Machine learning has revolutionized many fields,including materials science.However,predicting the properties of crystalline materials using machine learning faces challenges in input encoding,output versatility,and i...Machine learning has revolutionized many fields,including materials science.However,predicting the properties of crystalline materials using machine learning faces challenges in input encoding,output versatility,and interpretability.We introduce Crystal BERT,an adaptable transformer-based framework integrating space group,elemental,and unit cell information.This novel structure can seamlessly combine diverse features and accurately predict various physical properties,including topological properties,superconducting transition temperatures,dielectric constants,and more.Crystal BERT provides insightful interpretations of features influencing target properties.Our results indicate that space group and elemental information are crucial for predicting topological and superconducting properties,underscoring their intricate nature.By incorporating these features,we achieve91%accuracy in topological classification,surpassing prior studies and identifying previously misclassified materials.This research demonstrates that integrating diverse material information enhances the prediction of complex material properties,paving the way for more accurate and interpretable machine learning models in materials science.展开更多
基金supported by the Natural Science Foundation of China(Grant Nos.12350404 and 12174066)the Innovation Program for Quantum Science and Technology(Grant No.2021ZD0302600)+2 种基金the Science and Technology Commission of Shanghai Municipality(Grant Nos.23JC1400600,24LZ1400100,and 2019SHZDZX01)sponsored by“Shuguang Program”supported by Shanghai Education Development FoundationShanghai Municipal Education Commission。
文摘Machine learning has revolutionized many fields,including materials science.However,predicting the properties of crystalline materials using machine learning faces challenges in input encoding,output versatility,and interpretability.We introduce Crystal BERT,an adaptable transformer-based framework integrating space group,elemental,and unit cell information.This novel structure can seamlessly combine diverse features and accurately predict various physical properties,including topological properties,superconducting transition temperatures,dielectric constants,and more.Crystal BERT provides insightful interpretations of features influencing target properties.Our results indicate that space group and elemental information are crucial for predicting topological and superconducting properties,underscoring their intricate nature.By incorporating these features,we achieve91%accuracy in topological classification,surpassing prior studies and identifying previously misclassified materials.This research demonstrates that integrating diverse material information enhances the prediction of complex material properties,paving the way for more accurate and interpretable machine learning models in materials science.
