Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials

  title={Moment Tensor Potentials: A Class of Systematically Improvable Interatomic Potentials},
  author={Alexander V. Shapeev},
  journal={Multiscale Model. Simul.},
  • A. Shapeev
  • Published 18 December 2015
  • Physics
  • Multiscale Model. Simul.
Density functional theory offers a very accurate way of computing materials properties from first principles. However, it is too expensive for modelling large-scale molecular systems whose properties are, in contrast, computed using interatomic potentials. The present paper considers, from a mathematical point of view, the problem of constructing interatomic potentials that approximate a given quantum-mechanical interaction model. In particular, a new class of systematically improvable… 

Figures and Tables from this paper

Machine-Learning Interatomic Potentials for Materials Science
Large-scale atomistic computer simulations of materials rely on interatomic potentials providing computationally efficient predictions of energy and Newtonian forces. Traditional potentials have
Machine learned interatomic potentials using random features
The proposed model approximates the energy/forces using a linear combination of random features, thereby enabling fast parameter estimation by solving a linear least-squares problem and addressing scalability issues encountered in this class of machine learning problems.
Moment tensor potentials as a promising tool to study diffusion processes
’ s Choice Moment tensor potentials as a promising tool to study di ff usion processes
A recently proposed class of machine-learning interatomic potentials—Moment tensor potentials (MTPs)—is investigated in this work. MTPs are able to actively select configurations and parametrize the
Active learning of linearly parametrized interatomic potentials
Magnetic Moment Tensor Potentials for collinear spin-polarized materials reproduce different magnetic states of bcc Fe
We present the magnetic Moment Tensor Potentials (mMTPs), a class of machine-learning interatomic potentials, accurately reproducing both vibrational and magnetic degrees of freedom as provided,
Multi-scale approach for the prediction of atomic scale properties
This paper presents several examples that range from molecular physics to surface science and biophysics, demonstrating the ability of this multi-scale approach to model interactions driven by electrostatics, polarization and dispersion, as well as the cooperative behavior of dielectric response functions.
Machine Learning a General-Purpose Interatomic Potential for Silicon
The success of first principles electronic structure calculation for predictive modeling in chemistry, solid state physics, and materials science is constrained by the limitations on simulated length


Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons.
We introduce a class of interatomic potential models that can be automatically generated from data consisting of the energies and forces experienced by atoms, as derived from quantum mechanical
Permutationally invariant potential energy surfaces in high dimensionality
We review recent progress in developing potential energy and dipole moment surfaces for polyatomic systems with up to 10 atoms. The emphasis is on global linear least squares fitting of tens of
First principles interatomic potential for tungsten based on Gaussian process regression
An accurate description of atomic interactions, such as that provided by first principles quantum mechanics, is fundamental to realistic prediction of the properties that govern plasticity, fracture
Interatomic Forces in Condensed Matter
I: THE FRAMEWORK 1. Essential quantum mechanics 2. Essential density functional theory 3. Exploiting the variational principle 4. Linear response theory II: MODELLING ATOMS WITHIN SOLIDS 5. Testing
Atom-centered symmetry functions for constructing high-dimensional neural network potentials.
  • J. Behler
  • Computer Science
    The Journal of chemical physics
  • 2011
Neural networks offer an unbiased and numerically very accurate approach to represent high-dimensional ab initio potential-energy surfaces and a transformation to symmetry functions is required to enable molecular dynamics simulations of large systems.
Slave mode expansion for obtaining ab initio interatomic potentials
Here we propose an approach for performing a Taylor series expansion of the first-principles computed energy of a crystal as a function of the nuclear displacements. We enlarge the dimensionality of
Computational quantum chemistry: A primer
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.
Accuracy and transferability of Gaussian approximation potential models for tungsten
We introduce interatomic potentials for tungsten in the bcc crystal phase and its defects within the Gaussian approximation potential framework, fitted to a database of first-principles density