Small-data physics-informed ML model for magnetic exchange based on chemical composition and structure
cond-mat.str-el
Submitted: 2026-11-03
Updated: 2026-11-03
Comments: 7 pages, 4 figures
License: http://creativecommons.org/licenses/by-nc-sa/4.0/
The gist: In this paper we propose an ensemble model based on a swarm of dense neural networks, able to predict Heisenberg exchange interactions within less than 1% error.
Terminology
Abstract
In this paper we propose an ensemble model based on a swarm of dense neural networks, able to predict Heisenberg exchange interactions within less than 1% error. The model uses the inputs of the ab-initio Schrödinger equation, i.e. the compound structure and chemical composition. In this first work, we trained the model on a few compounds of the hexagonal manganite family and were able to infer, with similar accuracy, the J values for other compounds of the same family at randomly chosen geometries, thus showing that we accurately learned the effect of the chemical composition and structure on effective magnetic integrals J.
Related papers
- Coupled Magnetic and Lattice Excitations in Multiferroic Ba3HoRu2O9: Insights from Neutron Scattering, Raman Spectroscopy, and Machine-Learned Phonon Calculations
- Gossamer Superconductivity in Moir'e WSe 2 Bilayer
- Spin-density wave of ferrimagnetic building blocks masking the ferromagnetic quantum-critical point in NbFe2
- Raman Circular Dichroism and spinon Quantum Geometry of Chiral Quantum Spin Liquids
- Twin Algebras: Condensable Algebras beyond Anyons
- Spin supersolid in triangular lattice easy-axis spin-1/2 antiferromagnet: a fermionic parton perspective