The DOI matches its Crossref record; 56 of the 58 references it cites were found in a registry or an index.
Neural reparameterization for nonlocal metasurface topology optimization
Open accessAbstract
Metasurfaces are emerging as a paradigm for performing all-optical, energy efficient analog computing and image processing in an ultra-compact form-factor. While various operations have been demonstrated with simple metasurface geometries, broadening the range of available processing outputs will require non-trivial and non-intuitive designs. Topology optimization (TO) is a powerful inverse design technique capable of designing such metasurfaces with significantly enhanced optical properties. The two most important design considerations are the quality of the optical performance and the minimum feature size in the resulting device. Larger features can reduce the mismatch between design and realized device performance, increasing fabrication speed and extending the scalability of the fabrication. Metasurface TO is typically performed on a pixel grid to determine the material distribution at each point. Here, we compare two pixel-based methods to neural-network based parameterizations, where the parameters of a neural-network are trained to output a metasurface design. We produce 150 different computational metasurface design tasks to compare the performance of each parameterization with regard to the performance and feature sizes. In comparison to the best pixel-based approach, a hybrid neural-network and pixel method produced designs with a median minimum feature size 2.8 times larger with only a 1.4 times increase in RMS error. Compared to a pixel method capable of producing similar critical dimensions, the optical performance of the hybrid approach is improved by 39%. Finally, as a proof of concept, we use this neural-network based parameterization to design an angular bandpass filter with relatively large critical dimensions and non-trivial performance.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946
Flat optics with designer metasurfaces
Yu, N., & Capasso, F. (2014) · Nature Materials · doi:10.1038/nmat3839 · Cited by 5,984
Interspecimen Comparison of the Refractive Index of Fused Silica*,†
Malitson, I. H. (1965) · Journal of the Optical Society of America · doi:10.1364/josa.55.001205 · Cited by 4,216
Moharam, M. G., Gaylord, T. K., Grann, E. B., & Pommet, D. A. (1995) · Journal of the Optical Society of America A · doi:10.1364/josaa.12.001068 · Cited by 2,687
Rigorous coupled-wave analysis of planar-grating diffraction
Moharam, M. G., & Gaylord, T. K. (1981) · Journal of the Optical Society of America · doi:10.1364/josa.71.000811 · Cited by 2,248
On projection methods, convergence and robust formulations in topology optimization
Wang, F., Lazarov, B. S., & Sigmund, O. (2011) · Structural and Multidisciplinary Optimization · doi:10.1007/s00158-010-0602-y · Cited by 1,859
Inverse design in nanophotonics
Molesky, S., Lin, Z., Piggott, A. Y., Jin, W., Vucković, J., & Rodriguez, A. W. (2018) · Nature Photonics · doi:10.1038/s41566-018-0246-9 · Cited by 1,818
Topology optimization for nano‐photonics
Jensen, J. S., & Sigmund, O. (2011) · Laser & Photonics Reviews · doi:10.1002/lpor.201000014 · Cited by 767
Adjoint shape optimization applied to electromagnetic design
Lalau-Keraly, C. M., Bhargava, S., Miller, O. D., & Yablonovitch, E. (2013) · Optics Express · doi:10.1364/oe.21.021693 · Cited by 753
Physics-informed neural networks for inverse problems in nano-optics and metamaterials
Chen, Y., Lu, L., Karniadakis, G. E., & Dal Negro, L. (2020) · Optics Express · doi:10.1364/oe.384875 · Cited by 701
Research works printed but not linked: 1
- 1996, Introduction to Fourier Optics
Cited by
Full-space inverse-designed meta-optics for complex vector field shaping of intracavity landscapes
Xu, M., Sang, D., Pu, M., Gao, P., Zhao, B., Zheng, Y., 曾庆济, Chen, L., Zhang, F. B., Guo, Y., et al. (2026) · Light Science & Applications · doi:10.1038/s41377-026-02258-w · Cited by 5
“Future enhancements could explore neural reparameterization to implicitly enforce manufacturing constraints and improve feature size control during optimization 77 .”
Artificial intelligence empowered metasurface design
Wang, Y., Tang, X., Liu, C., & Ma, W. (2026) · Intelligent Opto-Electronics · doi:10.67704/ioe.2026.260007 · Cited by 1
Guest Editorial: Optical computing systems
Özcan, A., Lin, X., Angelis, C. D., et al. (2026) · APL Photonics · doi:10.1063/5.0333273
From intuition to optimization: a review of inverse design applied to optical nanotweezers
Nelson, D., Kim, S., & Crozier, K. B. (2026) · Reports on Progress in Physics · doi:10.1088/1361-6633/ae7f9a · Cited by 2
“Clark et al [146] used a convolutional neural network to design an angular bandpass filter.”
Metadata
- Authors
- Clark, L., Roberts, A., & Wesemann, L.
- Affiliations
- The University of Melbourne (AU)
- Corresponding author
- Clark, Lincoln
- Venue
- APL Photonics
- Publisher
- AIP Publishing
- Published
- 2025-10-01
- Volume
- 10
- Issue
- 10
- ISSN
- 2378-0967 (ISSN-L)
- OpenAlex
- W4415104676
- Cited by
- 4
- References
- 58
- Citations by year
- 2026: 4
- FWCI
- 0.64
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- APL Photonics (publishedVersion, cc-by)
- Minerva Access (University of Melbourne) (submittedVersion, cc-by)
- Funders
- Australian Research Council (CE200100010)
- Topics
- Physical Sciences › Materials Science › Electronic, Optical and Magnetic Materials › Metamaterials and Metasurfaces Applications
- Physical Sciences › Engineering › Civil and Structural Engineering › Topology Optimization in Engineering
- Physical Sciences › Engineering › Electrical and Electronic Engineering › Advanced Antenna and Metasurface Technologies
- Keywords
- neural network parameterization, inverse design, minimum feature size, analog optical computing, all-optical image processing
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Neural reparameterization for nonlocal metasurface topology optimization. https://app.cochat.ai/papers/10.1063/5.0283122
- The paper
- Clark, L., Roberts, A., & Wesemann, L. (2025). Neural reparameterization for nonlocal metasurface topology optimization. APL Photonics. https://doi.org/10.1063/5.0283122
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.