pith. sign in

arxiv: 2504.13062 · v3 · submitted 2025-04-17 · ⚛️ physics.optics · cond-mat.dis-nn· cond-mat.mes-hall

Seeing Beyond RGB Capabilities: Data-Driven and Physics-Guided Broadband Spectral Extrapolation of Plasmonic Nanostructures by Deep Learning

Mohammadrahim Kazemzadeh , Banghuan Zhang , Tao He , Haoran Liu , Zihe Jiang , Zhiwei Hu , Xiaohui Dong , Chaowei Sun
show 8 more authors
Wei Jiang Xiaobo He Shuyan Li Gonzalo Alvarez-Perez Ferruccio Pisanello Huatian Hu Wen Chen Hongxing Xu
This is my paper

Pith reviewed 2026-05-22 19:06 UTC · model grok-4.3

classification ⚛️ physics.optics cond-mat.dis-nncond-mat.mes-hall
keywords plasmonic nanostructuresdeep learningspectral extrapolationdark-field microscopyRGB imagingoptical resonancesnanoparticle screening
0
0 comments X

The pith

Deep learning predicts broadband plasmonic spectra from limited RGB images by learning resonance relationships.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper introduces SPARX, a deep learning method that predicts full dark-field spectra across 500-1000 nm for many plasmonic nanoparticles at once, starting only from standard RGB images captured below 700 nm. It achieves this by learning the physical connections between different orders of optical resonances in the particles. The approach replaces slow, sequential spectral measurements with fast batch predictions that take milliseconds, delivering selection accuracy for uniform resonances comparable to conventional spectroscopy. This matters because it addresses the challenge of inconsistent optical responses caused by morphological variations in nanostructures.

Core claim

SPARX can batch-predict broadband DF spectra (e.g., 500-1000 nm) of numerous nanoparticles simultaneously from an information-limited RGB image (i.e., below 700 nm) by learning the underlying physical relationships among multiple orders of optical resonances. The spectral predictions only take milliseconds, achieving a speedup of three to four orders of magnitude compared to traditional spectral acquisition, which may take from hours to days. As a proof-of-principle demonstration for screening identical resonances, the selection accuracy achieved by SPARX is comparable to that of conventional spectroscopy techniques.

What carries the argument

SPARX, a deep learning model trained to extrapolate spectra by capturing physical relationships among multiple orders of optical resonances in plasmonic nanoparticles.

If this is right

  • Rapid batch characterization becomes possible for large numbers of nanoparticles without full spectral scans.
  • Characterization time drops from hours or days to milliseconds per set of particles.
  • Screening for uniform resonances reaches accuracy levels matching traditional spectroscopy.
  • Consistent optical responses in plasmonic devices become more feasible through faster selection processes.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • The method could extend to predicting spectra in other wavelength bands or for different nanostructure classes if retrained on appropriate data.
  • Embedding such models in fabrication lines might enable visual-based quality checks during production.
  • It suggests data-driven techniques can reveal and exploit correlations between resonance modes that are hard to measure directly.

Load-bearing premise

The model accurately learns and extrapolates the physical relationships between optical resonances from its training data without major overfitting or failure on new nanoparticle shapes or materials.

What would settle it

Acquiring measured broadband spectra for a set of nanoparticles with shapes or materials absent from the training data and observing large systematic deviations from the model's predictions would show the extrapolation does not hold.

read the original abstract

Localized surface plasmons can confine light within a deep-subwavelength volume comparable to the scale of atoms and molecules, enabling ultrasensitive responses to near-field variations. On the other hand, this extreme localization also inevitably amplifies the unwanted noise from the response of local morphological imperfections, leading to complex spectral variations and reduced consistency across the plasmonic nanostructures. Seeking uniform optical responses has therefore long been a sought-after goal in nanoplasmonics. However, conventional probing techniques by dark-field (DF) confocal microscopy, such as image analysis or spectral measurements, can be inaccurate and time-consuming, respectively. Here, we introduce SPARX, a deep-learning-powered paradigm that surpasses conventional imaging and spectroscopic capabilities. In particular, SPARX can batch-predict broadband DF spectra (e.g., 500-1000 nm) of numerous nanoparticles simultaneously from an information-limited RGB image (i.e., below 700 nm). It achieves this extrapolative inference beyond the camera's capture capabilities by learning the underlying physical relationships among multiple orders of optical resonances. The spectral predictions only take milliseconds, achieving a speedup of three to four orders of magnitude compared to traditional spectral acquisition, which may take from hours to days. As a proof-of-principle demonstration for screening identical resonances, the selection accuracy achieved by SPARX is comparable to that of conventional spectroscopy techniques. This breakthrough paves the way for consistent plasmonic applications and next-generation microscopies.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

3 major / 2 minor

Summary. The paper introduces SPARX, a deep-learning framework that predicts broadband dark-field spectra (500-1000 nm) of plasmonic nanoparticles from RGB images limited to wavelengths below 700 nm. It claims to achieve this by learning underlying physical relationships among multiple orders of optical resonances, enabling batch predictions in milliseconds with selection accuracy comparable to conventional spectroscopy for screening identical resonances.

Significance. If the extrapolation claim holds with proper validation, SPARX could substantially accelerate high-throughput screening and characterization of plasmonic nanostructures, addressing long-standing issues of morphological noise and spectral inconsistency in nanoplasmonics while providing orders-of-magnitude speedup over traditional spectral acquisition.

major comments (3)
  1. [Abstract] The central extrapolation claim (broadband spectra from RGB-limited input) requires explicit demonstration that the model has learned transferable physical relationships rather than dataset-specific correlations. The abstract and title reference 'physics-guided' training, yet no details are provided on implementation (e.g., physics-informed loss terms, symmetry constraints, or resonance-order relationships enforced during training). This is load-bearing for the headline result.
  2. [Methods] No information is given on the training dataset composition, including number of samples, range of nanoparticle morphologies, sizes, materials, or dispersion relations. Without this, it is impossible to assess whether performance on in-distribution validation supports generalization to unseen structures, which is required for the claimed extrapolation beyond 700 nm.
  3. [Results] The proof-of-principle demonstration of 'selection accuracy comparable to conventional spectroscopy' lacks reported quantitative metrics, error bars, confusion matrices, or statistical tests. This undermines the claim that SPARX achieves reliable screening performance.
minor comments (2)
  1. Clarify the exact wavelength ranges used for input RGB images versus output spectra, and specify the camera's spectral response function if relevant to the information-limited input.
  2. [Abstract] The abstract states a speedup of 'three to four orders of magnitude' but does not compare against specific conventional acquisition times or hardware setups used in the experiments.

Simulated Author's Rebuttal

3 responses · 0 unresolved

We are grateful to the referee for their insightful comments, which have helped us identify areas for improvement in the manuscript. Below, we provide point-by-point responses to the major comments.

read point-by-point responses

  1. Referee: [Abstract] The central extrapolation claim (broadband spectra from RGB-limited input) requires explicit demonstration that the model has learned transferable physical relationships rather than dataset-specific correlations. The abstract and title reference 'physics-guided' training, yet no details are provided on implementation (e.g., physics-informed loss terms, symmetry constraints, or resonance-order relationships enforced during training). This is load-bearing for the headline result.

    Authors: We thank the referee for this important observation. The manuscript title and abstract refer to 'physics-guided' training to indicate that the model architecture and training process are designed to capture physical relationships between resonance orders. However, we agree that explicit details on the implementation are needed to substantiate the extrapolation claim. In the revised manuscript, we will add a section in the Methods describing the physics-guided components, such as the use of multi-order resonance consistency in the loss function and any symmetry or dispersion constraints applied during training. revision: yes

  2. Referee: [Methods] No information is given on the training dataset composition, including number of samples, range of nanoparticle morphologies, sizes, materials, or dispersion relations. Without this, it is impossible to assess whether performance on in-distribution validation supports generalization to unseen structures, which is required for the claimed extrapolation beyond 700 nm.

    Authors: We agree with the referee that details on the training dataset are necessary to evaluate generalization. In the revised manuscript, we will include a detailed description of the dataset composition in the Methods section, specifying the number of samples, the range of nanoparticle morphologies, sizes, materials, and dispersion relations. This will help demonstrate support for the claimed extrapolation capabilities. revision: yes

  3. Referee: [Results] The proof-of-principle demonstration of 'selection accuracy comparable to conventional spectroscopy' lacks reported quantitative metrics, error bars, confusion matrices, or statistical tests. This undermines the claim that SPARX achieves reliable screening performance.

    Authors: We acknowledge that additional quantitative metrics would strengthen the results. In the revision, we will report quantitative metrics for the spectral predictions and selection accuracy, including error bars, confusion matrices, and statistical analyses to support the claim of comparability to conventional spectroscopy. revision: yes

Circularity Check

0 steps flagged

No significant circularity: empirical ML extrapolation from data

full rationale

The paper introduces SPARX as a trained deep-learning model that maps RGB-limited inputs to broadband spectra by learning relationships from training data. No derivation chain, first-principles equations, or uniqueness theorems are presented that reduce predictions to inputs by construction. Claims rest on empirical performance and generalization of the network rather than self-referential fitting or self-citation load-bearing steps. The approach is self-contained as a data-driven predictor without the enumerated circular patterns.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

The central claim rests on the assumption that deep learning can reliably learn and extrapolate physical resonance relationships from limited spectral training data; no explicit free parameters, axioms, or invented entities are detailed in the abstract.

pith-pipeline@v0.9.0 · 5868 in / 1107 out tokens · 30806 ms · 2026-05-22T19:06:56.649755+00:00 · methodology

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Lean theorems connected to this paper

Citations machine-checked in the Pith Canon. Every link opens the source theorem in the public Lean library.

What do these tags mean?
matches
The paper's claim is directly supported by a theorem in the formal canon.
supports
The theorem supports part of the paper's argument, but the paper may add assumptions or extra steps.
extends
The paper goes beyond the formal theorem; the theorem is a base layer rather than the whole result.
uses
The paper appears to rely on the theorem as machinery.
contradicts
The paper's claim conflicts with a theorem or certificate in the canon.
unclear
Pith found a possible connection, but the passage is too broad, indirect, or ambiguous to say the theorem truly supports the claim.

Reference graph

Works this paper leans on

67 extracted references · 67 canonical work pages

  1. [1]

    Physical Review Letters 83(21), 4357–4360 (1999)

    Xu, H., Bjerneld, E.J., K¨ all, M., B¨ orjesson, L.: Spectroscopy of Single Hemoglobin Molecules by Surface Enhanced Raman Scattering. Physical Review Letters 83(21), 4357–4360 (1999)

    work page 1999

  2. [2]

    Chemical reviews111(6), 3913–3961 (2011) 21

    Halas, N.J., Lal, S., Chang, W.-S., Link, S., Nordlander, P.: Plasmons in strongly coupled metallic nanostructures. Chemical reviews111(6), 3913–3961 (2011) 21

    work page 2011

  3. [3]

    Nature Materials18(7), 668–678 (2019)

    Baumberg, J.J., Aizpurua, J., Mikkelsen, M.H., Smith, D.R.: Extreme nanopho- tonics from ultrathin metallic gaps. Nature Materials18(7), 668–678 (2019)

    work page 2019

  4. [4]

    picocavities

    Benz, F., Schmidt, M.K., Dreismann, A., Chikkaraddy, R., Zhang, Y., Demetri- adou, A., Carnegie, C., Ohadi, H., Nijs, B., Esteban, R., Aizpurua, J., Baumberg, J.J.: Single-molecule optomechanics in “picocavities”. Science354(6313), 726–729 (2016). Chap. Report

    work page 2016

  5. [5]

    Science337(6098), 1072–1074 (2012)

    Cirac` ı, C., Hill, R., Mock, J., Urzhumov, Y., Fern´ andez-Dom´ ınguez, A., Maier, S., Pendry, J., Chilkoti, A., Smith, D.: Probing the ultimate limits of plasmonic enhancement. Science337(6098), 1072–1074 (2012)

    work page 2012

  6. [6]

    Nature Photonics8(11), 835–840 (2014)

    Akselrod, G.M., Argyropoulos, C., Hoang, T.B., Cirac` ı, C., Fang, C., Huang, J., Smith, D.R., Mikkelsen, M.H.: Probing the mechanisms of large Purcell enhancement in plasmonic nanoantennas. Nature Photonics8(11), 835–840 (2014)

    work page 2014

  7. [7]

    ACS Nano14(1), 28–117 (2020)

    Langer, J., Jimenez De Aberasturi, D., Aizpurua, J., Alvarez-Puebla, R.A., Augui´ e, B., Baumberg, J.J., Bazan, G.C., Bell, S.E.J., Boisen, A., Brolo, A.G., Choo, J., Cialla-May, D., Deckert, V., Fabris, L., Faulds, K., Garc´ ıa De Abajo, F.J., Goodacre, R., Graham, D., Haes, A.J., Haynes, C.L., Huck, C., Itoh, T., K¨ all, M., Kneipp, J., Kotov, N.A., Kua...

    work page 2020

  8. [8]

    Nature Communications12(1), 2731 (2021)

    Chen, W., Roelli, P., Ahmed, A., Verlekar, S., Hu, H., Banjac, K., Lingenfelder, M., Kippenberg, T.J., Tagliabue, G., Galland, C.: Intrinsic luminescence blinking from plasmonic nanojunctions. Nature Communications12(1), 2731 (2021)

    work page 2021

  9. [9]

    Science374(6572), 1264–1267 (2021)

    Chen, W., Roelli, P., Hu, H., Verlekar, S., Amirtharaj, S.P., Barreda, A.I., Kip- penberg, T.J., Kovylina, M., Verhagen, E., Mart´ ınez, A., Galland, C.: Continuous- wave frequency upconversion with a molecular optomechanical nanocavity. Science374(6572), 1264–1267 (2021)

    work page 2021

  10. [10]

    Nano Letters (2025)

    Giovannini, T., Nicoli, L., Corni, S., Cappelli, C.: The electric field morphology of plasmonic picocavities. Nano Letters (2025)

    work page 2025

  11. [11]

    Advanced Materials36(49), 2405186 (2024)

    Li, Y., Chen, W., He, X., Shi, J., Cui, X., Sun, J., Xu, H.: Boosting Light-Matter Interactions in Plasmonic Nanogaps. Advanced Materials36(49), 2405186 (2024)

    work page 2024

  12. [12]

    Physical Review Letters126(25), 257401 (2021) 22

    Li, W., Zhou, Q., Zhang, P., Chen, X.-W.: Bright optical eigenmode of 1 nm 3 mode volume. Physical Review Letters126(25), 257401 (2021) 22

    work page 2021

  13. [13]

    Advanced Optical Materials 11(3), 2201914 (2023)

    Wang, Z., Liu, L., Zhang, D., Krasavin, A.V., Zheng, J., Pan, C., He, E., Wang, Z., Zhong, S., Li, Z.,et al.: Effect of mirror quality on optical response of nanoparticle-on-mirror plasmonic nanocavities. Advanced Optical Materials 11(3), 2201914 (2023)

    work page 2023

  14. [14]

    Acs Photonics7(4), 908–913 (2020)

    Cirac` ı, C., Vidal-Codina, F., Yoo, D., Peraire, J., Oh, S.-H., Smith, D.R.: Impact of surface roughness in nanogap plasmonic systems. Acs Photonics7(4), 908–913 (2020)

    work page 2020

  15. [15]

    ACS nano14(8), 10562–10568 (2020)

    Xomalis, A., Chikkaraddy, R., Oksenberg, E., Shlesinger, I., Huang, J., Gar- nett, E.C., Koenderink, A.F., Baumberg, J.J.: Controlling optically driven atomic migration using crystal-facet control in plasmonic nanocavities. ACS nano14(8), 10562–10568 (2020)

    work page 2020

  16. [16]

    Laser & Photonics Reviews16(5), 2100564 (2022)

    Sun, J., Hu, H., Xu, Y., Li, Y., Xu, H.: Revealing the photothermal behavior of plasmonic gap modes: toward thermostable nanocavities. Laser & Photonics Reviews16(5), 2100564 (2022)

    work page 2022

  17. [17]

    ACS photonics8(10), 2868–2875 (2021)

    Griffiths, J., De Nijs, B., Chikkaraddy, R., Baumberg, J.J.: Locating single- atom optical picocavities using wavelength-multiplexed raman scattering. ACS photonics8(10), 2868–2875 (2021)

    work page 2021

  18. [18]

    Nanophotonics12(20), 3931–3944 (2023)

    Bedingfield, K., Elliott, E., Gisdakis, A., Kongsuwan, N., Baumberg, J.J., Demetriadou, A.: Multi-faceted plasmonic nanocavities. Nanophotonics12(20), 3931–3944 (2023)

    work page 2023

  19. [19]

    Physical Review A92(5), 053811 (2015)

    Tserkezis, C., Esteban, R., Sigle, D.O., Mertens, J., Herrmann, L.O., Baum- berg, J.J., Aizpurua, J.: Hybridization of plasmonic antenna and cavity modes: Extreme optics of nanoparticle-on-mirror nanogaps. Physical Review A92(5), 053811 (2015)

    work page 2015

  20. [20]

    Advanced Science10(11), 2207178 (2023)

    Hu, S., Elliott, E., S´ anchez-Iglesias, A., Huang, J., Guo, C., Hou, Y., Kamp, M., Goerlitzer, E.S., Bedingfield, K., De Nijs, B.,et al.: Full control of plasmonic nanocavities using gold decahedra-on-mirror constructs with monodisperse facets. Advanced Science10(11), 2207178 (2023)

    work page 2023

  21. [21]

    Applied Physics Letters96(3) (2010)

    Pisanello, F., Martiradonna, L., Lem´ enager, G., Spinicelli, P., Fiore, A., Manna, L., Hermier, J.-P., Cingolani, R., Giacobino, E., De Vittorio, M., et al.: Room temperature-dipolelike single photon source with a colloidal dot-in-rod. Applied Physics Letters96(3) (2010)

    work page 2010

  22. [22]

    ACS Photonics7(2), 463–471 (2020)

    Kongsuwan, N., Demetriadou, A., Horton, M., Chikkaraddy, R., Baumberg, J.J., Hess, O.: Plasmonic nanocavity modes: From near-field to far-field radiation. ACS Photonics7(2), 463–471 (2020)

    work page 2020

  23. [23]

    The Journal of Physical Chemistry C 23 120(13), 7295–7298 (2016) https://doi.org/10.1021/acs.jpcc.6b02401

    El-Khoury, P.Z., Joly, A.G., Hess, W.P.: Hyperspectral Dark Field Optical Microscopy of Single Silver Nanospheres. The Journal of Physical Chemistry C 23 120(13), 7295–7298 (2016) https://doi.org/10.1021/acs.jpcc.6b02401

    work page doi:10.1021/acs.jpcc.6b02401 2016

  24. [24]

    Materials11(2), 243 (2018) https://doi.org/10.3390/ ma11020243

    Zamora-Perez, P., Tsoutsi, D., Xu, R., Rivera Gil, P.: Hyperspectral-Enhanced Dark Field Microscopy for Single and Collective Nanoparticle Characterization in Biological Environments. Materials11(2), 243 (2018) https://doi.org/10.3390/ ma11020243

    work page 2018

  25. [25]

    Biomedical Optics Express11(6), 3195 (2020) https://doi.org/10.1364/ BOE.386338

    Ortega, S., Halicek, M., Fabelo, H., Callico, G.M., Fei, B.: Hyperspectral and mul- tispectral imaging in digital and computational pathology: A systematic review [Invited]. Biomedical Optics Express11(6), 3195 (2020) https://doi.org/10.1364/ BOE.386338

    work page 2020

  26. [26]

    Science of The Total Environment772, 145478 (2021) https://doi.org/ 10.1016/j.scitotenv.2021.145478

    Fakhrullin, R., Nigamatzyanova, L., Fakhrullina, G.: Dark-field/hyperspectral microscopy for detecting nanoscale particles in environmental nanotoxicology research. Science of The Total Environment772, 145478 (2021) https://doi.org/ 10.1016/j.scitotenv.2021.145478

    work page doi:10.1016/j.scitotenv.2021.145478 2021

  27. [27]

    WIREs Nanomedicine and Nanobiotechnology13(1), 1661 (2021) https://doi.org/10

    Mehta, N., Sahu, S.P., Shaik, S., Devireddy, R., Gartia, M.R.: Dark-field hyperspectral imaging for label free detection of nano-bio-materials. WIREs Nanomedicine and Nanobiotechnology13(1), 1661 (2021) https://doi.org/10. 1002/wnan.1661

    work page 2021

  28. [28]

    Nature635(8037), 73–81 (2024) https:// doi.org/10.1038/s41586-024-08109-1

    Bian, L., Wang, Z., Zhang, Y., Li, L., Zhang, Y., Yang, C., Fang, W., Zhao, J., Zhu, C., Meng, Q., Peng, X., Zhang, J.: A broadband hyperspectral image sensor with high spatio-temporal resolution. Nature635(8037), 73–81 (2024) https:// doi.org/10.1038/s41586-024-08109-1

    work page doi:10.1038/s41586-024-08109-1 2024

  29. [29]

    Nature Photonics11(7), 411–414 (2017) https://doi.org/10.1038/nphoton.2017.82

    Pian, Q., Yao, R., Sinsuebphon, N., Intes, X.: Compressive hyperspectral time- resolved wide-field fluorescence lifetime imaging. Nature Photonics11(7), 411–414 (2017) https://doi.org/10.1038/nphoton.2017.82

    work page doi:10.1038/nphoton.2017.82 2017

  30. [30]

    The Journal of Physical Chemistry C126(5), 2614–2626 (2022) https://doi.org/10.1021/acs.jpcc.1c08359

    Xu, Y., Lu, L., Giljum, A., Payne, C.M., Hafner, J.H., Ringe, E., Kelly, K.F.: Compressive Hyperspectral Microscopy of Scattering and Fluorescence of Nanoparticles. The Journal of Physical Chemistry C126(5), 2614–2626 (2022) https://doi.org/10.1021/acs.jpcc.1c08359

    work page doi:10.1021/acs.jpcc.1c08359 2022

  31. [31]

    Optics and Lasers in Engineering165, 107541 (2023) https://doi.org/10.1016/j.optlaseng

    He, Y., Yao, Y., He, Y., Huang, Z., Ding, P., Qi, D., Wang, Z., Jia, T., Sun, Z., Zhang, S.: High-speed compressive wide-field fluorescence microscopy with an alternant deep denoisers-based image reconstruction algorithm. Optics and Lasers in Engineering165, 107541 (2023) https://doi.org/10.1016/j.optlaseng. 2023.107541

    work page doi:10.1016/j.optlaseng 2023

  32. [32]

    Nature Communications15(1), 1456 (2024) https://doi.org/10.1038/s41467-024-45856-1 24

    Xu, Y., Lu, L., Saragadam, V., Kelly, K.F.: A compressive hyperspectral video imaging system using a single-pixel detector. Nature Communications15(1), 1456 (2024) https://doi.org/10.1038/s41467-024-45856-1 24

    work page doi:10.1038/s41467-024-45856-1 2024

  33. [33]

    Nanotheranostics1(4), 369–388 (2017) https://doi.org/10.7150/ ntno.21136

    Wang, Y.W., Reder, N.P., Kang, S., Glaser, A.K., Liu, J.T.C.: Multiplexed Opti- cal Imaging of Tumor-Directed Nanoparticles: A Review of Imaging Systems and Approaches. Nanotheranostics1(4), 369–388 (2017) https://doi.org/10.7150/ ntno.21136

    work page 2017

  34. [34]

    The Journal of Physical Chemistry C123(35), 21571–21580 (2019)

    Ahn, J., Shi, S., Vannatter, B., Qin, D.: Comparative Study of the Adsorption of Thiol and Isocyanide Molecules on a Silver Surface by in Situ Surface-Enhanced Raman Scattering. The Journal of Physical Chemistry C123(35), 21571–21580 (2019)

    work page 2019

  35. [35]

    eLight5(1), 5 (2025)

    Wu, N., Sun, Y., Hu, J., Yang, C., Bai, Z., Wang, F., Cui, X., He, S., Li, Y., Zhang, C.,et al.: Intelligent nanophotonics: when machine learning sheds light. eLight5(1), 5 (2025)

    work page 2025

  36. [36]

    Science Advances11(33), 2299 (2025)

    Monta˜ no-Priede, J.L., Rao, A., S´ anchez-Iglesias, A., Grzelczak, M.: Acceler- ated design of gold nanoparticles with enhanced plasmonic performance. Science Advances11(33), 2299 (2025)

    work page 2025

  37. [37]

    Optica10(10), 1373–1382 (2023)

    Kanmaz, T.B., Ozturk, E., Demir, H.V., Gunduz-Demir, C.: Deep-learning- enabled electromagnetic near-field prediction and inverse design of metasurfaces. Optica10(10), 1373–1382 (2023)

    work page 2023

  38. [38]

    Light: Science & Applications7(1), 60 (2018)

    Malkiel, I., Mrejen, M., Nagler, A., Arieli, U., Wolf, L., Suchowski, H.: Plasmonic nanostructure design and characterization via deep learning. Light: Science & Applications7(1), 60 (2018)

    work page 2018

  39. [39]

    Nano letters18(10), 6570–6576 (2018)

    Liu, Z., Zhu, D., Rodrigues, S.P., Lee, K.-T., Cai, W.: Generative model for the inverse design of metasurfaces. Nano letters18(10), 6570–6576 (2018)

    work page 2018

  40. [40]

    Acs Photonics6(12), 3196–3207 (2019)

    An, S., Fowler, C., Zheng, B., Shalaginov, M.Y., Tang, H., Li, H., Zhou, L., Ding, J., Agarwal, A.M., Rivero-Baleine, C.,et al.: A deep learning approach for objective-driven all-dielectric metasurface design. Acs Photonics6(12), 3196–3207 (2019)

    work page 2019

  41. [41]

    Advanced Science6(12), 1900128 (2019)

    Qiu, T., Shi, X., Wang, J., Li, Y., Qu, S., Cheng, Q., Cui, T., Sui, S.: Deep learning: a rapid and efficient route to automatic metasurface design. Advanced Science6(12), 1900128 (2019)

    work page 2019

  42. [42]

    Advanced Optical Materials10(3), 2102113 (2022)

    An, S., Zheng, B., Shalaginov, M.Y., Tang, H., Li, H., Zhou, L., Dong, Y., Haerinia, M., Agarwal, A.M., Rivero-Baleine, C.,et al.: Deep convolutional neu- ral networks to predict mutual coupling effects in metasurfaces. Advanced Optical Materials10(3), 2102113 (2022)

    work page 2022

  43. [43]

    Applied Physics Letters126(10) (2025) 25

    Kazemzadeh, M., Mastrototaro, G., De Vittorio, M., Pisanello, F.: Deep learning- enabled gradient-based optimization of near-field enhancement in nano-plasmonic structures. Applied Physics Letters126(10) (2025) 25

    work page 2025

  44. [44]

    Nature nanotechnology19(12), 1758–1762 (2024)

    Yi, J., You, E.-M., Liu, G.-K., Tian, Z.-Q.: Ai–nano-driven surface-enhanced raman spectroscopy for marketable technologies. Nature nanotechnology19(12), 1758–1762 (2024)

    work page 2024

  45. [45]

    The Journal of Physical Chemistry C (2025)

    Shiratori, K., West, C.A., Jia, Z., Lee, S.A., Cook, E.A., Murphy, C.J., Landes, C.F., Link, S.: Machine learning to adaptively predict gold nanorod sizes on different substrates. The Journal of Physical Chemistry C (2025)

    work page 2025

  46. [46]

    ACS central science6(12), 2339–2346 (2020)

    Hu, J., Liu, T., Choo, P., Wang, S., Reese, T., Sample, A.D., Odom, T.W.: Single- nanoparticle orientation sensing by deep learning. ACS central science6(12), 2339–2346 (2020)

    work page 2020

  47. [47]

    Nature Communications15(1), 754 (2024)

    He, H., Cao, M., Gao, Y., Zheng, P., Yan, S., Zhong, J.-H., Wang, L., Jin, D., Ren, B.: Noise learning of instruments for high-contrast, high-resolution and fast hyperspectral microscopy and nanoscopy. Nature Communications15(1), 754 (2024)

    work page 2024

  48. [48]

    ACS nano17(21), 21251–21261 (2023)

    Ju, Y., Neumann, O., Bajomo, M., Zhao, Y., Nordlander, P., Halas, N.J., Patel, A.: Identifying surface-enhanced raman spectra with a raman library using machine learning. ACS nano17(21), 21251–21261 (2023)

    work page 2023

  49. [49]

    Biomedical Optics Express15(7), 4220–4236 (2024)

    Kazemzadeh, M., Martinez-Calderon, M., Otupiri, R., Artuyants, A., Lowe, M., Ning, X., Reategui, E., Schultz, Z.D., Xu, W., Blenkiron, C.,et al.: Deep autoen- coder as an interpretable tool for raman spectroscopy investigation of chemical and extracellular vesicle mixtures. Biomedical Optics Express15(7), 4220–4236 (2024)

    work page 2024

  50. [50]

    Analytical Chemistry94(37), 12907–12918 (2022)

    Kazemzadeh, M., Martinez-Calderon, M., Xu, W., Chamley, L.W., Hisey, C.L., Broderick, N.G.: Cascaded deep convolutional neural networks as improved meth- ods of preprocessing raman spectroscopy data. Analytical Chemistry94(37), 12907–12918 (2022)

    work page 2022

  51. [51]

    Analytical Chemistry 94(11), 4610–4616 (2022)

    Song, M.K., Ma, Y.P., Liu, H., Hu, P.P., Huang, C.Z., Zhou, J.: High resolution of plasmonic resonance scattering imaging with deep learning. Analytical Chemistry 94(11), 4610–4616 (2022)

    work page 2022

  52. [52]

    Nanoscale16(9), 4703–4709 (2024)

    Lei, M., Zhao, J., Zhou, J., Lee, H., Wu, Q., Burns, Z., Chen, G., Liu, Z.: Super resolution label-free dark-field microscopy by deep learning. Nanoscale16(9), 4703–4709 (2024)

    work page 2024

  53. [53]

    Nano Letters24(49), 15724–15730 (2024)

    Lei, M., Zhao, J., Sahan, A.Z., Hu, J., Zhou, J., Lee, H., Wu, Q., Zhang, J., Liu, Z.: Deep learning assisted plasmonic dark-field microscopy for super-resolution label-free imaging. Nano Letters24(49), 15724–15730 (2024)

    work page 2024

  54. [54]

    Nature communications9(1), 801 (2018) 26

    Chen, W., Zhang, S., Deng, Q., Xu, H.: Probing of sub-picometer vertical dif- ferential resolutions using cavity plasmons. Nature communications9(1), 801 (2018) 26

    work page 2018

  55. [55]

    John Wiley & Sons, ??? (2008)

    Bohren, C.F., Huffman, D.R.: Absorption and Scattering of Light by Small Particles. John Wiley & Sons, ??? (2008)

    work page 2008

  56. [56]

    science302(5644), 419–422 (2003)

    Prodan, E., Radloff, C., Halas, N.J., Nordlander, P.: A hybridization model for the plasmon response of complex nanostructures. science302(5644), 419–422 (2003)

    work page 2003

  57. [57]

    Nano Letters13(12), 5866–5872 (2013) https://doi.org/10.1021/ nl402660s

    Lassiter, J.B., McGuire, F., Mock, J.J., Cirac` ı, C., Hill, R.T., Wiley, B.J., Chilkoti, A., Smith, D.R.: Plasmonic Waveguide Modes of Film-Coupled Metal- lic Nanocubes. Nano Letters13(12), 5866–5872 (2013) https://doi.org/10.1021/ nl402660s . Accessed 2020-11-07

    work page 2013

  58. [58]

    ACS Nano 10(12), 11266–11279 (2016) https://doi.org/10.1021/acsnano.6b06406

    Pellarin, M., Ramade, J., Rye, J.M., Bonnet, C., Broyer, M., Lebeault, M.- A., Lerm´ e, J., Marguet, S., Navarro, J.R.G., Cottancin, E.: Fano Transparency in Rounded Nanocube Dimers Induced by Gap Plasmon Coupling. ACS Nano 10(12), 11266–11279 (2016) https://doi.org/10.1021/acsnano.6b06406 . Accessed 2022-04-07

    work page doi:10.1021/acsnano.6b06406 2016

  59. [59]

    Acs Photonics4(3), 469–475 (2017)

    Chikkaraddy, R., Zheng, X., Benz, F., Brooks, L.J., De Nijs, B., Carnegie, C., Kleemann, M.-E., Mertens, J., Bowman, R.W., Vandenbosch, G.A.,et al.: How ultranarrow gap symmetries control plasmonic nanocavity modes: from cubes to spheres in the nanoparticle-on-mirror. Acs Photonics4(3), 469–475 (2017)

    work page 2017

  60. [60]

    Chemical reviews117(23), 13890–13908 (2017)

    Heintzmann, R., Huser, T.: Super-resolution structured illumination microscopy. Chemical reviews117(23), 13890–13908 (2017)

    work page 2017

  61. [61]

    Chemical reviews117(11), 7538–7582 (2017)

    Willets, K.A., Wilson, A.J., Sundaresan, V., Joshi, P.B.: Super-resolution imaging and plasmonics. Chemical reviews117(11), 7538–7582 (2017)

    work page 2017

  62. [62]

    Nature communications13(1), 6631 (2022)

    Lee, Y.U., Li, S., Wisna, G.B.M., Zhao, J., Zeng, Y., Tao, A.R., Liu, Z.: Hyperbolic material enhanced scattering nanoscopy for label-free super-resolution imaging. Nature communications13(1), 6631 (2022)

    work page 2022

  63. [63]

    Scientific reports12(1), 11905 (2022)

    Zhang, J., Su, R., Fu, Q., Ren, W., Heide, F., Nie, Y.: A survey on computational spectral reconstruction methods from rgb to hyperspectral imaging. Scientific reports12(1), 11905 (2022)

    work page 2022

  64. [64]

    The Journal of Physical Chemistry C111(10), 3806–3819 (2007)

    Noguez, C.: Surface plasmons on metal nanoparticles: the influence of shape and physical environment. The Journal of Physical Chemistry C111(10), 3806–3819 (2007)

    work page 2007

  65. [65]

    Nanoscale12(20), 11297–11305 (2020)

    Gschneidtner, T.A., Lerch, S., Ols´ en, E., Wen, X., Liu, A.C., Stola´ s, A., Etheridge, J., Olsson, E., Moth-Poulsen, K.: Constructing a library of metal and metal– oxide nanoparticle heterodimers through colloidal assembly. Nanoscale12(20), 11297–11305 (2020)

    work page 2020

  66. [66]

    Physical Review 27 B—Condensed Matter and Materials Physics86(23), 235147 (2012)

    Olmon, R.L., Slovick, B., Johnson, T.W., Shelton, D., Oh, S.-H., Boreman, G.D., Raschke, M.B.: Optical dielectric function of gold. Physical Review 27 B—Condensed Matter and Materials Physics86(23), 235147 (2012)

    work page 2012

  67. [67]

    Science325(5940), 594–597 (2009) 28

    Nagpal, P., Lindquist, N.C., Oh, S.-H., Norris, D.J.: Ultrasmooth Patterned Metals for Plasmonics and Metamaterials. Science325(5940), 594–597 (2009) 28

    work page 2009