首页|期刊导航|Journal of Materiomics|An interpretable machine learning framework for predicting Curie temperature of lead-based piezoelectric ceramics

An interpretable machine learning framework for predicting Curie temperature of lead-based piezoelectric ceramicsOA

中文摘要

Lead-based perovskite piezoelectric ceramics exhibit tunable Curie temperatures through sophisticated compositional design,which is critical for high-temperature applications.However,predicting Tc re-mains challenging owing to complex compositional spaces.Herein,we develop an interpretable ma-chine learning framework leveraging published experimental data to guide the chemical design of lead-based piezoelectric ceramics.Our methodology involves:(1)exhaustive screening of feature combi-nations to minimize cross-validation errors,(2)Bayesian optimization of hyperparameters to reduce model error and improve predictive accuracy(R^(2)>0.98),and(3)Shapley Additive Explanations and partial dependence analysis to elucidate feature-T_(c) correlations and mitigate the black-box nature of conventional machine learning.Furthermore,the Sure Independence Screening and Sparsifying Oper-ator method extracts explicit mathematical formulas correlating with experimental Tc values(R^(2)>0.90).This work not only advances the rational design of lead-based piezoelectric ceramics for temperature-specific applications but also establishes a paradigm for machine learning in other func-tional material systems.

Zidong Wang;Chenbo Zhang;Fei Li

Electronic Materials Research Laboratory(Key Lab of Education Ministry),State Key Laboratory for Mechanical Behavior of Materials and School of Electronic and Information Engineering,Xi''an Jiaotong University,Xi''an,710049,ChinaMOE Key Laboratory of Advanced Micro-Structured Materials,School of Physics Science and Engineering,Institute for Advanced Study,Tongji University,Shanghai,200092,ChinaElectronic Materials Research Laboratory(Key Lab of Education Ministry),State Key Laboratory for Mechanical Behavior of Materials and School of Electronic and Information Engineering,Xi''an Jiaotong University,Xi''an,710049,China

信息技术与安全科学

Interpretable machine learningLead-based piezoelectric ceramicsCurie temperature prediction

《Journal of Materiomics》 2026 (4)

P.237-245,9

support of the National Key Research and Development Program of China(2024YFB3211800)National Natural Science Foundation of China(Grants:52325205 and 52422207)the Science and Technology Project of Xi''an(25ZQRC00005)Specialized Program for the Commercialization of Major Scientific and Technological Achievements of Xianyang(L2024-ZDKJ-ZDCGZH-0011)Shaanxi Provincial Key R&D Program Qinchuangyuan General Platform‘Four-Chain Integration’2024 PT-ZCK-14.

10.1016/j.jmat.2026.101247

评论