2025/01/09 by Angel Albavera-Mata, Pawan Prakash, Albavera-Mata, Angel +17
Computer Science · Decision Sciences · Mathematics · #Advanced Graph Neural Networks #Artificial intelligence #Computer science #Crossover #Disordered Systems and Neural Networks (cond-mat.dis-nn) #Equivariant map #FOS: Physical sciences #Graph #Materials Science (cond-mat.mtrl-sci) #Mathematics #Pure mathematics #Scientific Computing and Data Management #Theoretical computer science
paper · pdf · doi:10.48550/arxiv.2501.05341
openalex publication_date 2025/01/09 · openalex created_date 2025/01/11 · openalex updated_date 2026/08/01
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.