A novel approach to describe chemical environments in high-dimensional neural network potentials.

  title={A novel approach to describe chemical environments in high-dimensional neural network potentials.},
  author={Emir Kocer and Jeremy K. Mason and Hakan Erturk},
  journal={The Journal of chemical physics},
  volume={150 15},
A central concern of molecular dynamics simulations is the potential energy surfaces that govern atomic interactions. These hypersurfaces define the potential energy of the system and have generally been calculated using either predefined analytical formulas (classical) or quantum mechanical simulations (ab initio). The former can accurately reproduce only a selection of material properties, whereas the latter is restricted to short simulation times and small systems. Machine learning… Expand
11 Citations
Gaussian Moments as Physically Inspired Molecular Descriptors for Accurate and Scalable Machine Learning Potentials.
This work proposes a machine learning method for constructing high-dimensional potential energy surfaces based on feed-forward neural networks and proposes an extendable invariant local molecular descriptor constructed from geometric moments. Expand
Continuous and optimally complete description of chemical environments using Spherical Bessel descriptors
The Spherical Bessel descriptors have the advantage of allowing machine learning potentials of comparable accuracy that require roughly an order of magnitude less computation time per evaluation than the Smooth Overlap of Atomic Position descriptors, which appear to be the common choice of descriptors in recent studies. Expand
Fast and Sample-Efficient Interatomic Neural Network Potentials for Molecules and Materials Based on Gaussian Moments.
An improved NN architecture based on the previous GM-NN model is presented, which shows an improved prediction accuracy and considerably reduced training times and extends the applicability of Gaussian moment-based interatomic potentials to periodic systems and demonstrates the overall excellent transferability and robustness of the respective models. Expand
Strategies for the construction of machine-learning potentials for accurate and efficient atomic-scale simulations
Recent advances in machine-learning interatomic potentials have enabled the efficient modeling of complex atomistic systems with an accuracy that is comparable to that of conventionalExpand
Choosing the right molecular machine learning potential
This work evaluates the performance of popular machine learning potentials in terms of accuracy and computational cost, and delivers structured information for non-specialists in machine learning to guide them through the maze of acronyms, recognize each potential's main features, and judge what they could expect from each one. Expand
Machine learning accelerates quantum mechanics predictions of molecular crystals
Abstract Quantum mechanics (QM) approaches (DFT, MP2, CCSD(T), etc.) play an important role in calculating molecules and crystals with a high accuracy and acceptable efficiency. In recent years, withExpand
A bin and hash method for analyzing reference data and descriptors in machine learning potentials
The bin-and-hash (BAH) algorithm is presented, which is general and can be combined with any current type of MLP, to enable the efficient identification and comparison of large numbers of multidimensional vectors. Expand
Combining Machine Learning and Computational Chemistry for Predictive Insights Into Chemical Systems
A critical review of noteworthy applications that demonstrate how computational chemistry and machine learning can be used together to provide insightful predictions in molecular and materials modeling, retrosyntheses, catalysis, and drug design are reviewed. Expand
Closing the Gap Between Modeling and Experiments in the Self-Assembly of Biomolecules at Interfaces and in Solution
Molecular self-assembly is a powerful tool in materials design, wherein non-covalent interactions like electrostatic, hydrophobic, hydrogen bonding, and van der Waals can be exploited to produce su...
Choosing the right molecular machine learning potential
This article provides a lifeline for those lost in the sea of the molecular machine learning potentials by providing a balanced overview and evaluation of popular potentials.


Neural network potential-energy surfaces in chemistry: a tool for large-scale simulations.
  • J. Behler
  • Medicine
  • Physical chemistry chemical physics : PCCP
  • 2011
In this Perspective, the current status of NN potentials is reviewed, and their advantages and limitations are discussed. Expand
Ab initio potential-energy surfaces for complex, multichannel systems using modified novelty sampling and feedforward neural networks.
A neural network/trajectory approach is presented for the development of accurate potential-energy hypersurfaces that can be utilized to conduct ab initio molecular dynamics (AIMD) and Monte CarloExpand
High-dimensional neural network potentials for metal surfaces: A prototype study for copper
The atomic environments at metal surfaces differ strongly from the bulk, and, in particular, in case of reconstructions or imperfections at ``real surfaces,'' very complicated atomic configurationsExpand
A new approach to potential fitting using neural networks
Abstract A methodology is presented for developing transferable empirical potential functions without following the usual procedure of postulating a functional form. Instead, a neural network (NN) isExpand
Generalized neural-network representation of high-dimensional potential-energy surfaces.
A new kind of neural-network representation of DFT potential-energy surfaces is introduced, which provides the energy and forces as a function of all atomic positions in systems of arbitrary size and is several orders of magnitude faster than DFT. Expand
Constructing high-dimensional neural network potentials for molecular dynamics
A method for constructing analytic interatomic potentials by fitting artificial neural networks to data from molecular dynamics simulations by extending the LAMMPS distribution with an algorithm for sampling atomic configurations and energies is implemented. Expand
On representing chemical environments
We review some recently published methods to represent atomic neighborhood environments, and analyze their relative merits in terms of their faithfulness and suitability for fitting potential energyExpand
Neural network models of potential energy surfaces
Neural networks provide an efficient, general interpolation method for nonlinear functions of several variables. This paper describes the use of feed‐forward neural networks to model globalExpand
Comparing molecules and solids across structural and alchemical space.
This work discusses how one can combine such local descriptors using a regularized entropy match (REMatch) approach to describe the similarity of both whole molecular and bulk periodic structures, introducing powerful metrics that enable the navigation of alchemical and structural complexities within a unified framework. Expand
Machine learning based interatomic potential for amorphous carbon
We introduce a Gaussian approximation potential (GAP) for atomistic simulations of liquid and amorphous elemental carbon. Based on a machine learning representation of the density-functional theoryExpand