Graph Neural Networks Advance Spin Dynamics Simulations in Metallic Magnets

Researchers have developed a novel graph neural network (GNN) framework designed to predict the effective magnetic energy functional for metallic magnets. This approach bypasses the computationally intensive process of repeatedly solving electronic problems during simulations. The GNN-based magnetic force fields can efficiently evaluate spin torques and accurately model nonequilibrium spin dynamics, showing excellent agreement with direct electronic simulations. This advancement offers a path toward large-scale predictive simulations of magnetism across various scales. AI

IMPACT Enables more efficient and accurate large-scale simulations of magnetic phenomena, potentially accelerating materials science research.

RANK_REASON Academic paper detailing a new computational method for simulating magnetic materials. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.LG →

• Electronic Calculations
• graph neural network
• magnetic correlations in the pnictide superconductors CeFeAsO1−xFxand Sr(Fe1−xCox)2As2
• Metallic Magnets
• Nonequilibrium Magnetism
• Spin dynamics and superconductivity in some rare earth intermetallics
• Spin Torques in Systems with Spin Filtering and Spin Orbit Interaction

• paper
• infra

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →