Search for: All records

Abstract This study employs a data‐driven machine learning approach to investigate specific ferroelectric properties of Al_1−xSc_xN thin films, targeting their application in next‐generation nonvolatile memory (NVM) devices. This approach analyzes a vast design space, encompassing over a million data points, to predict a wide range of coercive field values that are crucial for optimizing Al_1−xSc_xN‐based NVM devices. We evaluated seven machine learning models to predict the coercive field across a range of conditions, identifying the random forest algorithm as the most accurate, with a testR²value of 0.88. The model utilized five key features: film thickness, measurement frequency, operating temperature, scandium concentration, and growth temperature to predict the design space. Our analysis spans 13 distinct scandium concentrations and 13 growth temperatures, encompassing thicknesses from 9–1000 nm, frequencies from 1 to 100 kHz, and operating temperatures from 273 to 700 K. The predictions revealed dominant coercive field values between 3.0 and 4.5 MV/cm, offering valuable insights for the precise engineering of Al_1−xSc_xN‐based NVM devices. This work underscores the potential of machine learning in guiding the development of advanced ferroelectric materials with tailored properties for enhanced device performance. 

Abstract (Al_xGa_1–x)₂O₃ is an ultrawide‐bandgap semiconductor with a high critical electric field for next‐generation high‐power transistors and deep‐ultraviolet photodetectors. While (010)‐(Al_xGa_1–x)₂O₃ films have been studied, the recent availability of (100), (01)‐Ga₂O₃ substrates have developed interest in (100), (01)‐(Al_xGa_1–x)₂O₃ films. In this work, an investigation of microscopic and spectroscopic characteristics of (100), (01), (010)–(Al_xGa_1–x)₂O₃ films is conducted. A combination of scanning transmission electron microscopy, atom probe tomography (APT), and first‐principle calculations (DFT) is performed. The findings reveal consistent in‐plane chemical homogeneity in lower aluminum content (x = 0.2) films. However, higher aluminum content (x = 0.5), showed inhomogeneity in (100), (010)–(Al_xGa_1–x)₂O₃ films attributed to their spectroscopic properties. The study expanded APT's capabilities to determine Ga─O and Al─O bond lengths by mapping their ion‐pair separations in detector space. The change in ion‐pair separations is consistent with varying orientations, irrespective of aluminum content. DFT also demonstrated a similar trend, concluding that Ga─O and Al─O bonding energy has an inverse relationship with their bond length as crystallographic orientations vary. This systematic study of growth orientation dependence of (Al_xGa_1–x)₂O₃ films’ microscopic and spectroscopic properties will guide the development of new (100) and (01)‐(Al_xGa_1–x)₂O₃ along with existing (010)–(Al_xGa_1–x)₂O₃ films.