Fitting to magnetic forces improves the reliability of magnetic Moment Tensor Potentials
arXiv:2405.07069 · doi:10.1016/j.commatsci.2024.113331
Abstract
We developed a method for fitting machine-learning interatomic potentials with magnetic degrees of freedom, namely, magnetic Moment Tensor Potentials (mMTP). The main feature of our method consists in fitting mMTP to magnetic forces (negative derivatives of energies with respect to magnetic moments) as obtained spin-polarized density functional theory calculations. We test our method on the bcc Fe-Al system with different compositions. Specifically, we calculate formation energies, equilibrium lattice parameter, and total cell magnetization. Our findings demonstrate an accurate correspondence between the values calculated with mMTP and those obtained by DFT at zero temperature. Additionally, using molecular dynamics, we estimate the finite-temperature lattice parameter and capture the cell expansion as was previously revealed in experiment. Furthermore, we demonstrate that fitting to magnetic forces increases the reliability of structure relaxation (or, equilibration), in the sense of ensuring that every relaxation run ends up with a successfully relaxed structure (the failure may otherwise be caused by falsely driving a configuration away from the region covered in the training set).
References in corpus (14)
- Gaussian Approximation Potentials: the accuracy of quantum mechanics, without the electrons
- DeePMD-kit: A deep learning package for many-body potential energy representation and molecular dynamics
- 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
- A Spectral Analysis Method for Automated Generation of Quantum-Accurate Interatomic Potentials
- Active learning of linearly parametrized interatomic potentials
- SchNet: A continuous-filter convolutional neural network for modeling quantum interactions
- Physically-informed artificial neural networks for atomistic modeling of materials
- Machine learning of molecular properties: locality and active learning
- TeaNet: universal neural network interatomic potential inspired by iterative electronic relaxations
- Quantum-accurate magneto-elastic predictions with classical spin-lattice dynamics
- Spin-Dependent Graph Neural Network Potential for Magnetic Materials
- A spectral-neighbour representation for vector fields: machine-learning potentials including spin