Availability of affordable and widely applicable interatomic potentials is the key needed to unlock the riches of modern materials modeling.Artificial neural network-based approaches for generating potentials are prom...Availability of affordable and widely applicable interatomic potentials is the key needed to unlock the riches of modern materials modeling.Artificial neural network-based approaches for generating potentials are promising;however,neural network training requires large amounts of data,sampled adequately from an often unknown potential energy surface.Here we propose a selfconsistent approach that is based on crystal structure prediction formalism and is guided by unsupervised data analysis,to construct an accurate,inexpensive,and transferable artificial neural network potential.Using this approach,we construct an interatomic potential for carbon and demonstrate its ability to reproduce first principles results on elastic and vibrational properties for diamond,graphite,and graphene,as well as energy ordering and structural properties of a wide range of crystalline and amorphous phases.展开更多
基金The work of E.Ka and E.Küwas supported by a DOE grant,BES Award DE-SC0019300E.Kü,F.P.,and S.d.G.are grateful for the financial support by European Union’s Horizon 2020 research and innovation program under Grant agreement No.676531(project E-CAM)+2 种基金S.d.G.also acknowledges EU funding under Grant agreement No.824143(project MaX)This work used the high-performance computing resources of CINECA,SISSA,and FASRC Cannon cluster supported by the FAS Division of Science Research Computing Group at Harvard University.This work also used the Extreme Science and Engineering Discovery Environment(XSEDE),which is supported by National Science Foundation Grant number ACI-154856263specifically it used Stampede2 at TACC through allocation TG-DMR120073.
文摘Availability of affordable and widely applicable interatomic potentials is the key needed to unlock the riches of modern materials modeling.Artificial neural network-based approaches for generating potentials are promising;however,neural network training requires large amounts of data,sampled adequately from an often unknown potential energy surface.Here we propose a selfconsistent approach that is based on crystal structure prediction formalism and is guided by unsupervised data analysis,to construct an accurate,inexpensive,and transferable artificial neural network potential.Using this approach,we construct an interatomic potential for carbon and demonstrate its ability to reproduce first principles results on elastic and vibrational properties for diamond,graphite,and graphene,as well as energy ordering and structural properties of a wide range of crystalline and amorphous phases.
