A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra

Stacking fault energy (SFE) is a critical property governing deformation mechanisms and influencing the mechanical behavior of materials. This work presents a unified framework for understanding and predicting SFE based solely on an electronic structure representation. By integrating density of stat...

Full description

Saved in:
Bibliographic Details
Main Authors: Md Tohidul Islam, Scott R. Broderick
Format: Article
Language:English
Published: MDPI AG 2025-04-01
Series:Crystals
Subjects:
Online Access:https://www.mdpi.com/2073-4352/15/5/390
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850257884049309696
author Md Tohidul Islam
Scott R. Broderick
author_facet Md Tohidul Islam
Scott R. Broderick
author_sort Md Tohidul Islam
collection DOAJ
description Stacking fault energy (SFE) is a critical property governing deformation mechanisms and influencing the mechanical behavior of materials. This work presents a unified framework for understanding and predicting SFE based solely on an electronic structure representation. By integrating density of states (DOS) spectral data, dimensionality reduction techniques, and machine learning models, it was found that the SFE behavior is indeed represented within the electronic structure and that this information can be used to accelerate the prediction of SFE. In the first part of this study, we established quantitative relationships between electronic structure and microstructural features, linking chemistry to mechanical properties. Using principal component analysis (PCA) and uniform manifold approximation and projection (UMAP), we identified key features from high-resolution vector representation of DOS data and explored their correlation with SFE. The second part of this work focuses on the predictive modeling of SFE, where a machine learning model trained on UMAP-reduced features achieved high accuracy (R<sup>2</sup> = 0.86, MAE = 15.46 mJ/m<sup>2</sup>). To bridge length scales, we extended this methodology to predict SFE in alloy systems, leveraging single-element data to inform multi-element alloy design. We illustrate this approach with Cu-Zn alloys, where the framework enabled rapid screening of compositional space while capturing complex electronic structure interactions. The proposed framework accelerates alloy design by reducing reliance on costly experiments and ab initio calculations.
format Article
id doaj-art-189dfe56dc954c3a908a37c4202ff76a
institution OA Journals
issn 2073-4352
language English
publishDate 2025-04-01
publisher MDPI AG
record_format Article
series Crystals
spelling doaj-art-189dfe56dc954c3a908a37c4202ff76a2025-08-20T01:56:19ZengMDPI AGCrystals2073-43522025-04-0115539010.3390/cryst15050390A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States SpectraMd Tohidul Islam0Scott R. Broderick1Department of Materials Design and Innovation, University at Buffalo, Buffalo, NY 14260, USADepartment of Materials Design and Innovation, University at Buffalo, Buffalo, NY 14260, USAStacking fault energy (SFE) is a critical property governing deformation mechanisms and influencing the mechanical behavior of materials. This work presents a unified framework for understanding and predicting SFE based solely on an electronic structure representation. By integrating density of states (DOS) spectral data, dimensionality reduction techniques, and machine learning models, it was found that the SFE behavior is indeed represented within the electronic structure and that this information can be used to accelerate the prediction of SFE. In the first part of this study, we established quantitative relationships between electronic structure and microstructural features, linking chemistry to mechanical properties. Using principal component analysis (PCA) and uniform manifold approximation and projection (UMAP), we identified key features from high-resolution vector representation of DOS data and explored their correlation with SFE. The second part of this work focuses on the predictive modeling of SFE, where a machine learning model trained on UMAP-reduced features achieved high accuracy (R<sup>2</sup> = 0.86, MAE = 15.46 mJ/m<sup>2</sup>). To bridge length scales, we extended this methodology to predict SFE in alloy systems, leveraging single-element data to inform multi-element alloy design. We illustrate this approach with Cu-Zn alloys, where the framework enabled rapid screening of compositional space while capturing complex electronic structure interactions. The proposed framework accelerates alloy design by reducing reliance on costly experiments and ab initio calculations.https://www.mdpi.com/2073-4352/15/5/390stacking fault energydensity of statesmachine learning (ML) in materials sciencealloy designdimensionality reduction
spellingShingle Md Tohidul Islam
Scott R. Broderick
A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra
Crystals
stacking fault energy
density of states
machine learning (ML) in materials science
alloy design
dimensionality reduction
title A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra
title_full A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra
title_fullStr A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra
title_full_unstemmed A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra
title_short A Data-Driven Framework for Accelerated Modeling of Stacking Fault Energy from Density of States Spectra
title_sort data driven framework for accelerated modeling of stacking fault energy from density of states spectra
topic stacking fault energy
density of states
machine learning (ML) in materials science
alloy design
dimensionality reduction
url https://www.mdpi.com/2073-4352/15/5/390
work_keys_str_mv AT mdtohidulislam adatadrivenframeworkforacceleratedmodelingofstackingfaultenergyfromdensityofstatesspectra
AT scottrbroderick adatadrivenframeworkforacceleratedmodelingofstackingfaultenergyfromdensityofstatesspectra
AT mdtohidulislam datadrivenframeworkforacceleratedmodelingofstackingfaultenergyfromdensityofstatesspectra
AT scottrbroderick datadrivenframeworkforacceleratedmodelingofstackingfaultenergyfromdensityofstatesspectra