Semiconductor Multilayer Nanometrology with Machine Learning  

作　　者：Hyunsoo Kwak Jungwon Kim 

机构地区：[1]Korea Advanced Institute of Science and Technology(KAIST),Daejeon 34141,South Korea

出　　处：《Nanomanufacturing and Metrology》2023年第2期37-54,共18页纳米制造与计量（英文）

基　　金：Funding National Research Foundation of Korea(Grants 2021R1A2B5B03001407 and 2021R1A5A1032937).

摘　　要：We review the measurement methods and thickness characterization algorithms of semiconductor multilayer devices.Today’s ultrahigh-density,high-energy-efficient three-dimensional semiconductor devices require an iterative semiconductor layer-stacking process.Accurate determination of nanometer-scale layer thickness is crucial for reliable semiconductor device fabrication.In this paper,we first review the commonly used semiconductor multilayer thickness measurement methods,including destructive and nondestructive measurement methods.Next,we review two approaches for thickness characterization:model-based algorithms using a physical interpretation of multilayer structures and a method using data-driven machine learning.With the growing importance of semiconductor multilayer devices,we anticipate that this study will help in selecting the most appropriate method for multilayer thickness characterization.

关 键 词：Semiconductor multilayer devices Electron microscopy SPECTROPHOTOMETRY Spectroscopic ellipsometry Raman spectroscopy Thickness characterization Machine learning 

分 类 号：TB383.1[一般工业技术—材料科学与工程] TP181[自动化与计算机技术—控制理论与控制工程]