Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon

@article{Lysogorskiy2021PerformantIO,
  title={Performant implementation of the atomic cluster expansion (PACE) and application to copper and silicon},
  author={Yury Lysogorskiy and Cas van der Oord and A. V. Bochkarev and Sarath Menon and Matteo Rinaldi and Thomas Hammerschmidt and Matous Mrovec and Aidan Thompson and G{\'a}bor Cs{\'a}nyi and Christoph Ortner and Ralf Drautz},
  journal={npj Computational Materials},
  year={2021},
  volume={7},
  pages={1-12}
}
The atomic cluster expansion is a general polynomial expansion of the atomic energy in multi-atom basis functions. Here we implement the atomic cluster expansion in the performant C++ code PACE that is suitable for use in large-scale atomistic simulations. We briefly review the atomic cluster expansion and give detailed expressions for energies and forces as well as efficient algorithms for their evaluation. We demonstrate that the atomic cluster expansion as implemented in PACE shifts a… 
Linear Atomic Cluster Expansion Force Fields for Organic Molecules: beyond RMSE
We demonstrate that accurate linear force fields can be built using the Atomic Cluster Ex- pansion (ACE) framework for molecules. Our model is built from body ordered symmetric polynomials which
Linear Atomic Cluster Expansion Force Fields for Organic Molecules: beyond RMSE
We demonstrate that accurate linear force fields can be built using the Atomic Cluster Expansion (ACE) framework for molecules. Our model is built from body ordered symmetric polynomials which makes
Linear Atomic Cluster Expansion Force Fields for Organic Molecules: Beyond RMSE
TLDR
It is demonstrated that fast and accurate linear force fields can be built for molecules using the atomic cluster expansion (ACE) framework, and the four- or five-body ACE force fields improve on the accuracy of the empirical force fields by up to a factor of 10, reaching the accuracy typical of recently proposed machine-learning-based approaches.
KLIFF: A framework to develop physics-based and machine learning interatomic potentials
TLDR
The KIM-based learning-integrated fitting framework (KLIFF), a package that facilitates the entire IP development process, is introduced and demonstrated by fitting a physics-based Stillinger–Weber potential and a machine learning neural network potential for silicon.
Machine-learning potentials enable predictive and tractable high-throughput screening of random alloys
We present an automated procedure for computing stacking fault energies in random alloys from large-scale simulations using moment tensor potentials (MTPs) with the accuracy of density functional
Ultra-fast interpretable machine-learning potentials
All-atom dynamics simulations are an indispensable quantitative tool in physics, chemistry, and materials science, but large systems and long simulation times remain challenging due to the trade-off
Exploring the necessary complexity of interatomic potentials
TLDR
It is demonstrated that high model complexities may not be strictly necessary in order to achieve near-DFT accuracy in interatomic potentials and an alternative route towards sampling the high accuracy, low complexity region of model space is suggested by starting with forms that promote simpler and more interpretable inter atomic potentials.
Equivariant analytical mapping of first principles Hamiltonians to accurate and transferable materials models
We propose a data-driven scheme to construct predictive models for Hamiltonian and overlap matrices in atomic orbital representation from ab initio data as a function of local atomic and bond
Automated free-energy calculation from atomistic simulations
We devise automated workflows for the calculation of Helmholtz and Gibbs free energies and their temperature and pressure dependence and provide the corresponding computational tools. We employ
Gaussian Process Regression for Materials and Molecules
TLDR
The focus of the present review is on the regression of atomistic properties: in particular, on the construction of interatomic potentials in the Gaussian Approximation Potential (GAP) framework; beyond this, the fitting of arbitrary scalar, vectorial, and tensorial quantities is discussed.
...
1
2
...

References

SHOWING 1-10 OF 80 REFERENCES
Atomic cluster expansion: Completeness, efficiency and stability
TLDR
A fast recursive algorithm is provided for efficient evaluation of the derivation of polynomial basis functions for approximating isometry and permutation invariant functions, particularly with an eye to modelling properties of atomistic systems.
Quantum-accurate spectral neighbor analysis potential models for Ni-Mo binary alloys and fcc metals
In recent years, efficient interatomic potentials approaching the accuracy of density functional theory (DFT) calculations have been developed using rigorous atomic descriptors satisfying strict
A Performance and Cost Assessment of Machine Learning Interatomic Potentials.
TLDR
A comprehensive evaluation of ML-IAPs based on four local environment descriptors --- atom-centered symmetry functions (ACSF), smooth overlap of atomic positions (SOAP), the Spectral Neighbor Analysis Potential (SNAP) bispectrum components, and moment tensors --- using a diverse data set generated using high-throughput density functional theory (DFT) calculations.
Regularised atomic body-ordered permutation-invariant polynomials for the construction of interatomic potentials
TLDR
It is shown that the low dimensionality combined with careful regularisation actually leads to better transferability than the high dimensional, kernel based Gaussian Approximation Potential.
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
Atom-centered symmetry functions for constructing high-dimensional neural network potentials.
  • J. Behler
  • Physics, Medicine
    The Journal of chemical physics
  • 2011
TLDR
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.
Efficient O(N) integration for all-electron electronic structure calculation using numeric basis functions
TLDR
It is shown that a conceptually simple top-down grid partitioning scheme achieves essentially the same efficiency as the more rigorous bottom-up approaches.
Generalized neural-network representation of high-dimensional potential-energy surfaces.
TLDR
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.
Structural stability and lattice defects in copper: Ab initio , tight-binding, and embedded-atom calculations
We evaluate the ability of the embedded-atom method ~EAM! potentials and the tight-binding ~TB! method to predict reliably energies and stability of nonequilibrium structures by taking Cu as a model
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 energy
...
1
2
3
4
5
...