Composition-temperature phase diagrams are crucial for designing ferroelectric materials,however predicting them accurately remains challenging due to limited phase transformation data and the constraints of conventio...Composition-temperature phase diagrams are crucial for designing ferroelectric materials,however predicting them accurately remains challenging due to limited phase transformation data and the constraints of conventional methods.Here,we utilize natural language processing(NLP)to text-mine 41,597 research articles,compiling a dataset of 2838 phase transformations across 846 ferroelectric materials.Leveraging this dataset,we develop FerroAI,a deep learning model for phase diagram prediction.FerroAI successfully predicts phase boundaries and transformations among different crystal symmetries in Ce/Zr co-doped BaTiO_(3)(BT)-xBa_(0.7)Ca_(0.3)TiO_(3)(BCT).It also identifies a morphotropic phase boundary in Zr/Hf co-doped BT-xBCT at x=0.3,guiding the discovery of a new ferroelectric material with an experimentally measured dielectric constant of 11,051.These results establish FerroAI as a powerful tool for phase diagram construction,guiding the design of highperformance ferroelectric materials.展开更多
基金support by National Natural Science Foundation of China(No.12204350)Fundamental Research Funds for the Central Universities(No.22120240009,22120250300)X.C.thank the financial support under GRF Grants 16203021,16204022,16203023 by the Research Grants Council,Hong Kong.
文摘Composition-temperature phase diagrams are crucial for designing ferroelectric materials,however predicting them accurately remains challenging due to limited phase transformation data and the constraints of conventional methods.Here,we utilize natural language processing(NLP)to text-mine 41,597 research articles,compiling a dataset of 2838 phase transformations across 846 ferroelectric materials.Leveraging this dataset,we develop FerroAI,a deep learning model for phase diagram prediction.FerroAI successfully predicts phase boundaries and transformations among different crystal symmetries in Ce/Zr co-doped BaTiO_(3)(BT)-xBa_(0.7)Ca_(0.3)TiO_(3)(BCT).It also identifies a morphotropic phase boundary in Zr/Hf co-doped BT-xBCT at x=0.3,guiding the discovery of a new ferroelectric material with an experimentally measured dielectric constant of 11,051.These results establish FerroAI as a powerful tool for phase diagram construction,guiding the design of highperformance ferroelectric materials.
