Machine Learning Prediction of Magnetic Proximity Effect in van der Waals Heterostructures: From Atoms to Moir\'e

TL;DR

This paper presents a machine learning approach to predict proximity-induced magnetism in van der Waals heterostructures, enabling large-scale analysis beyond traditional computational methods and revealing complex magnetic textures.

Contribution

The authors develop an ensemble regression model trained on DFT data that accurately predicts local magnetic moments from atomic environments, capturing complex magnetic textures in heterostructures.

Findings

The model successfully predicts magnetic moments with high locality.

It uncovers rich magnetic moiré patterns.

The approach is broadly applicable to proximity effects beyond analytical models.

Abstract

We introduce a machine learning framework that efficiently predicts large-scale proximity-induced magnetism in van der Waals heterostructures, overcoming the high computational cost of density functional theory (DFT). We apply it to graphene/\CGT, which exhibits a previously unrecognized dichotomy. Unlike the spin polarization at the Fermi level, which follows the pseudospin, the proximity-induced magnetic moments vary across carbon atoms, defying analytical modeling. To address this, we develop an ensemble-based regression model trained on DFT data and employ local environment descriptors to map the local ($\sim 2$\,nm$^2$) atomic-scale geometry to the carbon magnetic moments. Besides demonstrating locality, the model reveals rich magnetic moir\'e textures. Crucially, this method can be broadly applied to orbital and spin proximity effects that are highly sensitive to local atomic environments and are beyond analytical description.