Details
| Original language | English |
|---|---|
| Article number | 8074 |
| Journal | Scientific reports |
| Volume | 9 |
| Issue number | 1 |
| Publication status | Published - 30 May 2019 |
| Externally published | Yes |
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.
ASJC Scopus subject areas
Cite this
- Standard
- Harvard
- Apa
- Vancouver
- BibTeX
- RIS
In: Scientific reports, Vol. 9, No. 1, 8074, 30.05.2019.
Research output: Contribution to journal › Article › Research › peer review
}
TY - JOUR
T1 - Plasmonic colours predicted by deep learning
AU - Baxter, Joshua
AU - Calà Lesina, Antonino
AU - Guay, Jean Michel
AU - Weck, Arnaud
AU - Berini, Pierre
AU - Ramunno, Lora
N1 - Funding information: SOSCIP is funded by the Federal Economic Development Agency of Southern Ontario, the Province of Ontario, IBM Canada Ldt., Ontario Centres of Excellence, Mitacs and Ontario academic member institutions. The authors thank SOSCIP for their computational resources and financial support. We acknowledge the computational resources and support from Scinet. We acknowledge financial support from the National Sciences and Engineering Research Council of Canada, and the Canada Research Chairs program. The authors also thank the Royal Canadian Mint for the use of their laser lab and the data acquired from it. We would like to thank Graham Killaire, Meagan Ginn, Guillaume Côté, and Martin Charron for their contributions in creating the colour palettes at the Royal Canadian Mint.
PY - 2019/5/30
Y1 - 2019/5/30
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=85066508659&partnerID=8YFLogxK
U2 - 10.1038/s41598-019-44522-7
DO - 10.1038/s41598-019-44522-7
M3 - Article
C2 - 31147587
AN - SCOPUS:85066508659
VL - 9
JO - Scientific reports
JF - Scientific reports
SN - 2045-2322
IS - 1
M1 - 8074
ER -