# Plasmonic colours predicted by deep learning

## TL;DR

This paper demonstrates how deep learning can predict and invert plasmonic colours on noble metals created by laser pulses, combining experimental and simulation data for improved surface colour control.

## Contribution

It introduces a deep learning approach to predict and invert plasmonic colours based on experimental and simulation datasets, advancing surface colour engineering techniques.

## Key findings

- Deep learning accurately predicts colours from laser and geometric parameters.
- The inverse design method effectively determines parameters from observed colours.
- The approach bridges experimental and simulation data for plasmonic colour prediction.

## 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.