An equivariant message-passing neural network embeds atomic spins explicitly to learn magnetic interactions, achieving near-DFT accuracy and data efficiency across magnetic systems via fine-tuning.
OstravaJ: a tool for calculating magnetic exchange interactions via DFT
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
fields
cond-mat.mtrl-sci 2verdicts
UNVERDICTED 2representative citing papers
AMaRaNTA automates the four-state energy-mapping method to extract nearest-neighbor exchange tensors plus scalar second- and third-neighbor exchanges and single-ion anisotropy from DFT for 2D magnets.
citing papers explorer
-
Equivariant Many-body Message Passing Interatomic Potentials for Magnetic Materials
An equivariant message-passing neural network embeds atomic spins explicitly to learn magnetic interactions, achieving near-DFT accuracy and data efficiency across magnetic systems via fine-tuning.
-
AMaRaNTA: Automated First-Principles Exchange Parameters In 2D Magnets
AMaRaNTA automates the four-state energy-mapping method to extract nearest-neighbor exchange tensors plus scalar second- and third-neighbor exchanges and single-ion anisotropy from DFT for 2D magnets.