SIMPLE-NN: An efficient package for training and executing neural-network interatomic potentials

Abstract The molecular dynamics (MD) simulation is a favored method in materials science for understanding and predicting material properties from atomistic motions. In classical MD simulations, the interaction between atoms is described by an empirical interatomic potential, so the reliability of the simulation hinges on the accuracy of the underlying potential. Recently, machine learning (ML) based interatomic potentials are gaining attention as they can reproduce potential energy surfaces (PES) of a b i n i t i o calculations, with a much lower computational cost. Therefore, an efficient code for training ML potentials and inferencing PES in new configurations would widen the application range of MD simulations. Here, we announce an open-source package, SNU Interatomic Machine-learning PotentiaL packagE-version Neural Network (SIMPLE-NN) that generates and utilizes the ML potential based on the artificial neural network with the Behler–Parrinello type symmetry function as descriptors for the chemical environments. SIMPLE-NN uses the Atomic Simulation Environment (ASE) package and Google Tensorflow for high expandability and efficient training, and also supports the in-house code for quasi-Newton method. Notably, the package features a weighting scheme based on the Gaussian density function (GDF), which significantly improves accuracy and reliability of ML potentials by resolving sampling bias that exists in typical training sets. For MD simulations, SIMPLE-NN interfaces with the LAMMPS package. We demonstrate the performance and usage of SIMPLE-NN with examples of SiO2. Program summary Program Title: SIMPLE-NN Program Files doi: http://dx.doi.org/10.17632/pjv2yr7pvr.1 Licensing provisions: GPLv3 Programming language: Python/C++ Nature of problem: Inferencing the potential energy surface for the given system with accuracy comparable to ab initio methods but with much lower computational costs. Solution method: Calculate descriptor vectors that encode local chemical environment. High-dimensional neural network is used to predict the total energy from the descriptor vectors. The trained neural network can be used for molecular dynamics simulations.

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

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

[3]  Yizhou Zhu,et al.  Origin of fast ion diffusion in super-ionic conductors , 2017, Nature Communications.

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

[5]  W. Kohn,et al.  Self-Consistent Equations Including Exchange and Correlation Effects , 1965 .

[6]  Dongsun Yoo,et al.  All-atom simulation of molecular orientation in vapor-deposited organic light-emitting diodes , 2018 .

[7]  Steve Plimpton,et al.  Fast parallel algorithms for short-range molecular dynamics , 1993 .

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

[9]  Ericka Stricklin-Parker,et al.  Ann , 2005 .

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

[11]  Foiles,et al.  Embedded-atom-method functions for the fcc metals Cu, Ag, Au, Ni, Pd, Pt, and their alloys. , 1986, Physical review. B, Condensed matter.

[12]  W. Heisenberg,et al.  Zur Quantentheorie der Molekeln , 1924 .

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

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

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

[16]  Aditya Kamath,et al.  Neural networks vs Gaussian process regression for representing potential energy surfaces: A comparative study of fit quality and vibrational spectrum accuracy. , 2018, The Journal of chemical physics.

[17]  Alireza Khorshidi,et al.  Amp: A modular approach to machine learning in atomistic simulations , 2016, Comput. Phys. Commun..

[18]  Sudhir B. Kylasa,et al.  The ReaxFF reactive force-field: development, applications and future directions , 2016 .

[19]  G. G. Stokes.  "J." , 1890, The New Yale Book of Quotations.

[20]  Jacob R. Boes,et al.  Neural network predictions of oxygen interactions on a dynamic Pd surface , 2017 .

[21]  Jörg Behler,et al.  Concentration-Dependent Proton Transfer Mechanisms in Aqueous NaOH Solutions: From Acceptor-Driven to Donor-Driven and Back. , 2016, The journal of physical chemistry letters.

[22]  J. Behler.  Atom-centered symmetry functions for constructing high-dimensional neural network potentials. , 2011, The Journal of chemical physics.

[23]  Car,et al.  Unified approach for molecular dynamics and density-functional theory. , 1985, Physical review letters.

[24]  Dongheon Lee,et al.  Toward Reliable and Transferable Machine Learning Potentials: Uniform Training by Overcoming Sampling Bias , 2018, The Journal of Physical Chemistry C.

[25]  Kresse,et al.  Efficient iterative schemes for ab initio total-energy calculations using a plane-wave basis set. , 1996, Physical review. B, Condensed matter.

[26]  Nongnuch Artrith,et al.  An implementation of artificial neural-network potentials for atomistic materials simulations: Performance for TiO2 , 2016 .

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

[28]  Gang Su,et al.  Thermal conductivity of silicene calculated using an optimized Stillinger-Weber potential , 2014 .

[29]  Satoshi Watanabe,et al.  Study of Li atom diffusion in amorphous Li3PO4 with neural network potential. , 2017, The Journal of chemical physics.

[30]  Carlo Massobrio,et al.  Structure of amorphous GeSe9 by neutron diffraction and first-principles molecular dynamics: Impact of trajectory sampling and size effects. , 2016, The Journal of chemical physics.

[31]  Ekin D. Cubuk,et al.  Implanted neural network potentials: Application to Li-Si alloys , 2018 .

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

[33]  Jörg Behler,et al.  Neural network molecular dynamics simulations of solid-liquid interfaces: water at low-index copper surfaces. , 2016, Physical chemistry chemical physics : PCCP.

[34]  J. Tersoff,et al.  New empirical approach for the structure and energy of covalent systems. , 1988, Physical review. B, Condensed matter.

[35]  E Weinan,et al.  DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics , 2017, Comput. Phys. Commun..

[36]  Jörg Behler,et al.  Nuclear Quantum Effects in Sodium Hydroxide Solutions from Neural Network Molecular Dynamics Simulations. , 2018, The journal of physical chemistry. B.

[37]  Brian M. Foley,et al.  Thin Film Thermoelectric Metal–Organic Framework with High Seebeck Coefficient and Low Thermal Conductivity , 2015, Advanced materials.

[38]  Chandra Veer Singh,et al.  Metadynamics-Biased ab Initio Molecular Dynamics Study of Heterogeneous CO2 Reduction via Surface Frustrated Lewis Pairs , 2016 .

[39]  Stefano de Gironcoli,et al.  QUANTUM ESPRESSO: a modular and open-source software project for quantum simulations of materials , 2009, Journal of physics. Condensed matter : an Institute of Physics journal.

[40]  Alexie M. Kolpak,et al.  Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods , 2017, Scientific Reports.

[41]  Seungwu Han,et al.  Source of instability at the amorphous interface between InGaZnO 4 and SiO 2 : A theoretical investigation , 2015 .

[42]  Michael Walter,et al.  The atomic simulation environment-a Python library for working with atoms. , 2017, Journal of physics. Condensed matter : an Institute of Physics journal.

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

[44]  Jörg Behler,et al.  Atomistic Simulations of the Crystallization and Aging of GeTe Nanowires , 2017 .

[45]  Seungwu Han,et al.  An efficient method to generate amorphous structures based on local geometry , 2014 .

[46]  Jörg Behler,et al.  Proton-Transfer Mechanisms at the Water-ZnO Interface: The Role of Presolvation. , 2017, The journal of physical chemistry letters.

[47]  J S Smith,et al.  ANI-1: an extensible neural network potential with DFT accuracy at force field computational cost , 2016, Chemical science.