Machine Learning Approach to Characterize Ferromagnetic La0.7Sr0.3MnO3 Thin Films via Featurization of Surface Morphology

TL;DR

This paper uses machine learning to analyze the surface features of a magnetic material and link them to its electronic and magnetic properties.

Contribution

A novel machine learning method is introduced to classify LSMO thin films based on surface morphology and material properties.

Findings

Non-linear correlations between surface morphology and electronic/magnetic properties were captured using an ensemble model.

LSMO thin films were classified into five types with distinct properties and surface morphologies.

Surface morphology reveals hidden information about correlated material properties in ferromagnetic oxides.

Abstract

Ferromagnetic perovskite oxides, particularly La0.7​Sr0.3MnO3 (LSMO), show significant promise for spintronics and electromagnetic applications due to their unique half‐metallicity and colossal magnetoresistance properties. These properties are known to arise from Mn‐O‐Mn double‐exchange interactions, which are directly related to microscopic lattice structures. However, since the microscopic structure in LSMO is highly sensitive to various material parameters, such as thickness, lattice strain, oxygen deficiency, and cation stoichiometry, understanding the intricate relationship between the microscopic structures and the resulting physical properties of LSMO remains challenging. Herein, a machine learning approach is introduced to characterize ferromagnetic LSMO thin films by featurization of their surface morphology. Using an ensemble machine learning method, the non‐linear correlations between surface morphology and the electronic, magnetic properties of LSMO thin films are captured and modeled. Based on these estimated correlations, LSMO thin films are classified into five representative types, each characterized by distinctive properties and surface morphologies. These results imply that surface morphology can reveal hidden information about the strongly correlated properties of ferromagnetic LSMO thin films. Consequently, the machine learning‐based approach provides an efficient method for understanding the correlated material properties of ferromagnetic oxides and related materials through surface morphology analysis.

A machine‐learning approach is presented to characterize ferromagnetic LSMO thin films by featurizing their surface morphology. Through an ensemble model, the non‐linear correlations between surface morphology and the electric/magnetic properties of LSMO thin films are successfully captured. This result demonstrates that surface morphology can effectively reveal essential information about the correlated physical properties of ferromagnetic oxide materials.

Figures