Discovery of Spin-Crossover Candidates with Equivariant Graph Neural Networks and Relevance-Based Classification

TL;DR

This paper presents a machine learning approach using equivariant graph neural networks and relevance-based classification to efficiently identify spin-crossover materials from a large database, significantly improving candidate selection accuracy.

Contribution

The study introduces a specialized database, trains a novel neural network model, and applies relevance-based classification to enhance spin-crossover candidate discovery.

Findings

Mean absolute error of 360 meV in predicting spin-switching energies

Nearly four-fold improvement in candidate identification over traditional screening methods

Development of a specialized database of 1,439 materials

Abstract

Swift discovery of spin-crossover materials for their potential application in quantum information devices requires techniques which enable efficient identification of suitably bistable candidates. To this end, we screened the Cambridge Structural Database to develop a specialized database of 1,439 materials and computed spin-switching energies from density functional theory for each material. The database was used to train an equivariant graph convolutional neural network to predict the magnitude of the spin-conversion energy. A test mean absolute error was 360 meV. For candidate identification, we equipped the system with a relevance-based classifier. This approach leads to a nearly four-fold improvement in identifying potential spin-crossover systems of interest as compared to conventional high-throughput screening.