Generative adversarial networks (GAN) based efficient sampling of chemical composition space for inverse design of inorganic materials  

作　　者：Yabo Dan Yong Zhao Xiang Li Shaobo Li Ming Hu Jianjun Hu 

机构地区：[1]School of Mechanical Engineering,Guizhou University,Guiyang 550025,China [2]Department of Computer Science and Engineering,University of South Carolina,Columbia,SC 29201,USA [3]Key Laboratory of Advanced Manufacturing Technology,Ministry of Education,Guizhou University,Guiyang 550025,China [4]Department of Mechanical Engineering,University of South Carolina,Columbia,SC 29201,USA

出　　处：《npj Computational Materials》2020年第1期964-970,共7页计算材料学（英文）

基　　金：This work as partially supported by the National Science Foundation under grant numbers:1940099,1905775,OIA-1655740,and SC EPSCoR GEAR Grant 19-GC02 and by DOE under grant number DE-SC0020272;The authors also acknowledge funding from the National Natural Science Foundation of China under grant number 51741101;This work is also partially supported by National Major Scientific and Technological Special Project of China under grant number 2018AAA0101803;also by Guizhou Province Science&Technology Plan Talent Program under grant number[2017]5788.

摘　　要：A major challenge in materials design is how to efficiently search the vast chemical design space to find the materials with desired properties.One effective strategy is to develop sampling algorithms that can exploit both explicit chemical knowledge and implicit composition rules embodied in the large materials database.Here,we propose a generative machine learning model(MatGAN)based on a generative adversarial network(GAN)for efficient generation of new hypothetical inorganic materials.Trained with materials from the ICSD database,our GAN model can generate hypothetical materials not existing in the training dataset,reaching a novelty of 92.53% when generating 2 million samples.The percentage of chemically valid(charge-neutral and electronegativitybalanced)samples out of all generated ones reaches 84.5% when generated by our GAN trained with such samples screened from ICSD,even though no such chemical rules are explicitly enforced in our GAN model,indicating its capability to learn implicit chemical composition rules to form compounds.Our algorithm is expected to be used to greatly expand the range of the design space for inverse design and large-scale computational screening of inorganic materials.

关 键 词：CHEMICAL INVERSE NETWORKS 

分 类 号：TB321[一般工业技术—材料科学与工程]