(707a) Uncovering Magnetic Properties Composition Dependence of Substituted Ferrites for Magnetically Mediated Energy Delivery Applications: DFT and ML Study

We use computational methods to drive the design of substituted ferrites. Substituted ferrites are magnetic materials based off of the bulk structure of magnetite, i.e., Fe₃O₄ (Figure 1a). In this structure, two of the Fe ions are octahedrally coordinated with formal charges of +2 or +3, and one is tetrahedrally coordinated with a formal charge of +3 (Figure 1b). Substituted ferrites have the formula M_xFe_(3-x)O₄,where M is the substituent atom(s), and can be Mn, Co, Ni, Cu, or Zn; whereas x corresponds to the number of substitutions for the substituent atom(s). Capitalizing on their strong and tunable magnetic properties (e.g., magnetic moment, magnetic saturation and/or magnetic anisotropy), substituted ferrites can be used for magnetically mediated energy deliver (MagMED) applications. For biomedical applications, a goal is to optimize the magnetic saturation and anisotropy so that energy can be delivered (e.g., to cancer cells) effectively and safely. Recent literature suggests that the magnetic properties of substituted ferrites—such as magnetic moment—can be tuned via their compositions, as illustrate Figure 1c. In this work, we use a combination of Density Functional Theory (DFT) and machine learning (ML) to learn the relationship between composition and magnetic performance of substituted ferrites. Magnetic moment and magnetic saturation are calculated using DFT for ~666 composition—with normal and inverse spinel bulk structures—with x ranging from 0.0625 to 1. Substitutions are made at the octahedrally and tetrahedrally coordinated Fe²⁺ and Fe³⁺ sites respectively, which are highlighted in gray in Figure 1b. DFT values, for the magnetic moment and saturation, are input to machine-learning (ML) model to correlate it to composition. Specifically, an XGBoost algorithm is used to correlate the magnetic moment and saturation to tabulated properties of the substituent atom(s), such as electronic properties, nuclear properties, atomic sizes, and redox energies. All of these "features" of the substituent atom(s) are taken from established databases and do not require further calculations. Our first ML model which predicts if an specific composition results in normal or inverse spinel structures, Figure 1d shows parity plot comparing the difference in electronic energy (ΔE) for normal vs. inverse spinel structures as computed with DFT and predicted with our ML model. The developed ML model enables a rapid screening of vast chemical spaces of ferrites composition with surrogate ML models, which can be used to identify design rules and guide materials selection for substituted ferrites.