The atomic cluster expansion is a general polynomial expansion of the atomic energy in multi-atom basis functions.Here we implement the atomic cluster expansion in the performant C++code PACE that is suitable for use ...The atomic cluster expansion is a general polynomial expansion of the atomic energy in multi-atom basis functions.Here we implement the atomic cluster expansion in the performant C++code PACE that is suitable for use in large-scale atomistic simulations.We briefly review the atomic cluster expansion and give detailed expressions for energies and forces as well as efficient algorithms for their evaluation.We demonstrate that the atomic cluster expansion as implemented in PACE shifts a previously established Pareto front for machine learning interatomic potentials toward faster and more accurate calculations.Moreover,general purpose parameterizations are presented for copper and silicon and evaluated in detail.We show that the Cu and Si potentials significantly improve on the best available potentials for highly accurate large-scale atomistic simulations.展开更多
The Atomic Cluster Expansion(ACE)provides a formally complete basis for the local atomic environment.ACE is not limited to representing energies as a function of atomic positions and chemical species,but can be genera...The Atomic Cluster Expansion(ACE)provides a formally complete basis for the local atomic environment.ACE is not limited to representing energies as a function of atomic positions and chemical species,but can be generalized to vectorial or tensorial properties and to incorporate further degrees of freedom(DOF).This is crucial for magnetic materials with potential energy surfaces that depend on atomic positions and atomic magnetic moments simultaneously.In this work,we employ the ACE formalism to develop a non-collinear magnetic ACE parametrization for the prototypical magnetic element Fe.The model is trained on a broad range of collinear and non-collinear magnetic structures calculated using spin density functional theory.We demonstrate that the non-collinear magnetic ACE is able to reproduce not only ground state properties of various magnetic phases of Fe but also the magnetic and lattice excitations that are essential for a correct description of finite temperature behavior and properties of crystal defects.展开更多
We present a comprehensive and user-friendly framework built upon the pyiron integrated development environment(IDE),enabling researchers to perform the entire Machine Learning Potential(MLP)development cycle consisti...We present a comprehensive and user-friendly framework built upon the pyiron integrated development environment(IDE),enabling researchers to perform the entire Machine Learning Potential(MLP)development cycle consisting of(i)creating systematic DFT databases,(ii)fitting the Density Functional Theory(DFT)data to empirical potentials orMLPs,and(iii)validating the potentials in a largely automatic approach.The power and performance of this framework are demonstrated for three conceptually very different classes of interatomic potentials:an empirical potential(embedded atom method-EAM),neural networks(high-dimensional neural network potentials-HDNNP)and expansions in basis sets(atomic cluster expansion-ACE).As an advanced example for validation and application,we show the computation of a binary composition-temperature phase diagram for Al-Li,a technologically important lightweight alloy system with applications in the aerospace industry.展开更多
基金The authors acknowledge helpful discussions with Marc Cawkwell.R.D.acknowledges funding through the German Science Foundation(DFG),project number 405621217Sandia National Laboratories is a multimission laboratory managed and operated by National Technology&Engineering Solutions of Sandia,LLC,a wholly owned subsidiary of Honeywell International Inc.,for the U.S.Department of Energy’s National Nuclear Security Administration under contract DE-NA0003525.
文摘The atomic cluster expansion is a general polynomial expansion of the atomic energy in multi-atom basis functions.Here we implement the atomic cluster expansion in the performant C++code PACE that is suitable for use in large-scale atomistic simulations.We briefly review the atomic cluster expansion and give detailed expressions for energies and forces as well as efficient algorithms for their evaluation.We demonstrate that the atomic cluster expansion as implemented in PACE shifts a previously established Pareto front for machine learning interatomic potentials toward faster and more accurate calculations.Moreover,general purpose parameterizations are presented for copper and silicon and evaluated in detail.We show that the Cu and Si potentials significantly improve on the best available potentials for highly accurate large-scale atomistic simulations.
基金supported by the German Science Foundation(DFG),projects 405621081,405621217,and 403582885.
文摘The Atomic Cluster Expansion(ACE)provides a formally complete basis for the local atomic environment.ACE is not limited to representing energies as a function of atomic positions and chemical species,but can be generalized to vectorial or tensorial properties and to incorporate further degrees of freedom(DOF).This is crucial for magnetic materials with potential energy surfaces that depend on atomic positions and atomic magnetic moments simultaneously.In this work,we employ the ACE formalism to develop a non-collinear magnetic ACE parametrization for the prototypical magnetic element Fe.The model is trained on a broad range of collinear and non-collinear magnetic structures calculated using spin density functional theory.We demonstrate that the non-collinear magnetic ACE is able to reproduce not only ground state properties of various magnetic phases of Fe but also the magnetic and lattice excitations that are essential for a correct description of finite temperature behavior and properties of crystal defects.
基金The workflows,potentials,and results presented here were obtained in the framework of the POTENTIALS collaboration and scientific network“Assessment of atomistic simulations”with funding from the German Science Foundation(DFG)(grant number 405602047)S.M.acknowledges funding by the Deutsche Forschungsgemeinschaft(DFG,German Research Foundation)under the National Research Data Infrastructure-NFDI 38/1-project number 460247524+5 种基金J.B.acknowledges funding by the DFG(project number 405479457 as part of PAK 965/1)A.K.acknowledges funding by the Studienstiftung des Deutschen Volkes(doctoral scholarship)N.L.and J.R.acknowledge funding by the Deutsche Forschungsgemeinschaft(DFG,German Research Foundation)under grant number 405621137K.A.acknowledges funding from the the DFG undergrant number 405621160M.M.and R.D.acknowledge funding by the German Science Foundation(DFG),projects 405621081 and 405621217.R.D.and Y.L.acknowledge computation time by Center for Interface-Dominated High Performance Materials(ZGH)at Ruhr-Universität Bochum,GermanyJ.J.and J.N.acknowledge funding by the DFG under grant number 405621217.M.P.and J.N.acknowledge funding from the DFG under grant number 405621160.
文摘We present a comprehensive and user-friendly framework built upon the pyiron integrated development environment(IDE),enabling researchers to perform the entire Machine Learning Potential(MLP)development cycle consisting of(i)creating systematic DFT databases,(ii)fitting the Density Functional Theory(DFT)data to empirical potentials orMLPs,and(iii)validating the potentials in a largely automatic approach.The power and performance of this framework are demonstrated for three conceptually very different classes of interatomic potentials:an empirical potential(embedded atom method-EAM),neural networks(high-dimensional neural network potentials-HDNNP)and expansions in basis sets(atomic cluster expansion-ACE).As an advanced example for validation and application,we show the computation of a binary composition-temperature phase diagram for Al-Li,a technologically important lightweight alloy system with applications in the aerospace industry.
