来源：

ACS PHOTONICS | 2023年 / 10卷 / 05期

关键词：

machine learning; neural operators; inverse design; nanophotonics; ALGORITHM; NETWORKS;

D O I：

10.1021/acsphotonics.3c00156

中图分类号：

TB3 [工程材料学];

学科分类号：

0805 ; 080502 ;

摘要：

Neural operators have emerged as a powerful tool for solving partial differential equations in the context of scientific machine learning. Here, we implement and train a modified Fourier neural operator as a surrogate solver for electromagnetic scattering problems and compare its data efficiency to existing methods. We further demonstrate its application to the gradient-based nanophotonic inverse design of free-form, fully three-dimensional electromagnetic scatterers, an area that has so far eluded the application of deep-learning techniques.

引用

页码：1547 / 1557

页数：11

共 69 条

[61] Learning the solution operator of parametric partial differential equations with physics-informed DeepONets [J].

Wang, Sifan ;

Wang, Hanwen ;

Perdikaris, Paris .

SCIENCE ADVANCES, 2021, 7 (40)

[62] Inverse design of nanophotonics devices and materials [J].

Wiecha, Peter R. ;

Petrovb, Alexander Yu. ;

Genevet, Patrice ;

Bogdanov, Andrey .

PHOTONICS AND NANOSTRUCTURES-FUNDAMENTALS AND APPLICATIONS, 2022, 52

[63] Deep Learning Meets Nanophotonics: A Generalized Accurate Predictor for Near Fields and Far Fields of Arbitrary 3D Nanostructures [J].

Wiecha, Peter R. ;

Muskens, Otto L. .

NANO LETTERS, 2020, 20 (01) :329-338

[64] Comment: The FAIR Guiding Principles for scientific data management and stewardship [J].

Wilkinson, Mark D. ;

Dumontier, Michel ;

Aalbersberg, IJsbrand Jan ;

Appleton, Gabrielle ;

Axton, Myles ;

Baak, Arie ;

Blomberg, Niklas ;

Boiten, Jan-Willem ;

Santos, Luiz Bonino da Silva ;

Bourne, Philip E. ;

Bouwman, Jildau ;

Brookes, Anthony J. ;

Clark, Tim ;

Crosas, Merce ;

Dillo, Ingrid ;

Dumon, Olivier ;

Edmunds, Scott ;

Evelo, Chris T. ;

Finkers, Richard ;

Gonzalez-Beltran, Alejandra ;

Gray, Alasdair J. G. ;

Groth, Paul ;

Goble, Carole ;

Grethe, Jeffrey S. ;

Heringa, Jaap ;

't Hoen, Peter A. C. ;

Hooft, Rob ;

Kuhn, Tobias ;

Kok, Ruben ;

Kok, Joost ;

Lusher, Scott J. ;

Martone, Maryann E. ;

Mons, Albert ;

Packer, Abel L. ;

Persson, Bengt ;

Rocca-Serra, Philippe ;

Roos, Marco ;

van Schaik, Rene ;

Sansone, Susanna-Assunta ;

Schultes, Erik ;

Sengstag, Thierry ;

Slater, Ted ;

Strawn, George ;

Swertz, Morris A. ;

Thompson, Mark ;

van der Lei, Johan ;

van Mulligen, Erik ;

Velterop, Jan ;

Waagmeester, Andra ;

Wittenburg, Peter .

SCIENTIFIC DATA, 2016, 3

[65] On the use of artificial neural networks in topology optimisation [J].

Woldseth, Rebekka V. ;

Aage, Niels ;

Baerentzen, J. Andreas ;

Sigmund, Ole .

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2022, 65 (10)

[66] Trace formulation for photonic inverse design with incoherent sources [J].

Yao, Wenjie ;

Verdugo, Francesc ;

Christiansen, Rasmus E. ;

Johnson, Steven G. .

STRUCTURAL AND MULTIDISCIPLINARY OPTIMIZATION, 2022, 65 (11)

[67]

Zeiler MD, 2010, PROC CVPR IEEE, P2528, DOI 10.1109/CVPR.2010.5539957

[68] A compact 2-D full-wave finite-difference frequency-domain method for general guided wave structures [J].

Zhao, YJ ;

Wu, KL ;

Cheng, KKM .

IEEE TRANSACTIONS ON MICROWAVE THEORY AND TECHNIQUES, 2002, 50 (07) :1844-1848

[69] Algorithm 778: L-BFGS-B: Fortran subroutines for large-scale bound-constrained optimization [J].

Zhu, CY ;

Byrd, RH ;

Lu, PH ;

Nocedal, J .

ACM TRANSACTIONS ON MATHEMATICAL SOFTWARE, 1997, 23 (04) :550-560

← 1 2 3 4 5 6 7 →