Machine Learning Force-Field Approach for Itinerant Electron Magnets

• URL: http://arxiv.org/abs/2501.06171v1
• Date: Fri, 10 Jan 2025 18:50:45 GMT
• Title: Machine Learning Force-Field Approach for Itinerant Electron Magnets
• Authors: Sheng Zhang, Yunhao Fan, Kotaro Shimizu, Gia-Wei Chern,
• Abstract summary: We review the recent development of machine-learning (ML) frameworks for Landau-Lifshitz-Gilbert (LLG) dynamics simulations. We show that LLG simulations based on local fields predicted by the trained ML models successfully reproduce representative non-collinear spin structures.
• Score: 3.3312479395168455
• License:
• Abstract: We review the recent development of machine-learning (ML) force-field frameworks for Landau-Lifshitz-Gilbert (LLG) dynamics simulations of itinerant electron magnets, focusing on the general theory and implementations of symmetry-invariant representations of spin configurations. The crucial properties that such magnetic descriptors must satisfy are differentiability with respect to spin rotations and invariance to both lattice point-group symmetry and internal spin rotation symmetry. We propose an efficient implementation based on the concept of reference irreducible representations, modified from the group-theoretical power-spectrum and bispectrum methods. The ML framework is demonstrated using the s-d models, which are widely applied in spintronics research. We show that LLG simulations based on local fields predicted by the trained ML models successfully reproduce representative non-collinear spin structures, including 120$^\circ$, tetrahedral, and skyrmion crystal orders of the triangular-lattice s-d models. Large-scale thermal quench simulations enabled by ML models further reveal intriguing freezing dynamics and glassy stripe states consisting of skyrmions and bi-merons. Our work highlights the utility of ML force-field approach to dynamical modeling of complex spin orders in itinerant electron magnets.

Related papers

• Machine learning force-field model for kinetic Monte Carlo simulations of itinerant Ising magnets [0.0]
  We present a scalable machine learning (ML) framework for large-scale kinetic Monte Carlo (kMC) simulations of electron Ising systems. Our approach is reminiscent of the ML force-field models widely used in first-principles molecular dynamics simulations.
  arXiv  Detail & Related papers  (2024-11-29T15:35:37Z)
• Latent Space Energy-based Neural ODEs [73.01344439786524]
  This paper introduces novel deep dynamical models designed to represent continuous-time sequences. We train the model using maximum likelihood estimation with Markov chain Monte Carlo. Experimental results on oscillating systems, videos and real-world state sequences (MuJoCo) demonstrate that our model with the learnable energy-based prior outperforms existing counterparts.
  arXiv  Detail & Related papers  (2024-09-05T18:14:22Z)
• Kinetics of orbital ordering in cooperative Jahn-Teller models: Machine-learning enabled large-scale simulations [7.540467064488348]
  We present a scalable machine learning (ML) force-field model for the adiabatic dynamics of Jahn-Teller (JT) systems. Large scale dynamical simulations of the JT model shed light on the orbital ordering dynamics in colossal magnetoresistance manganites.
  arXiv  Detail & Related papers  (2024-05-23T16:44:29Z)
• Machine learning force-field models for metallic spin glass [4.090038845129619]
  We present a scalable machine learning framework for dynamical simulations of metallic spin glasses. A Behler-Parrinello type neural-network model is developed to accurately and efficiently predict electron-induced local magnetic fields.
  arXiv  Detail & Related papers  (2023-11-28T17:12:03Z)
• The Role of Reference Points in Machine-Learned Atomistic Simulation Models [0.0]
  Chemical Environment Modeling Theory (CEMT) is designed to overcome the limitations inherent in traditional atom-centered Machine Learning Force Field (MLFF) models. It allows the leveraging of spatially-resolved energy densities and charge densities from FE-DFT calculations.
  arXiv  Detail & Related papers  (2023-10-28T01:02:14Z)
• Geometric Neural Diffusion Processes [55.891428654434634]
  We extend the framework of diffusion models to incorporate a series of geometric priors in infinite-dimension modelling. We show that with these conditions, the generative functional model admits the same symmetry.
  arXiv  Detail & Related papers  (2023-07-11T16:51:38Z)
• Capturing dynamical correlations using implicit neural representations [85.66456606776552]
  We develop an artificial intelligence framework which combines a neural network trained to mimic simulated data from a model Hamiltonian with automatic differentiation to recover unknown parameters from experimental data. In doing so, we illustrate the ability to build and train a differentiable model only once, which then can be applied in real-time to multi-dimensional scattering data.
  arXiv  Detail & Related papers  (2023-04-08T07:55:36Z)
• Slow semiclassical dynamics of a two-dimensional Hubbard model in disorder-free potentials [77.34726150561087]
  We show that introduction of harmonic and spin-dependent linear potentials sufficiently validates fTWA for longer times. In particular, we focus on a finite two-dimensional system and show that at intermediate linear potential strength, the addition of a harmonic potential and spin dependence of the tilt, results in subdiffusive dynamics.
  arXiv  Detail & Related papers  (2022-10-03T16:51:25Z)
• Descriptors for Machine Learning Model of Generalized Force Field in Condensed Matter Systems [3.9811842769009034]
  We outline the general framework of machine learning (ML) methods for multi-scale dynamical modeling of condensed matter systems. We focus on the group-theoretical method that offers a systematic and rigorous approach to compute invariants based on the bispectrum coefficients.
  arXiv  Detail & Related papers  (2022-01-03T18:38:26Z)
• Molecular spin qudits for quantum simulation of light-matter interactions [62.223544431366896]
  We show that molecular spin qudits provide an ideal platform to simulate the quantum dynamics of photon fields strongly interacting with matter. The basic unit of the proposed molecular quantum simulator can be realized by a simple dimer of a spin 1/2 and a spin $S$ transition metal ion, solely controlled by microwave pulses.
  arXiv  Detail & Related papers  (2021-03-17T15:03:12Z)
• Energy and momentum conservation in spin transfer [77.34726150561087]
  We show that energy and linear momentum conservation laws impose strong constraints on the properties of magnetic excitations induced by spin transfer. Our results suggest the possibility to achieve precise control of spin transfer-driven magnetization dynamics.
  arXiv  Detail & Related papers  (2020-04-04T15:43:30Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.