Plasmonic colours predicted by deep learning

authored by

Joshua Baxter, Antonino Calà Lesina, Jean Michel Guay, Arnaud Weck, Pierre Berini, Lora Ramunno

Abstract

Picosecond laser pulses have been used as a surface colouring technique for noble metals, where the colours result from plasmonic resonances in the metallic nanoparticles created and redeposited on the surface by ablation and deposition processes. This technology provides two datasets which we use to train artificial neural networks, data from the experiment itself (laser parameters vs. colours) and data from the corresponding numerical simulations (geometric parameters vs. colours). We apply deep learning to predict the colour in both cases. We also propose a method for the solution of the inverse problem – wherein the geometric parameters and the laser parameters are predicted from colour – using an iterative multivariable inverse design method.

External Organisation(s)

University of Ottawa

Type

Article

Journal

Scientific reports

Volume

9

ISSN

2045-2322

Publication date

30.05.2019

Publication status

Published

Peer reviewed

Yes

ASJC Scopus subject areas

General

Electronic version(s)

https://doi.org/10.1038/s41598-019-44522-7 (Access: Open)