Simple machine-learned interatomic potentials for complex alloys

Byggmästar, Jesper; Nordlund, Kai; Djurabekova, Flyura

doi:10.48550/arxiv.2203.08458

Cited by 1 publication

(1 citation statement)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To ease the computational burden during training and prediction stages, tabulated versions based on spline approximation of Gaussian Approximation Potentials (GAP) have been proposed [26,27]. The developed potentials were used to study defect evolution in MoNbTaVW [27,28]. Though computationally faster than kernel methods, the accuracy of this potential is limited by the step size of the spline approximations.…”

Section: Introductionmentioning

confidence: 99%

Sparse random Fourier features based interatomic potentials for high entropy alloys

Dhaliwal¹,

Anand²,

Nair³

et al. 2023

Preprint

View full text Add to dashboard Cite

Computational modeling of high entropy alloys (HEA) is challenging given scalability issues of Density functional theory (DFT) and non-availability of Interatomic potentials (IP) for molecular dynamics simulations (MD). This work presents a computationally efficient IP for modeling complex elemental interactions present in HEAs. The proposed random features-based IP can accurately model melting behaviour along with various process related defects. The disordering of atoms during the melting process was simulated. Predicted atomic forces are within 0.08 eV / Å of corresponding DFT forces. MD simulations predictions of mechanical and thermal properties are within 7% of the DFT values. High temperature self diffusion in the alloy system was investigated using the IP. A novel sparse model is also proposed which reduced the computational cost by 94% without compromising on the force prediction accuracy.

show abstract