hgheiberger/quantum-structure-ml: Machine Learning Magnetism Classifiers from Atomic Coordinates

Code repository for the research paper "Machine Learning Magnetism Classifiers from Atomic Coordinates"

Paper Abstract: The determination of magnetic structure poses a long-standing challenge in condensed matter physics and materials science. Experimental techniques such as neutron diffraction are resource-limited and require complex structure refinement protocols, while computational approaches such as first-principles density functional theory (DFT) need additional semi-empirical correction, and reliable prediction is still largely limited to collinear magnetism. In this work, we present a machine-learning model that aims to classify the magnetic structure by inputting atomic coordinates that contain transition metal and rare-earth elements. By building an equivariant Euclidean neural network that preserves the crystallographic symmetry, the magnetic structure (ferromagnetic, anti-ferromagnetic, and non-magnetic) and magnetic propagation vector (zero or non-zero) can be predicted with an average accuracy of 77.8% and 73.6%, respectively. In particular, a 91% accuracy is reached when predicting no magnetic ordering even if it contains magnetic element(s). Our work represents one step forward to solving the grand challenge of full magnetic structure determination.