Skip to content
PaperFren

Plasmonics

Can a neural network design nanostructures for a chosen color response?

Malkiel I, Mrejen M, Nagler A, et al. · Light, science & applications · 2018

Open access · cc by · source: Europe PMC

A neural network trained on simulations could read a nanostructure's shape from its light spectrum and design shapes for a target spectrum in milliseconds, matching real fabricated samples.

Save to libraryView originalAsk PaperFrenStudy view

Study at a glance

Design
Computational / modelling — Bidirectional deep neural network trained on finite-element (COMSOL) spectra of H-shaped gold nanostructures, then tested on fabricated gold-on-ITO samples measured by transmission spectroscopy.
N
Training set of more than 15,000 simulated nanostructure 'experiments', plus 1500 extra simulated geometries for the ITO substrate; the number of fabricated samples is not stated.
Population
Simulated and fabricated gold H-shaped plasmonic nanostructures
Outcome
Accuracy of predicted geometry from spectra and predicted spectra from geometry (mean squared error), agreement with SEM-measured dimensions

Structured fields used in claim comparison tables when every cited study has a complete layer.

Key findings

Training the two halves together gave a much lower error (mean squared error 0.16) than training them separately and combining them (0.37). Deeper inverse networks helped, with eight joined layers clearly better than five or seven. Retrieved dimensions of fabricated structures agreed well with electron-microscope sizes, and the network correctly returned 'no structure' for flat spectra it had never seen. It also proposed designs matching the absorption bands of dichloromethane and a phthalocyanine dimer in seconds.

Methodology

The authors simulated the transmission spectra, for two light polarizations, of thousands of gold nanostructures shaped like a variable letter H using finite-element software. They trained a two-part network: one half predicts the geometry from the spectra (the inverse problem) and feeds that geometry into a second half that predicts the spectra back. They then fabricated gold structures on ITO-coated glass, measured their spectra, and asked the network to recover the dimensions, comparing with electron-microscope measurements.

Limitations

The network only knows one family of shapes (H-like, fixed 40 nm thickness), so it cannot design arbitrary nanostructures. The paper reports agreement on fabricated samples mostly through figures, without stating how many samples were made or giving numerical error for them. The molecule-targeted designs were not fabricated or tested, so their performance is only predicted. Much of the training detail is left to a supplement not included in the text.

How this study connects

Role on claims

Each row is a claim on a concept or method page where this paper supports, challenges, or qualifies the statement. Roles are hand-checked — not a model guess.

  • SupportsPlasmonic nanogaps and field enhancementconcept

    Deep learning can invert spectrum-to-shape design within one shape family.

    A neural network trained on simulations inferred structure dimensions from spectra and proposed geometries for target spectra in seconds; joint training cut error from 0.37 to 0.16 (MSE), and retrieved sizes agreed with electron microscopy of fabricated samples.

    Evidence for the claim as stated.

Related papers in this topic

Same topic cluster — not a recommendation engine.