Predicting magnetism with first-principles AI

arXiv:2602.09093v2 Announce Type: replace-cross Abstract: Computational discovery of magnetic materials remains challenging because magnetism arises from the competition between kinetic energy and Coulomb interaction that is often beyond the reach of standard electronic-structure methods. Here we tackle this challenge by directly solving the many-electron Schrodinger equation with neural-network variational Monte Carlo, which provides a highly expressive variational wavefunction for strongly correlated systems. Applying this technique to transition metal dichalcogenide moire semicondutors, we predict itinerant ferromagnetism in WSe_2/WS_2 and an antiferromagnetic insulator in twisted Gamma-valley homobilayer, using the same neural network without any physics input beyond the microscopic Hamiltonian. Crucially, both types of magnetic states are obtained from a single calculation within the S_z=0 sector, removing the need to compute and compare multiple S_z sectors. This significantly reduces computational cost and paves the way for faster and more reliable magnetic material design.

Source: arXiv cs.LG | 2026-09-22