Machine-learned interatomic potentials for alloys and alloy phase diagrams

We introduce machine-learned potentials for Ag-Pd to describe the energy of alloy configurations over a wide range of compositions. We compare two different approaches. Moment tensor potentials (MTPs) are polynomial-like functions of interatomic distances and angles. The Gaussian approximation potential (GAP) framework uses kernel regression, and we use the smooth overlap of atomic position (SOAP) representation of atomic neighborhoods that consist of a complete set of rotational and permutational invariants provided by the power spectrum of the spherical Fourier transform of the neighbor density. Both types of potentials give excellent accuracy for a wide range of compositions, competitive with the accuracy of cluster expansion, a benchmark for this system. While both models are able to describe small deformations away from the lattice positions, SOAP-GAP excels at transferability as shown by sensible transformation paths between configurations, and MTP allows, due to its lower computational cost, the calculation of compositional phase diagrams. Given the fact that both methods perform nearly as well as cluster expansion but yield off-lattice models, we expect them to open new avenues in computational materials modeling for alloys.

[1]  J. Sopoušek,et al.  Experimental determination of phase equilibria and reassessment of Ag–Pd system , 2010 .

[2]  Tomi Laurila,et al.  Reactivity of Amorphous Carbon Surfaces: Rationalizing the Role of Structural Motifs in Functionalization Using Machine Learning , 2018, Chemistry of materials : a publication of the American Chemical Society.

[3]  Mark A. Rodriguez,et al.  Behavior of Silver and Palladium Mixtures during Heating , 2004 .

[4]  A. Darling.  Some Properties and Applications of the Platinum-Group Metals , 1973 .

[5]  Volker L. Deringer,et al.  Understanding the thermal properties of amorphous solids using machine-learning-based interatomic potentials , 2018 .

[6]  A. Shapeev,et al.  Improving accuracy of interatomic potentials: more physics or more data? A case study of silica , 2018, Materials Today Communications.

[7]  Axel van de Walle,et al.  Prediction of the material with highest known melting point from ab initio molecular dynamics calculations , 2015 .

[8]  D. Alfé,et al.  Melting curve of face-centred-cubic nickel from first principles calculations , 2013, 1307.4061.

[9]  Gábor Csányi,et al.  Comparing molecules and solids across structural and alchemical space. , 2015, Physical chemistry chemical physics : PCCP.

[10]  S. Naidu,et al.  X‐Ray Determinations of the Debye Temperatures and Thermal Expansions for the Pd–Ag–Au System , 1971 .

[11]  D. Fruchart,et al.  A high pressure investigation of Pd and the Pd–H system , 1999 .

[12]  K. Müller,et al.  Fast and accurate modeling of molecular atomization energies with machine learning. , 2011, Physical review letters.

[13]  P. Rao,et al.  X‐Ray Measurements of Faulting in Ag–Pd Alloys , 1968 .

[14]  G. B. Olson,et al.  Thermodynamic modeling of the Pd-X(X= Ag, Co, Fe, Ni) systems , 1999 .

[15]  Volker L. Deringer,et al.  Extracting Crystal Chemistry from Amorphous Carbon Structures , 2017, Chemphyschem : a European journal of chemical physics and physical chemistry.

[16]  M. Payne,et al.  Determining pressure-temperature phase diagrams of materials , 2015, 1503.03404.

[17]  Cas van der Oord,et al.  Regularised atomic body-ordered permutation-invariant polynomials for the construction of interatomic potentials , 2019, Mach. Learn. Sci. Technol..

[18]  Technology,et al.  Moment tensor potentials as a promising tool to study diffusion processes , 2018, Computational Materials Science.

[19]  Gus L. W. Hart,et al.  A robust algorithm for $k$-point grid generation and symmetry reduction. , 2018 .

[20]  Gábor Csányi,et al.  Constant-pressure nested sampling with atomistic dynamics. , 2017, Physical review. E.

[21]  W. T. Thompson,et al.  The Ag Pd Silver Palladium System , 1988 .

[22]  Gábor Csányi,et al.  Efficient sampling of atomic configurational spaces. , 2009, The journal of physical chemistry. B.

[23]  Gus L. W. Hart,et al.  Algorithm for Generating Derivative Structures , 2008 .

[24]  Paul L. A. Popelier,et al.  Polarisable multipolar electrostatics from the machine learning method Kriging: an application to alanine , 2012, Theoretical Chemistry Accounts.

[25]  Alex Brown,et al.  Classical and quasiclassical spectral analysis of CH5+ using an ab initio potential energy surface , 2003 .

[26]  Alexander V. Shapeev,et al.  Active learning of linearly parametrized interatomic potentials , 2016, 1611.09346.

[27]  Christoph Ortner,et al.  Atomic permutationally invariant polynomials for fitting molecular force fields , 2020, Mach. Learn. Sci. Technol..

[28]  Gábor Csányi,et al.  Accuracy and transferability of Gaussian approximation potential models for tungsten , 2014 .

[29]  Noam Bernstein,et al.  Modeling the Phase-Change Memory Material, Ge2Sb2Te5, with a Machine-Learned Interatomic Potential. , 2018, The journal of physical chemistry. B.

[30]  H. Monkhorst,et al.  SPECIAL POINTS FOR BRILLOUIN-ZONE INTEGRATIONS , 1976 .

[31]  A. Zunger,et al.  First-principles predictions of yet-unobserved ordered structures in the Ag-Pd phase diagram. , 2001, Physical review letters.

[32]  William A. Curtin,et al.  Screw dislocation structure and mobility in body centered cubic Fe predicted by a Gaussian Approximation Potential , 2018, npj Computational Materials.

[33]  Pekka Taskinen,et al.  Thermodynamic properties of silver–palladium alloys determined by a solid state electrochemical method , 2014, Journal of Materials Science.

[34]  Michael A. Collins,et al.  Multi-dimensional potential energy surface determination by modified Shepard interpolation for a molecule–surface reaction: H2+Pt(111) , 2003 .

[35]  Andreas Ziehe,et al.  Learning Invariant Representations of Molecules for Atomization Energy Prediction , 2012, NIPS.

[36]  Alexander V. Shapeev,et al.  Accelerating crystal structure prediction by machine-learning interatomic potentials with active learning , 2018, Physical Review B.

[37]  Volker L. Deringer,et al.  Data-Driven Learning of Total and Local Energies in Elemental Boron. , 2017, Physical review letters.

[38]  D. Chadi,et al.  Special points for Brillouin-zone integrations , 1977 .

[39]  G. Kresse,et al.  Efficiency of ab-initio total energy calculations for metals and semiconductors using a plane-wave basis set , 1996 .

[40]  Gabor Csanyi,et al.  Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron , 2017, 1706.10229.

[41]  G. Kresse,et al.  From ultrasoft pseudopotentials to the projector augmented-wave method , 1999 .

[42]  Blöchl,et al.  Projector augmented-wave method. , 1994, Physical review. B, Condensed matter.

[43]  A. Gross,et al.  Representing high-dimensional potential-energy surfaces for reactions at surfaces by neural networks , 2004 .

[44]  Hafner,et al.  Ab initio molecular-dynamics simulation of the liquid-metal-amorphous-semiconductor transition in germanium. , 1994, Physical review. B, Condensed matter.

[45]  Gus L. W. Hart,et al.  Generating derivative structures: Algorithm and applications , 2008, 0804.3544.

[46]  G. Bond,et al.  The Structure and Catalytic Properties of Palladium-Silver and Palladium-Gold Alloys , 1972 .

[47]  Volker L. Deringer,et al.  Data-driven learning and prediction of inorganic crystal structures. , 2018, Faraday discussions.

[48]  M. Gillan,et al.  Melting curve of tantalum from first principles , 2007 .

[49]  Markus Bachmayr,et al.  Atomic Cluster Expansion: Completeness, Efficiency and Stability , 2019 .

[50]  Gus L. W. Hart,et al.  Accelerating high-throughput searches for new alloys with active learning of interatomic potentials , 2018, Computational Materials Science.

[51]  G. Kresse,et al.  Ab initio molecular dynamics for liquid metals. , 1993 .

[52]  Sanguthevar Rajasekaran,et al.  Accelerating materials property predictions using machine learning , 2013, Scientific Reports.

[53]  A M Russell,et al.  Science and technology. , 1972, Science.

[54]  Conrad W. Rosenbrock,et al.  Robustness of the cluster expansion: Assessing the roles of relaxation and numerical error , 2017, 1701.03080.

[55]  George C. Schatz,et al.  A local interpolation scheme using no derivatives in quantum-chemical calculations , 1999 .

[56]  Ivano Tavernelli,et al.  Optimization of effective atom centered potentials for london dispersion forces in density functional theory. , 2004, Physical review letters.

[57]  Noam Bernstein,et al.  Machine Learning a General-Purpose Interatomic Potential for Silicon , 2018, Physical Review X.

[58]  Klaus-Robert Müller,et al.  Assessment and Validation of Machine Learning Methods for Predicting Molecular Atomization Energies. , 2013, Journal of chemical theory and computation.

[59]  B. Johansson,et al.  Theoretical investigation of bulk ordering and surface segregation in Ag-Pd and other isoelectornic alloys , 2007 .

[60]  Tim Mueller,et al.  Efficient generation of generalized Monkhorst-Pack grids through the use of informatics , 2016 .

[61]  K. Terakura,et al.  Electronic theory for phase stability of nine AB binary alloys, with A=Ni, Pd, or Pt and B=Cu, Ag, or Au. , 1989, Physical review. B, Condensed matter.

[62]  Conrad W. Rosenbrock,et al.  Machine-learned multi-system surrogate models for materials prediction , 2018, npj Computational Materials.

[63]  Eric R. Homer,et al.  Discovering the building blocks of atomic systems using machine learning: application to grain boundaries , 2017, npj Computational Materials.

[64]  H. Flandorfer,et al.  Enthalpies of mixing of metallic systems relevant for lead-free soldering: Ag–Pd and Ag–Pd–Sn , 2005 .

[65]  Ralf Drautz,et al.  Atomic cluster expansion for accurate and transferable interatomic potentials , 2019, Physical Review B.

[66]  Felix A Faber,et al.  Crystal structure representations for machine learning models of formation energies , 2015, 1503.07406.

[67]  F. Brouers,et al.  On the temperature dependence of electrical resistivit in concentrated disordered transition binary alloys , 1975 .

[68]  Noam Bernstein,et al.  Machine learning unifies the modeling of materials and molecules , 2017, Science Advances.

[69]  Lance J. Nelson,et al.  Ground-state characterizations of systems predicted to exhibit L11 or L13 crystal structures , 2012 .

[70]  Burke,et al.  Generalized Gradient Approximation Made Simple. , 1996, Physical review letters.

[71]  Gábor Csányi,et al.  Modeling Molecular Interactions in Water: From Pairwise to Many-Body Potential Energy Functions , 2016, Chemical reviews.

[72]  E. Glandt,et al.  Nearly monodisperse fluids. I. Monte Carlo simulations of Lennard‐Jones particles in a semigrand ensemble , 1987 .

[73]  M. Hasebe,et al.  Thermodynamic Constraints to Describe Gibbs Energies for Binary Alloys , 1999 .

[74]  Atsuto Seko,et al.  Group-theoretical high-order rotational invariants for structural representations: Application to linearized machine learning interatomic potential , 2019, Physical Review B.

[75]  Alexander V. Shapeev,et al.  Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials , 2015, Multiscale Model. Simul..

[76]  Gábor Csányi,et al.  Many-Body Coarse-Grained Interactions Using Gaussian Approximation Potentials. , 2016, The journal of physical chemistry. B.

[77]  Jörg Behler,et al.  Next generation interatomic potentials for condensed systems , 2014 .

[78]  R. Kondor,et al.  Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons. , 2009, Physical review letters.

[79]  R. Kondor,et al.  On representing chemical environments , 2012, 1209.3140.

[80]  Hafner,et al.  Ab initio molecular dynamics for liquid metals. , 1995, Physical review. B, Condensed matter.

[81]  A. Shapeev,et al.  Automated calculation of thermal rate coefficients using ring polymer molecular dynamics and machine-learning interatomic potentials with active learning. , 2018, Physical chemistry chemical physics : PCCP.

[82]  George Malcolm Stocks,et al.  First-Principles Calculations of Cluster Densities of States and Short-Range Order in Ag c Pd 1-c Alloys , 1983 .

[83]  M. Ellner.  Partial atomic volume and partial molar enthalpy of formation of the 3d metals in the palladium-based solid solutions , 2004 .