Spectral neighbor analysis method for automated generation of quantum-accurate interatomic potentials

By Aidan P. Thompson, Laura Painton Swiler, Christian Robert Trott, S. Foiles, Garritt J. Tucker. 2014

1,032 citations recorded by the source corpus.

We present a new interatomic potential for solids and liquids called Spectral Neighbor Analysis Potential (SNAP). The SNAP potential has a very general form and uses machine-learning techniques to reproduce the energies, forces, and stress tensors of a large set of small configurations of atoms, which are obtained using high-accuracy quantum electronic structure (QM) calculations. The local environment of each atom is characterized by a set of bispectrum components of the local neighbor density projected onto a basis of hyperspherical harmonics in four dimensions. The bispectrum components are the same bond-orientational order parameters employed by the GAP potential 1]. The SNAP potential, unlike GAP, assumes a linear relationship between atom energy and bispectrum components. The linear SNAP coefficients are determined using weighted least-squares linear regression against the full QM training set. This allows the SNAP potential to be fit in a robust, automated manner to large QM data sets using many bispectrum components. The calculation of the bispectrum components and the SNAP potential are implemented in the LAMMPS parallel molecular dynamics code. We demonstrate that a previously unnoticed symmetry property can be exploited to reduce the computational cost of the force calculations by more than one order of magnitude. We present results for a SNAP potential for tantalum, showing that it accurately reproduces a range of commonly calculated properties of both the crystalline solid and the liquid phases. In addition, unlike simpler existing potentials, SNAP correctly predicts the energy barrier for screw dislocation migration in BCC tantalum.

Subfields: Atomic and Molecular Physics, and Optics, Materials Chemistry

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Atomic and Molecular Physics, and Optics

In Materials Chemistry

Citations in the corpus

Machine Learning for High-entropy Alloys: Progress, Challenges and Opportunities (2022, methodology): “SNAP is closely related to GAP in that the central quantity is also the atomic neighbor density in Eq.”
A Performance and Cost Assessment of Machine Learning Interatomic Potentials. (2019, methodology): “. D.; Csanyi, G.; Marzari, N. Achieving DFT Accuracy with a Machine-Learning Interatomic Potential: Thermomechanics and Defects in Bcc Ferromagnetic Iron. Physical Review Materials 2018 , 2, 013808. (15) Thompson, A.; Swiler, L.; Trott, C.; Foiles, S.; Tucker, G. Spectral neighbor analysis method fo”
The MLIP package: moment tensor potentials with MPI and active learning (2020, background): “This includes the spectral neighbor analysis potential (SNAP) [74, 78] including the recent extension to multicomponent systems [13], and polynomial-based approaches [18,75] including moment tensor potentials (MTP) [67]—the main focus of the present work.”
Emerging materials intelligence ecosystems propelled by machine learning (2020, background): “150 ) and SNAP 151 ) that allow users to train and validate their own potentials for a particular system have also been released.”
A universal graph deep learning interatomic potential for the periodic table (2022, neutral): “eij G eij + gGW̃2ẽij + b̃2) ⊙ σGW̃1ẽij + b̃1) (6)”
Learning local equivariant representations for large-scale atomistic dynamics (2022, methodology): “MLIPs using strictly local descriptors such as Behler-Parrinello neural networks [5], GAP [6], SNAP [7], DeepMD [20], Moment Tensor Potentials [8], or ACE [12] do not suffer from this obstacle due to their strict locality.”