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

Search research articles

Related Experiment Video

Updated: May 21, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Data-Driven Prediction and Inverse Design of Fluoride Glasses via Explainable GA-BP Neural Networks.

Runze Zhou¹, Xinqiang Yuan¹, Longfei Zhang²

¹School of Physics and Optoelectronic Engineering, Hangzhou Institute for Advanced Study, University of Chinese Academy of Sciences, Hangzhou 310024, China.

Materials (Basel, Switzerland)

|May 13, 2026

Summary

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

Size-tunable and efficient fabrication of CsPbBr<sub>3</sub> superlattices by high-temperature self-assembly for superfluorescence.

Journal of colloid and interface science·2026

Same author

Design and implementation of an avalanche photodiode array receiver for fluorescent-antenna-based visible light communication systems.

Applied optics·2026

Same author

Single-crystal growth of complex non-fullerene acceptor molecules via cocrystallization.

Nature communications·2026

Same author

Ultra-fast photoluminescence dynamics process based on CsPbBr<sub>3</sub> perovskite microspheres.

Optics express·2026

Same author

Visualization-guided growth of CsPbBr<sub>3</sub> microcrystals via water-induced phase transition.

Communications chemistry·2025

Same author

Diffusion model-based inverse design of photonic crystals for customized refraction.

Nanophotonics (Berlin, Germany)·2025

Machine learning accelerates fluoride glass design by predicting properties and identifying optimal compositions. This data-driven approach surpasses traditional methods, enabling efficient development of advanced optical materials.

Area of Science:

Materials Science
Optics
Computational Chemistry

Background:

Traditional glass development relies on empirical methods, which are insufficient for advanced optical material demands.
Novel fluoride glasses offer unique optical properties but require efficient design strategies.

Purpose of the Study:

To develop a machine learning-based method for designing advanced fluoride glass materials.
To predict glass properties and perform inverse design for specific applications.

Main Methods:

Developed predictive models for density and refractive index using neural networks and online fluoride glass datasets.
Utilized SHapley Additive exPlanations (SHAP) for quantitative composition-property relationship analysis.
Employed inverse design with a trained model to identify optimal glass compositions.

Keywords:

SHapley Additive exPlanations density fluoride glass inverse design neural network refractive index

Related Experiment Videos

Last Updated: May 21, 2026

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Evidence-based Knowledge Synthesis and Hypothesis Validation: Navigating Biomedical Knowledge Bases via Explainable AI and Agentic Systems

Published on: June 13, 2025

Main Results:

Successfully predicted density and refractive index of fluoride glasses.
Identified key composition-property relationships using SHAP analysis.
Experimentally validated several recommended compositions, showing good agreement between predicted and measured properties.

Conclusions:

The proposed neural network-based machine learning method is effective for designing advanced fluoride glass materials.
This data-driven approach significantly improves upon traditional methods for glass development.
The validated compositions demonstrate the practical applicability of the machine learning model.