Machine Learning Framework for Magnetic Candidate Discovery in Cerium-Based Compounds

Abstract

Cerium (Ce), the most abundant lanthanide, offers significant potential for addressing shortages in high-performance magnetic materials, particularly through the discovery of compounds suitable for gap magnets. However, predicting Ce-based ferromagnets with uniaxial magnetic anisotropy remains challenging because their magnetic behavior depends strongly on crystal structure, exchange geometry, and electronic interactions. Here, we present a physics-guided computational framework to screen known Ce-based crystal structures and identify promising Ising ferromagnets for future synthesis. A Random Forest classifier uses seven structural and SOAP descriptors, including unit-cell volume, density, atomic sites, space group, atomic density, Ce SOAP overlap, and transition-metal SOAP overlap, to prioritize candidate compounds. Selected crystallographic structures are then analyzed using Ising-model Monte Carlo simulations to characterize phase behavior and critical properties. Critical exponents extracted from simulated phase transitions provide quantitative insight into magnetic regimes and anisotropy-related effects. We further employ autoencoders trained on affinity-based features from simulated spin configurations to identify latent signatures of phase evolution and transition behavior. Together, this framework integrates structural screening, statistical-mechanical simulation, and machine learning to accelerate the identification of promising Ce-based magnetic materials and provide candidates for experimental synthesis and validation.