Materials design with target-oriented Bayesian optimization

Abstract Materials design using Bayesian optimization (BO) typically focuses on optimizing materials properties by estimating the maxima/minima of unknown functions. However, materials often possess good properties at specific values or show effective response under certain conditions. We propose a...

Full description

Saved in:
Bibliographic Details
Main Authors: Yuan Tian, Tongtong Li, Jianbo Pang, Yumei Zhou, Dezhen Xue, Xiangdong Ding, Turab Lookman
Format: Article
Language:English
Published: Nature Portfolio 2025-07-01
Series:npj Computational Materials
Online Access:https://doi.org/10.1038/s41524-025-01704-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849334450517704704
author Yuan Tian
Tongtong Li
Jianbo Pang
Yumei Zhou
Dezhen Xue
Xiangdong Ding
Turab Lookman
author_facet Yuan Tian
Tongtong Li
Jianbo Pang
Yumei Zhou
Dezhen Xue
Xiangdong Ding
Turab Lookman
author_sort Yuan Tian
collection DOAJ
description Abstract Materials design using Bayesian optimization (BO) typically focuses on optimizing materials properties by estimating the maxima/minima of unknown functions. However, materials often possess good properties at specific values or show effective response under certain conditions. We propose a target-oriented BO to efficiently suggest materials with target-specific properties. The method samples potential candidates by allowing their properties to approach the target value from either above or below, minimizing experimental iterations. We compare the performance of target-oriented BO with that of other BO methods on synthetic functions and materials databases. The average results from hundreds of repeated trials demonstrate target-oriented BO requires fewer experimental iterations to reach the same target, especially when the training dataset is small. We further employ the method to discover a thermally-responsive shape memory alloy Ti0.20Ni0.36Cu0.12Hf0.24Zr0.08 with a transformation temperature difference of only 2.66 °C (0.58% of the range) from the target temperature in 3 experimental iterations. Our method provides a solution tailored for optimizing target-specific properties, facilitating the accelerated development of materials with predefined properties.
format Article
id doaj-art-32b1b5cfd26849f8b31b3fa9f8b532c1
institution Kabale University
issn 2057-3960
language English
publishDate 2025-07-01
publisher Nature Portfolio
record_format Article
series npj Computational Materials
spelling doaj-art-32b1b5cfd26849f8b31b3fa9f8b532c12025-08-20T03:45:34ZengNature Portfolionpj Computational Materials2057-39602025-07-0111111110.1038/s41524-025-01704-4Materials design with target-oriented Bayesian optimizationYuan Tian0Tongtong Li1Jianbo Pang2Yumei Zhou3Dezhen Xue4Xiangdong Ding5Turab Lookman6Materials Genome Institute, Shanghai UniversitySchool of Materials Science and Engineering, Zhejiang Sci-Tech UniversityState Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong UniversityState Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong UniversityState Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong UniversityState Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong UniversityState Key Laboratory for Mechanical Behavior of Materials, Xi’an Jiaotong UniversityAbstract Materials design using Bayesian optimization (BO) typically focuses on optimizing materials properties by estimating the maxima/minima of unknown functions. However, materials often possess good properties at specific values or show effective response under certain conditions. We propose a target-oriented BO to efficiently suggest materials with target-specific properties. The method samples potential candidates by allowing their properties to approach the target value from either above or below, minimizing experimental iterations. We compare the performance of target-oriented BO with that of other BO methods on synthetic functions and materials databases. The average results from hundreds of repeated trials demonstrate target-oriented BO requires fewer experimental iterations to reach the same target, especially when the training dataset is small. We further employ the method to discover a thermally-responsive shape memory alloy Ti0.20Ni0.36Cu0.12Hf0.24Zr0.08 with a transformation temperature difference of only 2.66 °C (0.58% of the range) from the target temperature in 3 experimental iterations. Our method provides a solution tailored for optimizing target-specific properties, facilitating the accelerated development of materials with predefined properties.https://doi.org/10.1038/s41524-025-01704-4
spellingShingle Yuan Tian
Tongtong Li
Jianbo Pang
Yumei Zhou
Dezhen Xue
Xiangdong Ding
Turab Lookman
Materials design with target-oriented Bayesian optimization
npj Computational Materials
title Materials design with target-oriented Bayesian optimization
title_full Materials design with target-oriented Bayesian optimization
title_fullStr Materials design with target-oriented Bayesian optimization
title_full_unstemmed Materials design with target-oriented Bayesian optimization
title_short Materials design with target-oriented Bayesian optimization
title_sort materials design with target oriented bayesian optimization
url https://doi.org/10.1038/s41524-025-01704-4
work_keys_str_mv AT yuantian materialsdesignwithtargetorientedbayesianoptimization
AT tongtongli materialsdesignwithtargetorientedbayesianoptimization
AT jianbopang materialsdesignwithtargetorientedbayesianoptimization
AT yumeizhou materialsdesignwithtargetorientedbayesianoptimization
AT dezhenxue materialsdesignwithtargetorientedbayesianoptimization
AT xiangdongding materialsdesignwithtargetorientedbayesianoptimization
AT turablookman materialsdesignwithtargetorientedbayesianoptimization