Deep-learning-based quality filtering of mechanically exfoliated 2D crystals

查看全文 作　　者：Yu [1,9]Saito;Kento [2]Shin;Kei [1,3]Terayama;Shaan [1]Desai;Masaru [4]Onga;Yuji [4]Nakagawa;Yuki [4]M.Itahashi;Yoshihiro [4,5]Iwasa;Makoto [1,6,7]Yamada;Koji [1,2,8]Tsuda

机构地区：[1]RIKEN Center for Advanced Intelligence Project(AIP),Tokyo 103-0027,Japan;[2]Department of Computational Biology and Medical Sciences,Graduate School of Frontier Sciences,The University of Tokyo,Kashiwa 277-8561,Japan;[3]Graduate School of Medicine,Kyoto University,Kyoto 606-8501,Japan;[4]Quantum-Phase Electronics Center(QPEC)and Department of Applied Physics,The University of Tokyo,Tokyo 113-8656,Japan;[5]RIKEN Center for Emergent Matter Science(CEMS),Wako 351-0198,Japan;[6]Department of Intelligence Science and Technology,Kyoto University,Kyoto 606-8501,Japan;[7]PRESTO,Japan Science and Technology Agency(JST),4-1-8,Honcho,Kawaguchi-shi,Saitama 332-0012,Japan;[8]National Institute for Materials Science(NIMS),Center for Materials Research by Information Integration,Tsukuba 305-0047,Japan;[9]California NanoSystems Institute,University of California at Santa Barbara,Santa Barbara,CA 93106,USA

出　　处：《npj Computational Materials》索引2019年第1期,共6页

基　　金：This work was supported by the“Materials research by Information Integration”Initiative(MI2I)project and Core Research for Evolutional Science and Technology(CREST)(JSPS KAKENHI Grant Numbers JPMJCR1502 and JPMJCR17J2)from Japan Science and Technology Agency(JST);It was also supported by Grant-in-Aid for Scientific Research on Innovative Areas“Nano Informatics”(JSPS KAKENHI Grant Number JP25106005);Grant-in-Aid for Specially Promoted Research(JSPS KAKENHI Grant Number JP25000003)from JSPS.M.O.and Y.M.I.were supported by Advanced Leading Graduate Course for Photon Science(ALPS).Y.S.was supported by Elings Prize Fellowship.Y.N.was supported by Materials Education program for the future leaders in Research,Industry,and Technology(MERIT).M.O.and Y.N.were supported by the Japan Society for the Promotion of Science(JSPS)through a research fellowship for young scientists(Grant-in-Aid for JSPS Research Fellow,JSPS KAKENHI Grant Numbers JP17J09152 and JP17J08941,respectively);M.Y.was supported by JST PRESTO(Precursory Research for Embryonic Science and Technology)program JPMJPR165A. 摘　　要：Two-dimensional(2D)crystals are attracting growing interest in various research fields such as engineering,physics,chemistry,pharmacy,and biology owing to their low dimensionality and dramatic change of properties compared to the bulk counter parts.Among the various techniques used to manufacture 2D crystals,mechanical exfoliation has been essential to practical applications and fundamental research.However,mechanically exfoliated crystals on substrates contain relatively thick flakes that must be found and removed manually,limiting high-throughput manufacturing of atomic 2D crystals and van der Waals heterostructures.Here,we present a deep-learning-based method to segment and identify the thickness of atomic layer flakes from optical microscopy images.Through carefully designing a neural network based on U-Net,we found that our neural network based on Unet trained only with the data based on realistically small number of images successfully distinguish monolayer and bilayer MoS2 and graphene with a success rate of 70–80%,which is a practical value in the first screening process for choosing monolayer and bilayer flakes of all flakes on substrates without human eye.The remarkable results highlight the possibility that a large fraction of manual laboratory work can be replaced by AI-based systems,boosting productivity. 关键词：CRYSTALS FILTERING attracting

相关文献

参考文献（39）
引证文献（4）
耦合文献（16）

参考文献(39)

引证文献(4)

耦合文献(16)

互联网出版许可证新出网证(渝)字10号全国400电话 - 免长途话费

Deep-learning-based quality filtering of mechanically exfoliated 2D crystals

参考文献(39)

引证文献(4)

耦合文献(16)

用户提示