Intrinsic magnetic properties for SmFe 12−xTx thin films via high-throughput experiments and machine learning techniques

The development of next-generation permanent magnets has become critical due to the limited performance improvements in Nd-Fe-B magnets and concerns over rare earth supply. ThMn  12-type rare-earth intermetallic compounds have emerged as promising alternatives, offering superior performance and reduced rare earth content. This study systematically investigates the magnetic properties of Sm(Fe 12−xTx)-based thin films synthesized via combinatorial sputtering. Various stabilizing elements (e.g. Ti, V, Co, Cr) were analyzed to explore their effects on phase stability, saturation magnetization (μ0Ms), anisotropy field (μ0Hs), and Curie temperature (Tc). High-throughput structural and magnetic characterizations, coupled with machine learning (ML) predictions, facilitated efficient data acquisition and analysis. Experimental results reaffirmed trends such as μ0Ms enhancement with Co and phase-stabilization capabilities of Ti and V. Novel insights into additives like Cr and Ta revealed potential Tc improvements. ML regression models (Random Forest and XGBoost) identified electronegativity as a key factor influencing μ0Ms. Predictive analyses successfully estimated μ0Ms trends and ThMn 12 phase stability for unexplored compositions, enhancing the active learning framework for material discovery. This work highlights the synergy of combinatorial deposition, high-throughput data collection, and ML-assisted prediction in accelerating the exploration of magnetic materials. Future extensions to multi-element systems and other magnetic phases are expected to expedite the discovery of high-performance magnets for motors and energy applications. A novel high-throughput evaluation method reveals key intrinsic properties of ThMn₁₂-type magnets, enabling efficient discovery and optimization of high-performance permanent magnets via combinatorial experiments and machine learning