Recommender system for discovery of inorganic compounds

作     者：Hiroyuki Hayashi Atsuto Seko Isao Tanaka 

作者机构：Department of Materials Science and EngineeringKyoto UniversityKyotoJapan Nano Research LaboratoryJapan Fine Ceramics Center(JFCC)NagoyaJapan 

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：2084-2090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] 070303[理学-有机化学] 0703[理学-化学] 

基　　金：H.H.was supported by PRESTO,JST,and JSPS KAKENHI(Grant No.JP20H02423) A.S.was supported by PRESTO,JST,and JSPS KAKENHI(Grant Nos.JP18K18942 and JP19H05787) I.T.was supported by JSPS KAKENHI(Grant No.JP21H04621) 

主　　题：method. inorganic system 

摘      要：A recommender system based on experimental databases is useful for the efficient discovery of inorganic ***,we review studies on the discovery of as-yet-unknown compounds using recommender *** first method used compositional descriptors made up of elemental *** compositions registered in the inorganic crystal structure database(ICSD)were supplied to machine learning for binary *** other method did not use any descriptors,but a tensor decomposition technique was *** predictive performance for currently unknown chemically relevant compositions(CRCs)was determined by examining their presence in other *** to the recommendation,synthesis experiments of two pseudo-ternary compounds with currently unknown structures were ***,a synthesis-condition recommender system was constructed by machine learning of a parallel experimental data-set collected in-house using a polymerized complex *** scores for unexperimented conditions were then *** experiments under the targeted conditions found two yet-unknown pseudo-binary oxides.