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

Uniform Depth Channel Flow: Problem Solving

Uniform Depth Channel Flow: Problem Solving

To calculate the flow rate for a trapezoidal channel, first, identify the bottom width, side slope, and flow depth of the channel. The cross-sectional area (A) corresponding to the depth of flow (y), channel bottom width (B), and side slope (θ) is determined by:Next, calculate the wetted perimeter, which includes the bottom width and the sloped side lengths in contact with the water. Using the values of the cross-sectional area and the wetted perimeter, determine the hydraulic radius by...

Multicompartment Models: Overview

Multicompartment Models: Overview

Multicompartment models are mathematical constructs that depict how drugs are distributed and eliminated within the body. They segment the body into several compartments, symbolizing various physiological or anatomical areas connected through drug transfer processes such as absorption, metabolism, distribution, and elimination.
These models offer a more comprehensive representation of drug behavior in the body than one-compartment models. They accommodate the complexity of drug distribution,...

You might also read

Related Articles

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

Sort by

Same author

Ice-phase optothermal tweezers.

Nature communications·2026

Same author

Optothermal Bubble Etch Lithography.

ACS applied materials & interfaces·2026

Same author

Freeform optical flow based on meta-conveyors for compact, programmable in situ nanomanipulation.

Nature communications·2026

Same author

High-Q multimodal guided-surface lattice resonances in index-discontinuous environments.

Nature communications·2026

Same author

Mapping the landscape of OSA research: a scientometric comparison between otolaryngology and stomatology contributions.

Oral and maxillofacial surgery·2026

Same author

Sound matters: Using acoustics to move material.

Science advances·2026

Same journal

Strabismic imaging for correcting in-plane motion distortion in scanning imaging instruments and rolling shutter cameras.

Advanced photonics·2026

Same journal

Precise photoelectrochemical tuning of semiconductor microdisk lasers.

Advanced photonics·2024

Same journal

Resolution enhancement with deblurring by pixel reassignment.

Advanced photonics·2024

Same journal

Review of bio-optical imaging systems with a high space-bandwidth product.

Advanced photonics·2022

Same journal

High spatial and temporal resolution synthetic aperture phase microscopy.

Advanced photonics·2021

See all related articles

Search research articles

Related Experiment Video

Updated: Sep 10, 2025

Procedure for the Transfer of Polymer Films Onto Porous Substrates with Minimized Defects

Procedure for the Transfer of Polymer Films Onto Porous Substrates with Minimized Defects

Published on: June 22, 2019

Nested deep transfer learning for modeling of multilayer thin films.

Rohit Unni^1,2, Kan Yao^1,2, Yuebing Zheng^1,2

¹Walker Department of Mechanical Engineering, The University of Texas at Austin, Austin, Texas 78712, USA.

Advanced Photonics

|August 21, 2025

Summary

This summary is machine-generated.

Nested transfer learning significantly reduces data needs for nanophotonics by training models on increasingly complex structures. This approach accurately predicts optical properties for intricate thin film stacks with modest data requirements.

Keywords:

artificial neural networks inverse design multilayer structures nanophotonics transfer learning

More Related Videos

Layer-by-layer Synthesis and Transfer of Freestanding Conjugated Microporous Polymer Nanomembranes

Layer-by-layer Synthesis and Transfer of Freestanding Conjugated Microporous Polymer Nanomembranes

Published on: December 15, 2015

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

Related Experiment Videos

Last Updated: Sep 10, 2025

Procedure for the Transfer of Polymer Films Onto Porous Substrates with Minimized Defects

Procedure for the Transfer of Polymer Films Onto Porous Substrates with Minimized Defects

Published on: June 22, 2019

Layer-by-layer Synthesis and Transfer of Freestanding Conjugated Microporous Polymer Nanomembranes

Layer-by-layer Synthesis and Transfer of Freestanding Conjugated Microporous Polymer Nanomembranes

Published on: December 15, 2015

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Author Spotlight: Unraveling the Pathogenesis of Age-Related Macular Degeneration and Discovering Potential Therapies

Published on: July 28, 2023

Area of Science:

Nanophotonics
Computational Materials Science
Machine Learning Applications

Background:

Machine learning (ML) is increasingly used in nanophotonics for predicting optical properties and designing structures.
Acquiring training data for complex nanophotonic structures via simulations is computationally expensive and time-consuming.
Traditional transfer learning offers benefits but has limitations for more complex tasks.

Purpose of the Study:

To introduce a novel nested transfer learning approach to overcome data acquisition challenges in nanophotonics.
To enable accurate modeling of thin film stacks with higher optical complexity than previously achievable.
To reduce the data requirements for training predictive models in nanophotonics.

Main Methods:

A nested transfer learning strategy was developed, training models sequentially on structures of increasing complexity.
A bidirectional recurrent neural network was used for the forward model to predict optical properties.
A convolutional mixture density network was employed for the inverse model to design structures.
A relaxed material choice at each layer was incorporated for enhanced versatility.

Main Results:

The nested transfer learning models achieved high accuracy in retrieving complex arbitrary spectra.
The models successfully matched idealized spectra for specific applications, such as selective thermal emitters.
The approach demonstrated the ability to handle thin film stacks with significantly higher optical complexity.
Data requirements for training were kept modest, showcasing improved data efficiency.

Conclusions:

The proposed nested transfer learning approach effectively addresses the challenge of limited training data in nanophotonics.
This method allows for the accurate design and prediction of complex nanophotonic structures.
The technique offers a promising and versatile solution for accelerating research and development in nanophotonics.