Automated atomistic simulations of dissociated dislocations with ab initio accuracy
arXiv:2311.01830 · doi:10.1103/PhysRevB.109.094120
Abstract
In (M Hodapp and A Shapeev 2020 Mach. Learn.: Sci. Technol. 1 045005), we have proposed an algorithm that fully automatically trains machine-learning interatomic potentials (MLIPs) during large-scale simulations, and successfully applied it to simulate screw dislocation motion in body-centered cubic tungsten. The algorithm identifies local subregions of the large-scale simulation region where the potential extrapolates, and then constructs periodic configurations of 100--200 atoms out of these non-periodic subregions that can be efficiently computed with plane-wave Density Functional Theory (DFT) codes. In this work, we extend this algorithm to dissociated dislocations with arbitrary character angles and apply it to partial dislocations in face-centered cubic aluminum. Given the excellent agreement with available DFT reference results, we argue that our algorithm has the potential to become a universal way of simulating dissociated dislocations in face-centered cubic and possibly also other materials, such as hexagonal closed-packed magnesium, and their alloys. Moreover, it can be used to construct reliable training sets for MLIPs to be used in large-scale simulations of curved dislocations.
arXiv commentpreprint accepted for publication
References in corpus (23)
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- ANI-1: An extensible neural network potential with DFT accuracy at force field computational cost
- E(3)-Equivariant Graph Neural Networks for Data-Efficient and Accurate Interatomic Potentials
- Moment Tensor Potentials: a class of systematically improvable interatomic potentials
- Interatomic potentials from first-principles calculations: the force-matching method
- A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
- A Performance and Cost Assessment of Machine Learning Interatomic Potentials
- Active learning of linearly parametrized interatomic potentials
- On-the-fly machine learning force field generation: Application to melting points
- Active Learning of Uniformly Accurate Inter-atomic Potentials for Materials Simulation
- Physically-informed artificial neural networks for atomistic modeling of materials
- Achieving DFT accuracy with a machine-learning interatomic potential: thermomechanics and defects in bcc ferromagnetic iron
- DFT-FE -- A massively parallel adaptive finite-element code for large-scale density functional theory calculations
- From Electrons to Finite Elements: A Concurrent Multiscale Approach for Metals
- TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
- Modelling atomic and nanoscale structure in the silicon-oxygen system through active machine learning
- Systematic Atomic Structure Datasets for Machine Learning Potentials: Application to Defects in Magnesium
- Development of a general-purpose machine-learning interatomic potential for aluminum by the physically-informed neural network method
- Lattice Resistance and Peierls Stress in Finite-size Atomistic Dislocation Simulations
- Electronic-structure study of an edge dislocation in Aluminum and the role of macroscopic deformations on its energetics
- In operando active learning of interatomic interaction during large-scale simulations
- Electronic structure study of screw dislocation core energetics in Aluminum and core energetics informed forces in a dislocation aggregate
- Geometries of edge and mixed dislocations in bcc Fe from first principles calculations