Using Machine Learning to Selectively Optimize Photonic Nanostructures

Facebook X LinkedIn Email
BERLIN, Germany, Oct. 1, 2018 — Using machine learning and computer simulations, the Nano-SIPPE team at Helmholtz-Zentrum Berlin (HZB) has identified the most important patterns of field distribution in a photonic nanostructure. The numerical method used by the researchers combines finite element simulations (FEM) and post-processing using clustering to identify photonic modes with large local field energies and specific spatial properties. The method they present could enable the systematic optimization of nanophotonic structures for biosensing, bioimaging, and photon upconversion applications.

Machine learning used to improve photonic nanostructures, Helmholtz Zentrum Berlin.
The computer simulation shows how the electromagnetic field is distributed in the silicon layer with hole pattern after excitation with a laser. Here, stripes with local field maxima are formed, so that quantum dots shine particularly strongly. Courtesy of Carlo Barth/HZB.

To systematically record what happened when individual parameters of the nanostructure changed, the researchers calculated the 3D electric field distribution for each parameter set using software developed at the Zuse Institute Berlin. They analyzed this enormous amount of data using other computer programs, based on machine learning.

“The computer has searched through the approximately 45,000 data records and grouped them into about 10 different patterns,” said researcher Carlo Barth. He worked with professor Christiane Becker to identify three basic patterns among these 10, in which the fields were amplified in various specific areas of the nanoholes.

This approach could allow photonic crystal membranes to be optimized for virtually any application, based on excitation amplification. For example, some biomolecules would accumulate preferentially along the hole edges, while others would accumulate along the plateaus between the holes, depending on the application.

Nanostructures can increase the sensitivity of optical sensors if their geometry meets certain conditions and matches the wavelength of the incident light. With the correct geometry and the right excitation by light, the maximum electric field amplification can be generated exactly at the attachment sites of the desired molecules, said the researchers. This could increase the sensitivity of optical sensors for cancer markers to the level of individual molecules, for example.

The research was published in Communication Physics (

Published: October 2018
An SI prefix meaning one billionth (10-9). Nano can also be used to indicate the study of atoms, molecules and other structures and particles on the nanometer scale. Nano-optics (also referred to as nanophotonics), for example, is the study of how light and light-matter interactions behave on the nanometer scale. See nanophotonics.
machine learning
Machine learning (ML) is a subset of artificial intelligence (AI) that focuses on the development of algorithms and statistical models that enable computers to improve their performance on a specific task through experience or training. Instead of being explicitly programmed to perform a task, a machine learning system learns from data and examples. The primary goal of machine learning is to develop models that can generalize patterns from data and make predictions or decisions without being...
quantum dots
A quantum dot is a nanoscale semiconductor structure, typically composed of materials like cadmium selenide or indium arsenide, that exhibits unique quantum mechanical properties. These properties arise from the confinement of electrons within the dot, leading to discrete energy levels, or "quantization" of energy, similar to the behavior of individual atoms or molecules. Quantum dots have a size on the order of a few nanometers and can emit or absorb photons (light) with precise wavelengths,...
photonic crystals
Photonic crystals are artificial structures or materials designed to manipulate and control the flow of light in a manner analogous to how semiconductors control the flow of electrons. Photonic crystals are often engineered to have periodic variations in their refractive index, leading to bandgaps that prevent certain wavelengths of light from propagating through the material. These bandgaps are similar in principle to electronic bandgaps in semiconductors. Here are some key points about...
Research & TechnologyeducationEuropenanonanophotonicnanostructuremachine learningOpticsquantum dotsoptical sensorsphotonic crystalscomputer simulationHelmholtz Zentrum Berlin

We use cookies to improve user experience and analyze our website traffic as stated in our Privacy Policy. By using this website, you agree to the use of cookies unless you have disabled them.