Property-guided generation of complex polymer topologies using variational autoencoders  

作　　者：Shengli Jiang Adji Bousso Dieng Michael A.Webb 

机构地区：[1]Department of Chemical and Biological Engineering,Princeton University,Princeton,NJ,USA [2]Vertaix,Department of Computer Science,Princeton University,Princeton,NJ,USA

出　　处：《npj Computational Materials》2024年第1期1825-1837,共13页计算材料学(英文)

基　　金：M.A.W.and A.B.D acknowledge funding from the Princeton Catalysis Initiative for this research;M.A.W.and S.J.also acknowledge support from the donors of ACS Petroleum Research Fund under Doctoral New Investigator Grant 66706-DNI7.

摘　　要：The complexity and diversity of polymer topologies,or chain architectures,present substantial challenges in predicting and engineering polymer properties.Although machine learning is increasingly used in polymer science,applications to address architecturally complex polymers are nascent.Here,we use a generative machine learning model based on variational autoencoders and data generated from molecular dynamics simulations to design polymer topologies that exhibit target properties.

关 键 词：properties VARIATIONAL POLYMER 

分 类 号：O63[理学—高分子化学]