Theory-guided machine learning to predict configurational energies of high distortion alloy systems

Cluster expansion (CE) is a popular surrogate model to density functional theory (DFT) for modeling the stability of alloy systems through configurational energies. However, since CE is a lattice-based model, its accuracy is often poor when applied to high-entropy alloys (HEAs) with significan...

Full description

Saved in:
Bibliographic Details
Main Author: Huang, Xufa
Other Authors: Kedar Hippalgaonkar
Format: Final Year Project
Language:English
Published: Nanyang Technological University 2023
Subjects:
Online Access:https://hdl.handle.net/10356/165985
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-165985
record_format dspace
spelling sg-ntu-dr.10356-1659852024-04-09T02:34:29Z Theory-guided machine learning to predict configurational energies of high distortion alloy systems Huang, Xufa Kedar Hippalgaonkar School of Materials Science and Engineering Agency for Science, Technology and Research (A*STAR) Institute of Material Research and Engineering, A*STAR Institute of High Performance Computing, A*STAR Tan Teck Leong Leong Zhidong tantl@ihpc.a-star.edu.sg, leong_zhidong@ihpc.a-star.edu.sg, kedar@ntu.edu.sg Engineering::Materials Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling Cluster expansion (CE) is a popular surrogate model to density functional theory (DFT) for modeling the stability of alloy systems through configurational energies. However, since CE is a lattice-based model, its accuracy is often poor when applied to high-entropy alloys (HEAs) with significant structural distortion. State-of-the-art attempts at using CE with machine learning (ML) models like Lasso and Bayesian for selecting meaningful clusters show high prediction errors for these high distortion alloy systems, where the contributions of long-range effective cluster interactions (ECIs) to configurational energetics remain significant. Adopting only clusters as descriptors has proven insufficient for accurate and robust predictions. This paper presents the novel integration of feature generation from clusters in CE and over 3000 Matminer material descriptors, to comprehensively capture the behavior of complex high distortion systems. Matminer features have proved effective for predicting material properties such as bandgap, elastic constants, formation energies, adsorption energies, and ferromagnetic properties in the past. Using recursive feature elimination, optimized based on stable weight assignment of ridge regularization, we sieved out only important descriptors in a high dimensional framework where configurational energy labels vastly exceed the number of descriptors. The pipeline is applied to the ten constituent binary alloys of HEA Mo-Nb-V-Ti-Zr, which is known to have large structural distortions, and we discovered that the prediction accuracy significantly improved by an average of 56%, consistent across all ten binary alloy systems. More importantly, we found the four important classes of features—coordination number, XRD, dihedral-angle distribution function, and clusters—that our model consistently select across all ten binaries. Our results are robust, showing that the additional descriptors from Matminer can better capture the behavior of high-distortion alloy systems. These important classes of descriptors are also transferable to other complex systems, such as HEAs, that are currently poorly understood, and to give robust prediction of their properties, accelerating the discovery of these high-performance alloys. Bachelor of Engineering (Materials Engineering) 2023-04-17T07:56:00Z 2023-04-17T07:56:00Z 2023 Final Year Project (FYP) Huang, X. (2023). Theory-guided machine learning to predict configurational energies of high distortion alloy systems. Final Year Project (FYP), Nanyang Technological University, Singapore. https://hdl.handle.net/10356/165985 https://hdl.handle.net/10356/165985 en application/pdf Nanyang Technological University
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic Engineering::Materials
Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling
spellingShingle Engineering::Materials
Engineering::Computer science and engineering::Computing methodologies::Simulation and modeling
Huang, Xufa
Theory-guided machine learning to predict configurational energies of high distortion alloy systems
description Cluster expansion (CE) is a popular surrogate model to density functional theory (DFT) for modeling the stability of alloy systems through configurational energies. However, since CE is a lattice-based model, its accuracy is often poor when applied to high-entropy alloys (HEAs) with significant structural distortion. State-of-the-art attempts at using CE with machine learning (ML) models like Lasso and Bayesian for selecting meaningful clusters show high prediction errors for these high distortion alloy systems, where the contributions of long-range effective cluster interactions (ECIs) to configurational energetics remain significant. Adopting only clusters as descriptors has proven insufficient for accurate and robust predictions. This paper presents the novel integration of feature generation from clusters in CE and over 3000 Matminer material descriptors, to comprehensively capture the behavior of complex high distortion systems. Matminer features have proved effective for predicting material properties such as bandgap, elastic constants, formation energies, adsorption energies, and ferromagnetic properties in the past. Using recursive feature elimination, optimized based on stable weight assignment of ridge regularization, we sieved out only important descriptors in a high dimensional framework where configurational energy labels vastly exceed the number of descriptors. The pipeline is applied to the ten constituent binary alloys of HEA Mo-Nb-V-Ti-Zr, which is known to have large structural distortions, and we discovered that the prediction accuracy significantly improved by an average of 56%, consistent across all ten binary alloy systems. More importantly, we found the four important classes of features—coordination number, XRD, dihedral-angle distribution function, and clusters—that our model consistently select across all ten binaries. Our results are robust, showing that the additional descriptors from Matminer can better capture the behavior of high-distortion alloy systems. These important classes of descriptors are also transferable to other complex systems, such as HEAs, that are currently poorly understood, and to give robust prediction of their properties, accelerating the discovery of these high-performance alloys.
author2 Kedar Hippalgaonkar
author_facet Kedar Hippalgaonkar
Huang, Xufa
format Final Year Project
author Huang, Xufa
author_sort Huang, Xufa
title Theory-guided machine learning to predict configurational energies of high distortion alloy systems
title_short Theory-guided machine learning to predict configurational energies of high distortion alloy systems
title_full Theory-guided machine learning to predict configurational energies of high distortion alloy systems
title_fullStr Theory-guided machine learning to predict configurational energies of high distortion alloy systems
title_full_unstemmed Theory-guided machine learning to predict configurational energies of high distortion alloy systems
title_sort theory-guided machine learning to predict configurational energies of high distortion alloy systems
publisher Nanyang Technological University
publishDate 2023
url https://hdl.handle.net/10356/165985
_version_ 1814047391835226112