Machine learning discovery of the dielectric properties of strontium-containing condensed matter

The dielectric constant is one of the most important physical properties of dielectrics. The pursuit of materials with high dielectric constants has long been a central focus in both fundamental research and practical applications. Traditional theoretical predictions or first-principles calculations...

Full description

Saved in:
Bibliographic Details
Main Authors: Dongyang Huang, Jiaxing Fu, Chenghao Yu
Format: Article
Language:English
Published: Frontiers Media S.A. 2025-06-01
Series:Frontiers in Physics
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fphy.2025.1599182/full
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849418594045132800
author Dongyang Huang
Jiaxing Fu
Chenghao Yu
author_facet Dongyang Huang
Jiaxing Fu
Chenghao Yu
author_sort Dongyang Huang
collection DOAJ
description The dielectric constant is one of the most important physical properties of dielectrics. The pursuit of materials with high dielectric constants has long been a central focus in both fundamental research and practical applications. Traditional theoretical predictions or first-principles calculations of dielectric constants are often challenging and require significant time and computational resources. Machine learning techniques can establish models that link composition and properties, facilitating the study of dielectric properties in condensed matter and enhancing the efficiency of discovering new dielectrics. Strontium-containing dielectrics constitute a diverse class of materials, some of which exhibit exceptionally high dielectric constants, thereby showing great potential for practical applications. In this work, machine learning models were successfully developed to capture the relationship between composition and dielectric properties of strontium-containing dielectrics using different algorithms, with hyperparameter optimization performed via grid search. The optimal model achieved a correlation coefficient of 0.868 and demonstrated a certain degree of generalization ability on the test set. This model serves as a valuable reference and guide, improving the efficiency of dielectric material selection and the discovery of novel high-performance dielectrics.
format Article
id doaj-art-0a7ef27b1d8d45c9aeb5fbccc457b03c
institution Kabale University
issn 2296-424X
language English
publishDate 2025-06-01
publisher Frontiers Media S.A.
record_format Article
series Frontiers in Physics
spelling doaj-art-0a7ef27b1d8d45c9aeb5fbccc457b03c2025-08-20T03:32:24ZengFrontiers Media S.A.Frontiers in Physics2296-424X2025-06-011310.3389/fphy.2025.15991821599182Machine learning discovery of the dielectric properties of strontium-containing condensed matterDongyang Huang0Jiaxing Fu1Chenghao Yu2Materials Genome Institute, Shanghai University, Shanghai, ChinaAdvanced Micro-Fabrication Equipment Inc., Shanghai, ChinaDivision of Mechanics and Manufacture Measurement Technology, Shanghai Institute of Measurement and Testing Technology, Shanghai, ChinaThe dielectric constant is one of the most important physical properties of dielectrics. The pursuit of materials with high dielectric constants has long been a central focus in both fundamental research and practical applications. Traditional theoretical predictions or first-principles calculations of dielectric constants are often challenging and require significant time and computational resources. Machine learning techniques can establish models that link composition and properties, facilitating the study of dielectric properties in condensed matter and enhancing the efficiency of discovering new dielectrics. Strontium-containing dielectrics constitute a diverse class of materials, some of which exhibit exceptionally high dielectric constants, thereby showing great potential for practical applications. In this work, machine learning models were successfully developed to capture the relationship between composition and dielectric properties of strontium-containing dielectrics using different algorithms, with hyperparameter optimization performed via grid search. The optimal model achieved a correlation coefficient of 0.868 and demonstrated a certain degree of generalization ability on the test set. This model serves as a valuable reference and guide, improving the efficiency of dielectric material selection and the discovery of novel high-performance dielectrics.https://www.frontiersin.org/articles/10.3389/fphy.2025.1599182/fulldielectricsstrontiumdielectric constantmachine learningelectronic structure
spellingShingle Dongyang Huang
Jiaxing Fu
Chenghao Yu
Machine learning discovery of the dielectric properties of strontium-containing condensed matter
Frontiers in Physics
dielectrics
strontium
dielectric constant
machine learning
electronic structure
title Machine learning discovery of the dielectric properties of strontium-containing condensed matter
title_full Machine learning discovery of the dielectric properties of strontium-containing condensed matter
title_fullStr Machine learning discovery of the dielectric properties of strontium-containing condensed matter
title_full_unstemmed Machine learning discovery of the dielectric properties of strontium-containing condensed matter
title_short Machine learning discovery of the dielectric properties of strontium-containing condensed matter
title_sort machine learning discovery of the dielectric properties of strontium containing condensed matter
topic dielectrics
strontium
dielectric constant
machine learning
electronic structure
url https://www.frontiersin.org/articles/10.3389/fphy.2025.1599182/full
work_keys_str_mv AT dongyanghuang machinelearningdiscoveryofthedielectricpropertiesofstrontiumcontainingcondensedmatter
AT jiaxingfu machinelearningdiscoveryofthedielectricpropertiesofstrontiumcontainingcondensedmatter
AT chenghaoyu machinelearningdiscoveryofthedielectricpropertiesofstrontiumcontainingcondensedmatter