Active learning of collinear magnetic Moment Tensor Potentials using the spin-MLIP package from soft-constrained spin-polarized DFT calculations: a case study of Fe-Pd
Abstract
Explicit incorporation of magnetic degrees of freedom in machine-learning interatomic potentials (magnetic MLIPs) plays a crucial role in the correct description of magnetic materials and their properties. An important ingredient for fitting of magnetic MLIPs is spin-polarized density functional theory (DFT) calculations with non-equilibrium magnetic moments, i.e. DFT calculations with constraints on magnetic moments. In this study, we present a workflow for active learning of magnetic Moment Tensor Potential (mMTP) during molecular dynamics (MD) simulations. Magnetic MTP and its active learning algorithm were implemented in the open-source spin-MLIP code, DFT soft-constrained spin-polarized calculations were performed with the VASP code, and MD simulations were conducted in the open-source LAMMPS code. We test our workflow on the Fe-Pd crystal. The dependencies of magnetization and phonon density of states (DOSs) on the volume of a supercell (or, pressure) are in good agreement with those calculated with DFT. Furthermore, the calculated DOSs correspond to the experimental ones.
Related
- Revisiting quantum effects on dislocation glide in bcc metals from DFT calculations and machine-learning potentials
- Machine Learning Local Potentials for Accelerated Electron-Phonon Interactions Calculations within the Projector Augmented-Wave Framework
- SLUSCHI-UP: A Web Infrastructure for SLUSCHI Melting-Temperature Calculations Using Universal Machine-Learning Interatomic Potentials
- Optical design for implementing non-collinear circularly polarized high harmonic generation in an enhancement cavity
- Exchange-Correlation Potentials and Energies from Inverse Generalized Kohn-Sham Calculations
BibTeX
@misc{burov2026active,
title = {{Active learning of collinear magnetic Moment Tensor Potentials using the spin-MLIP package from soft-constrained spin-polarized DFT calculations: a case study of Fe-Pd}},
author = {Arseniy Burov and Alexey S. Kotykhov and Dmitry A. Aksyonov and Ivan S. Novikov and Vladimir V. Ladygin},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2605.26897},
eprint = {2605.26897},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2605.26897},
note = {CC BY-NC-ND 4.0},
}
RIS
TY - UNPB
TI - Active learning of collinear magnetic Moment Tensor Potentials using the spin-MLIP package from soft-constrained spin-polarized DFT calculations: a case study of Fe-Pd
AU - Arseniy Burov
AU - Alexey S. Kotykhov
AU - Dmitry A. Aksyonov
AU - Ivan S. Novikov
AU - Vladimir V. Ladygin
PY - 2026
DA - 2026/10/02
PB - arXiv
DO - 10.48550/arxiv.2605.26897
UR - https://arxiv.org/abs/2605.26897
AB - Explicit incorporation of magnetic degrees of freedom in machine-learning interatomic potentials (magnetic MLIPs) plays a crucial role in the correct description of magnetic materials and their properties. An important ingredient for fitting of magnetic MLIPs is spin-polarized density functional theory (DFT) calculations with non-equilibrium magnetic moments, i.e. DFT calculations with constraints on magnetic moments. In this study, we present a workflow for active learning of magnetic Moment Tensor Potential (mMTP) during molecular dynamics (MD) simulations. Magnetic MTP and its active learning algorithm were implemented in the open-source spin-MLIP code, DFT soft-constrained spin-polarized calculations were performed with the VASP code, and MD simulations were conducted in the open-source LAMMPS code. We test our workflow on the Fe-Pd crystal. The dependencies of magnetization and phonon density of states (DOSs) on the volume of a supercell (or, pressure) are in good agreement with those calculated with DFT. Furthermore, the calculated DOSs correspond to the experimental ones.
ER -