Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification

Abstract Chalcogenide glasses, renowned for their exceptional optoelectronic properties, have become the material of choice for numerous microelectronic and optical devices. With the rapid development of artificial intelligence technologies in the field of materials science, researchers have increas...

Full description

Saved in:
Bibliographic Details
Main Authors: Hui Li, Pan Liu, Shaoyun Liu, Bin Yang
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-04391-9
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849725318338707456
author Hui Li
Pan Liu
Shaoyun Liu
Bin Yang
author_facet Hui Li
Pan Liu
Shaoyun Liu
Bin Yang
author_sort Hui Li
collection DOAJ
description Abstract Chalcogenide glasses, renowned for their exceptional optoelectronic properties, have become the material of choice for numerous microelectronic and optical devices. With the rapid development of artificial intelligence technologies in the field of materials science, researchers have increasingly incorporated machine learning (ML) methods to accelerate the exploration of composition–structure–property relationships in chalcogenide glasses. However, traditional ML methods, which predominantly rely on single-property modelling, are often inadequate for addressing the practical demand for multiproperty collaborative optimization. To overcome this limitation, this study proposes a graph-based deep learning approach and develops a novel model for the efficient prediction of key properties of chalcogenide glasses. Furthermore, relevant data were collected from the publicly available SciGlass database to construct an experimental dataset, and the performance of the developed model was systematically evaluated. The experimental results demonstrate the model’s remarkable stability and predictive performance, highlighting its potential application value in the design and development of chalcogenide glasses.
format Article
id doaj-art-1a8d6e13a9a94e0199f364479ddac8bd
institution DOAJ
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-1a8d6e13a9a94e0199f364479ddac8bd2025-08-20T03:10:29ZengNature PortfolioScientific Reports2045-23222025-06-011511810.1038/s41598-025-04391-9Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classificationHui Li0Pan Liu1Shaoyun Liu2Bin Yang3Kunming University of Science and TechnologyShandong Humon Smelting Co., Ltd.Shandong Humon Smelting Co., Ltd.Kunming University of Science and TechnologyAbstract Chalcogenide glasses, renowned for their exceptional optoelectronic properties, have become the material of choice for numerous microelectronic and optical devices. With the rapid development of artificial intelligence technologies in the field of materials science, researchers have increasingly incorporated machine learning (ML) methods to accelerate the exploration of composition–structure–property relationships in chalcogenide glasses. However, traditional ML methods, which predominantly rely on single-property modelling, are often inadequate for addressing the practical demand for multiproperty collaborative optimization. To overcome this limitation, this study proposes a graph-based deep learning approach and develops a novel model for the efficient prediction of key properties of chalcogenide glasses. Furthermore, relevant data were collected from the publicly available SciGlass database to construct an experimental dataset, and the performance of the developed model was systematically evaluated. The experimental results demonstrate the model’s remarkable stability and predictive performance, highlighting its potential application value in the design and development of chalcogenide glasses.https://doi.org/10.1038/s41598-025-04391-9Chalcogenide glasses; Deep learning; Property prediction
spellingShingle Hui Li
Pan Liu
Shaoyun Liu
Bin Yang
Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification
Scientific Reports
Chalcogenide glasses; Deep learning; Property prediction
title Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification
title_full Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification
title_fullStr Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification
title_full_unstemmed Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification
title_short Deep learning-assisted attribute prediction of chalcogenide glasses based on graph classification
title_sort deep learning assisted attribute prediction of chalcogenide glasses based on graph classification
topic Chalcogenide glasses; Deep learning; Property prediction
url https://doi.org/10.1038/s41598-025-04391-9
work_keys_str_mv AT huili deeplearningassistedattributepredictionofchalcogenideglassesbasedongraphclassification
AT panliu deeplearningassistedattributepredictionofchalcogenideglassesbasedongraphclassification
AT shaoyunliu deeplearningassistedattributepredictionofchalcogenideglassesbasedongraphclassification
AT binyang deeplearningassistedattributepredictionofchalcogenideglassesbasedongraphclassification