Morphology-Embedded Signatures of Lattice Strain in Ferroelectric BaTiO3 Thin Films Revealed by Machine Learning
Small, 2026
This work introduces a machine learning framework that infers lattice strain in epitaxial BaTiO3 thin films directly from atomic force microscopy surface morphology, accurately classifying strain-engineered functional regimes without diffraction-based characterization and generalizing across different substrates (SrTiO3 to LaAlO3), establishing surface morphology as a scalable, non-destructive descriptor for strain-engineered ferroelectric and quantum functionalities.
BibTeX
@article{yeom2026morphology,
title={Morphology-Embedded Signatures of Lattice Strain in Ferroelectric BaTiO3 Thin Films Revealed by Machine Learning},
author={Yeom, Sanghoon and Jo, Junhyuk and Song, Haeyun and Myung, Sung and Lee, Sunwoo and Lee, Hyungwoo},
journal={Small},
pages={e74593},
year={2026},
publisher={Wiley Online Library}
}