On machine learning force fields for metallic nanoparticles

ABSTRACT Machine learning algorithms have recently emerged as a tool to generate force fields which display accuracies approaching the ones of the ab-initio calculations they are trained on, but are much faster to compute. The enhanced computational speed of machine learning force fields results key for modelling metallic nanoparticles, as their fluxionality and multi-funneled energy landscape needs to be sampled over long time scales. In this review, we first formally introduce the most commonly used machine learning algorithms for force field generation, briefly outlining their structure and properties. We then address the core issue of training database selection, reporting methodologies both already used and yet unused in literature. We finally report and discuss the recent literature regarding machine learning force fields to sample the energy landscape and study the catalytic activity of metallic nanoparticles. Graphical abstract

[1]  S. Bulusu,et al.  c-T phase diagram and Landau free energies of (AgAu)55 nanoalloy via neural-network molecular dynamic simulations. , 2017, The Journal of chemical physics.

[2]  Gerbrand Ceder,et al.  Efficient and accurate machine-learning interpolation of atomic energies in compositions with many species , 2017, 1706.06293.

[3]  P. Erhart,et al.  Beyond Magic Numbers: Atomic Scale Equilibrium Nanoparticle Shapes for Any Size. , 2017, Nano letters.

[4]  H. Scheraga,et al.  Monte Carlo-minimization approach to the multiple-minima problem in protein folding. , 1987, Proceedings of the National Academy of Sciences of the United States of America.

[5]  J. Skilling.  Nested sampling for general Bayesian computation , 2006 .

[6]  Michele Ceriotti,et al.  Atom-density representations for machine learning. , 2018, The Journal of chemical physics.

[7]  Chang Q. Sun.  Size dependence of nanostructures: Impact of bond order deficiency , 2007 .

[8]  S. Bulusu,et al.  A transferable artificial neural network model for atomic forces in nanoparticles. , 2018, The Journal of chemical physics.

[9]  Volker L. Deringer,et al.  Machine learning based interatomic potential for amorphous carbon , 2016, 1611.03277.

[10]  Jonathan P. K. Doye,et al.  On potential energy surfaces and relaxation to the global minimum , 1996 .

[11]  Shweta Jindal,et al.  Neural network potentials for dynamics and thermodynamics of gold nanoparticles. , 2017, The Journal of chemical physics.

[12]  Rampi Ramprasad,et al.  Adaptive machine learning framework to accelerate ab initio molecular dynamics , 2015 .

[13]  Michael Fernandez,et al.  Identification of Nanoparticle Prototypes and Archetypes. , 2015, ACS nano.

[14]  Jeffrey C Grossman,et al.  Crystal Graph Convolutional Neural Networks for an Accurate and Interpretable Prediction of Material Properties. , 2017, Physical review letters.

[15]  Kohn,et al.  Density functional and density matrix method scaling linearly with the number of atoms. , 1996, Physical review letters.

[16]  First-principles determination of the structure of NaN and NaN- clusters with up to 80 atoms. , 2011, The Journal of chemical physics.

[17]  Kurt Hornik,et al.  Approximation capabilities of multilayer feedforward networks , 1991, Neural Networks.

[18]  R. Johnston,et al.  Global optimization of clusters using electronic structure methods , 2013 .

[19]  Gábor Csányi,et al.  Thermodynamics of CuPt nanoalloys , 2018, Scientific Reports.

[20]  G. Rossi,et al.  Searching for low-energy structures of nanoparticles: a comparison of different methods and algorithms , 2009, Journal of physics. Condensed matter : an Institute of Physics journal.

[21]  Michele Parrinello,et al.  Generalized neural-network representation of high-dimensional potential-energy surfaces. , 2007, Physical review letters.

[22]  Joanna Aizenberg,et al.  Probing Atomic Distributions in Mono- and Bimetallic Nanoparticles by Supervised Machine Learning. , 2018, Nano letters.

[23]  Yanchao Wang,et al.  Particle-swarm structure prediction on clusters. , 2012, The Journal of chemical physics.

[24]  Gábor Csányi,et al.  Gaussian approximation potentials: A brief tutorial introduction , 2015, 1502.01366.

[25]  David J. Wales,et al.  Kinetic analysis of discrete path sampling stationary point databases , 2006, cond-mat/0604165.

[26]  R. Palmer,et al.  Experimental evidence for fluctuating, chiral-type Au55 clusters by direct atomic imaging. , 2012, Nano letters (Print).

[27]  Rampi Ramprasad,et al.  Learning scheme to predict atomic forces and accelerate materials simulations , 2015, 1505.02701.

[28]  C. Noguez.  Surface Plasmons on Metal Nanoparticles: The Influence of Shape and Physical Environment , 2007 .

[29]  R. Johnston.  Evolving better nanoparticles: Genetic algorithms for optimising cluster geometries , 2003 .

[30]  Ole Winther,et al.  A Deep Learning Approach to Identify Local Structures in Atomic‐Resolution Transmission Electron Microscopy Images , 2018, Advanced Theory and Simulations.

[31]  Noam Bernstein,et al.  De novo exploration and self-guided learning of potential-energy surfaces , 2019, npj Computational Materials.

[32]  B. Cuenya.  Synthesis and catalytic properties of metal nanoparticles: Size, shape, support, composition, and oxidation state effects , 2010 .

[33]  Josh E. Campbell,et al.  Machine learning for the structure–energy–property landscapes of molecular crystals† †Electronic supplementary information (ESI) available. See DOI: 10.1039/c7sc04665k , 2017, Chemical science.

[34]  David J Wales,et al.  Comparison of double-ended transition state search methods. , 2007, The Journal of chemical physics.

[35]  Steven D. Brown,et al.  Neural network models of potential energy surfaces , 1995 .

[36]  Artem R Oganov,et al.  Method for Simultaneous Prediction of Atomic Structure and Stability of Nanoclusters in a Wide Area of Compositions. , 2018, The journal of physical chemistry letters.

[37]  Aldo Glielmo,et al.  Efficient nonparametric n -body force fields from machine learning , 2018, 1801.04823.

[38]  Peter Sollich,et al.  Accurate interatomic force fields via machine learning with covariant kernels , 2016, 1611.03877.

[39]  S. Bulusu,et al.  Modeling of DFT quality neural network potential for sodium clusters: Application to melting of sodium clusters (Na20 to Na40) , 2016 .

[40]  Guigang Zhang,et al.  Deep Learning , 2016, Int. J. Semantic Comput..

[41]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[42]  R. Ferrando,et al.  Experimental determination of the energy difference between competing isomers of deposited, size-selected gold nanoclusters , 2018, Nature Communications.

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

[44]  Kersti Hermansson,et al.  Representation of Intermolecular Potential Functions by Neural Networks , 1998 .

[45]  Jonathan Vandermause,et al.  On-the-fly active learning of interpretable Bayesian force fields for atomistic rare events , 2020, npj Computational Materials.

[46]  Matthias Rupp,et al.  Unified representation of molecules and crystals for machine learning , 2017, Mach. Learn. Sci. Technol..

[47]  Nathan S. Lewis,et al.  Machine-Learning Methods Enable Exhaustive Searches for Active Bimetallic Facets and Reveal Active Site Motifs for CO2 Reduction , 2017 .

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

[49]  K. Rossi,et al.  Metallic nanoparticles meet metadynamics. , 2015, The Journal of chemical physics.

[50]  Petros Drineas,et al.  CUR matrix decompositions for improved data analysis , 2009, Proceedings of the National Academy of Sciences.

[51]  Tejs Vegge,et al.  Genetic algorithms for computational materials discovery accelerated by machine learning , 2019, npj Computational Materials.

[52]  Geng Sun,et al.  Metastable Structures in Cluster Catalysis from First-Principles: Structural Ensemble in Reaction Conditions and Metastability Triggered Reactivity. , 2018, Journal of the American Chemical Society.

[53]  Alexie M. Kolpak,et al.  Grand canonical molecular dynamics simulations of Cu–Au nanoalloys in thermal equilibrium using reactive ANN potentials , 2015 .

[54]  Alessandro De Vita,et al.  Building Nonparametric n-Body Force Fields Using Gaussian Process Regression , 2019, Machine Learning Meets Quantum Physics.

[55]  Zhenwei Li,et al.  Molecular dynamics with on-the-fly machine learning of quantum-mechanical forces. , 2015, Physical review letters.

[56]  Giulia Rossi,et al.  Electronic and structural shell closure in AgCu and AuCu nanoclusters. , 2006, The journal of physical chemistry. B.

[57]  D. W. Noid,et al.  Potential energy surfaces for macromolecules. A neural network technique , 1992 .

[58]  Chris J. Pickard,et al.  Hyperspatial optimization of structures , 2019, Physical Review B.

[59]  Yu Xie,et al.  Global minimization of gold clusters by combining neural network potentials and the basin-hopping method. , 2015, Nanoscale.

[60]  Geoffrey E. Hinton,et al.  Bayesian Learning for Neural Networks , 1995 .

[61]  A. Laio,et al.  Metadynamics: a method to simulate rare events and reconstruct the free energy in biophysics, chemistry and material science , 2008 .

[62]  Michael Gastegger,et al.  Molecular Dynamics with Neural Network Potentials , 2018, Machine Learning Meets Quantum Physics.

[63]  Michele Ceriotti,et al.  Recognizing Local and Global Structural Motifs at the Atomic Scale. , 2018, Journal of chemical theory and computation.

[64]  D. Wales,et al.  Grand and Semigrand Canonical Basin-Hopping , 2015, Journal of chemical theory and computation.

[65]  Jörg Behler,et al.  Automatic selection of atomic fingerprints and reference configurations for machine-learning potentials. , 2018, The Journal of chemical physics.

[66]  Adam S. Foster,et al.  Machine learning hydrogen adsorption on nanoclusters through structural descriptors , 2018, npj Computational Materials.

[67]  F. Baletto,et al.  Structural properties of nanoclusters: Energetic, thermodynamic, and kinetic effects , 2005 .

[68]  Nongnuch Artrith,et al.  High-dimensional neural network potentials for metal surfaces: A prototype study for copper , 2012 .

[69]  Scott M Woodley,et al.  An efficient genetic algorithm for structure prediction at the nanoscale. , 2017, Nanoscale.

[70]  Nicola Gaston,et al.  Building machine learning force fields for nanoclusters. , 2018, The Journal of chemical physics.

[71]  D. Lu,et al.  Supervised Machine-Learning-Based Determination of Three-Dimensional Structure of Metallic Nanoparticles. , 2017, The journal of physical chemistry letters.

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

[73]  Nongnuch Artrith,et al.  Understanding the composition and activity of electrocatalytic nanoalloys in aqueous solvents: a combination of DFT and accurate neural network potentials. , 2014, Nano letters.

[74]  Christian Trott,et al.  Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials , 2014, J. Comput. Phys..

[75]  Nongnuch Artrith,et al.  Neural network potentials for metals and oxides – First applications to copper clusters at zinc oxide , 2013 .

[76]  Huanchen Zhai,et al.  Ensemble-Average Representation of Pt Clusters in Conditions of Catalysis Accessed through GPU Accelerated Deep Neural Network Fitting Global Optimization. , 2016, Journal of chemical theory and computation.

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

[78]  Amanda S Barnard,et al.  Predicting archetypal nanoparticle shapes using a combination of thermodynamic theory and machine learning. , 2018, Nanoscale.

[79]  Jordan Dorrell,et al.  Thermodynamics and the potential energy landscape: case study of small water clusters. , 2019, Physical chemistry chemical physics : PCCP.

[80]  R. Johnston,et al.  Nanoalloys: from theory to applications of alloy clusters and nanoparticles. , 2008, Chemical reviews.

[81]  Isaac Tamblyn,et al.  Convolutional neural networks for atomistic systems , 2017, Computational Materials Science.

[82]  S. Hajinazar,et al.  Multitribe evolutionary search for stable Cu-Pd-Ag nanoparticles using neural network models. , 2019, Physical chemistry chemical physics : PCCP.

[83]  Chad A Mirkin,et al.  Gold nanoparticles for biology and medicine. , 2010, Angewandte Chemie.

[84]  N. Turner,et al.  Biocatalytic desymmetrization of an atropisomer with both an enantioselective oxidase and ketoreductases. , 2010, Angewandte Chemie.

[85]  Joonhee Kang,et al.  First-principles database driven computational neural network approach to the discovery of active ternary nanocatalysts for oxygen reduction reaction. , 2018, Physical chemistry chemical physics : PCCP.

[86]  C. Catlow,et al.  Controlling Structural Transitions in AuAg Nanoparticles through Precise Compositional Design. , 2016, The journal of physical chemistry letters.

[87]  K-R Müller,et al.  SchNet - A deep learning architecture for molecules and materials. , 2017, The Journal of chemical physics.

[88]  Ryosuke Jinnouchi,et al.  Extrapolating Energetics on Clusters and Single-Crystal Surfaces to Nanoparticles by Machine-Learning Scheme , 2017 .

[89]  A. Laio,et al.  Escaping free-energy minima , 2002, Proceedings of the National Academy of Sciences of the United States of America.

[90]  Ryosuke Jinnouchi,et al.  Predicting Catalytic Activity of Nanoparticles by a DFT-Aided Machine-Learning Algorithm. , 2017, The journal of physical chemistry letters.

[91]  K. Rossi,et al.  The effect of chemical ordering and lattice mismatch on structural transitions in phase segregating nanoalloys. , 2017, Physical chemistry chemical physics : PCCP.

[92]  Jonathan Doye,et al.  Global minima for transition metal clusters described by Sutton–Chen potentials , 1997 .

[93]  K. Rossi,et al.  A genomic characterisation of monometallic nanoparticles. , 2018, Physical chemistry chemical physics : PCCP.

[94]  Bjørk Hammer,et al.  Neural-network-enhanced evolutionary algorithm applied to supported metal nanoparticles , 2018 .

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

[96]  Jonathan Vandermause,et al.  On-the-Fly Bayesian Active Learning of Interpretable Force-Fields for Atomistic Rare Events , 2019 .

[97]  Cormac Toher,et al.  Universal fragment descriptors for predicting properties of inorganic crystals , 2016, Nature Communications.