Regularised Atomic Body-Ordered Permutation-Invariant Polynomials for the Construction of Interatomic Potentials - Archive ouverte HAL Accéder directement au contenu
Article Dans Une Revue Machine Learning: Science and Technology Année : 2020

Regularised Atomic Body-Ordered Permutation-Invariant Polynomials for the Construction of Interatomic Potentials

Résumé

We investigate the use of invariant polynomials in the construction of data-driven interatomic potentials for material systems. The "atomic body-ordered permutation-invariant polynomials" (aPIPs) comprise a systematic basis and are constructed to preserve the symmetry of the potential energy function with respect to rotations and permutations. In contrast to kernel based and artificial neural network models, the explicit decomposition of the total energy as a sum of atomic body-ordered terms allows to keep the dimensionality of the fit reasonably low, up to just 10 for the 5-body terms. The explainability of the potential is aided by this decomposition, as the low body-order components can be studied and interpreted independently. Moreover, although polynomial basis functions are thought to extrapolate poorly, we show that the low dimensionality combined with careful regularisation actually leads to better transferability than the high dimensional, kernel based Gaussian Approximation Potential.

Dates et versions

hal-02552893 , version 1 (23-04-2020)

Identifiants

Citer

Cas van Der Oord, Geneviève Dusson, Gábor Csányi, Christoph Ortner. Regularised Atomic Body-Ordered Permutation-Invariant Polynomials for the Construction of Interatomic Potentials. Machine Learning: Science and Technology, 2020. ⟨hal-02552893⟩
86 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Mastodon Facebook X LinkedIn More