Perovskite synthesizability using graph neural networks

作     者：Geun Ho Gu Jidon Jang Juhwan Noh Aron Walsh Yousung Jung 

作者机构：Department of Chemical and Biomolecular Engineering(BK21 four)KAIST291 Daehak-ro 34141Daejeon305-335South Korea School of Energy TechnologyKorea Institute of Energy Technology200 Hyuksin-roNaju58330South Korea Department of MaterialsImperial College LondonLondonSW72AZUK Department of Materials Science and EngineeringYonsei UniversitySeoul03722South Korea 

出 版 物：《npj Computational Materials》 (计算材料学（英文）)

年 卷 期：2022年第8卷第1期

页      面：697-704页

核心收录：

学科分类：081704[工学-应用化学] 07[理学] 08[工学] 0817[工学-化学工程与技术] 0805[工学-材料科学与工程（可授工学、理学学位）] 0703[理学-化学] 070301[理学-无机化学] 

基　　金：We acknowledge generous financial support from NRF Korea(NRF-2019M3D3A1A01069099) 

主　　题：methods. perovskite halide 

摘      要：Perovskite is an important material type in geophysics and for technologically important ***,the number of synthetic perovskites remains relatively *** accelerate the high-throughput discovery of perovskites,we propose a graph neural network model to assess their *** trained model shows a promising 0.957 out-of-sample true positive rate,significantly improving over empirical rule-based *** validation is established by demonstrating that a significant portion of the virtual crystals that are predicted to be synthesizable have already been indeed synthesized in literature,and those with the lowest synthesizability scores have not been *** previous empirical strategies are mainly applicable to metal oxides,our model is general and capable of predicting the synthesizability across all classes of perovskites,including chalcogenide,halide,and hydride perovskites,as well as *** apply the method to identify synthesizable perovskite candidates for two potential applications,the Li-rich ion conductors and metal halide optical materials that can be tested experimentally.