Chang, Hye Jung Choi, Haneul Keun Won Lee Hyung-Jin Choi Lee, Jun Young Jun Hyeok Choi BAEK, SEUNG HYUB Ki Sub Cho 2025-10-31T02:00:18Z 2025-10-31T02:00:18Z 2025-10-28 2025-12-08 https://pubs.kist.re.kr/handle/201004/153385 This study presents an efficient method for automatically identifying the crystal structure and orientation of Y-doped HfO2-based thin films using deep learning. This approach enables largescale crystallographic analysis with sub-nanometer spatial resolution using only scanning transmission electron microscopy (STEM) atomic images, thereby reducing the reliance on manual expert interpretation. The Xception network-based model extracts detailed crystallographic information through structure and entropy maps, effectively identifying subtle pattern changes and local structural discontinuities. Entropy maps are utilized to analyze the atomic structure disorder and detect ambiguous boundaries and strained regions. Analysis of Y-doped HfO2 thin films revealed that the film thickness significantly affects the ferroelectric properties, with the O-phase dominant in 5 nm films and the M-phase proportion increasing as the thickness increases. This machine-learning-based STEM atomic image analysis method provides an automated solution to accelerate ferroelectric material research and promote the development of next-generation electronic devices, offering an accurate understanding and control of microstructural characteristics. The Korean Physical Society Machine learning-powered recognition of crystalline phases and orientations in epitaxial Y-doped HfO₂ via atomic-resolution STEM Conference 1 The 14th International Conference on Advanced Materials and Devices (ICAMD 2025) The 14th International Conference on Advanced Materials and Devices (ICAMD 2025) KO BEXCO, Busan, Korea 2025-12-08 The 14th International Conference on Advanced Materials and Devices (ICAMD 2025)