Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Edge-emitting LED refractometer.

Optics express·2026

Same author

Polarization-independent narrow-band integrated add-drop filter for the short near-infrared wavelength range.

Optics letters·2026

Same author

Fine Mapping of MHC Region Identifies Novel Susceptibility Loci in Multiple Myeloma When Comparing With Its Precursor Monoclonal Gammopathy of Unknown Significance.

HLA·2026

Same author

Planar waveguide circulating Gaussian beam resonators on a silicon photonic chip.

Optics express·2025

Same author

Molecular and immunological determinants of long-term survival in multiple myeloma.

Blood advances·2025

Same author

Inhibition of FOXM1 Synergizes with BH3 Mimetics Venetoclax and Sonrotoclax in Killing Multiple Myeloma Cells through Repressing MYC Pathway.

Advanced science (Weinheim, Baden-Wurttemberg, Germany)·2025

Search research articles

Related Experiment Video

Updated: Jan 5, 2026

Patterning via Optical Saturable Transitions - Fabrication and Characterization

Patterning via Optical Saturable Transitions - Fabrication and Characterization

Published on: December 11, 2014

Mapping the global design space of nanophotonic components using machine learning pattern recognition.

Daniele Melati¹, Yuri Grinberg², Mohsen Kamandar Dezfouli¹

¹Advanced Electronics and Photonics Research Centre, National Research Council Canada, 1200 Montreal Rd., Ottawa, ON, K1A 0R6, Canada.

Nature Communications

|October 23, 2019

Summary

This study introduces a machine learning approach to map the complex design space of nanophotonic components. It enables faster exploration and visualization of design parameters for next-generation devices.

More Related Videos

Trapping of Micro Particles in Nanoplasmonic Optical Lattice

Trapping of Micro Particles in Nanoplasmonic Optical Lattice

Published on: September 5, 2017

Using Microwave and Macroscopic Samples of Dielectric Solids to Study the Photonic Properties of Disordered Photonic Bandgap Materials

Using Microwave and Macroscopic Samples of Dielectric Solids to Study the Photonic Properties of Disordered Photonic Bandgap Materials

Published on: September 26, 2014

Related Experiment Videos

Last Updated: Jan 5, 2026

Patterning via Optical Saturable Transitions - Fabrication and Characterization

Patterning via Optical Saturable Transitions - Fabrication and Characterization

Published on: December 11, 2014

Trapping of Micro Particles in Nanoplasmonic Optical Lattice

Trapping of Micro Particles in Nanoplasmonic Optical Lattice

Published on: September 5, 2017

Using Microwave and Macroscopic Samples of Dielectric Solids to Study the Photonic Properties of Disordered Photonic Bandgap Materials

Using Microwave and Macroscopic Samples of Dielectric Solids to Study the Photonic Properties of Disordered Photonic Bandgap Materials

Published on: September 26, 2014

Area of Science:

Nanophotonics
Computational Physics
Materials Science

Background:

Designing complex nanophotonic components requires optimizing numerous parameters simultaneously.
Current methods often focus on single objectives, yielding isolated designs and limited understanding of parameter influence.

Purpose of the Study:

To develop and demonstrate a machine learning-based approach for mapping and characterizing the multi-parameter design space of nanophotonic components.
To enable a comprehensive understanding of how design parameters influence device behavior across multiple performance criteria.

Main Methods:

Utilizing pattern recognition to identify relationships within a sparse set of optimized designs.
Reducing the dimensionality of the design space through parameter characterization.
Mapping the lower-dimensional design subspace significantly faster than the original space.

Main Results:

A significant reduction in the number of characterizing parameters for nanophotonic components.
Identification of a lower-dimensional design subspace that can be mapped orders of magnitude faster.
Visualization of device behavior across multiple performance criteria, revealing parameter interplay.

Conclusions:

The proposed machine learning approach offers a global perspective on high-dimensional nanophotonic design problems.
This method provides a powerful tool for exploring complexity and inspiring new designs in next-generation nanophotonic devices.
It facilitates a deeper understanding of performance and structural limitations inherent in nanophotonic component design.