Chen Ying, Lin Yibo, Chen Rui, Dong Lisong, Wu Ruixuan, Gai Tianyang, Ma Le, Su Yajuan, Wei Yayi
Opt Express. 2020 Jun 8;28(12):18493-18506. doi: 10.1364/OE.394590.
Extreme ultraviolet (EUV) lithography mask defects may cause severe reflectivity deformation and phase shift in advanced nodes, especially like multilayer defects. Geometric parameter characterization is essential for mask defect compensation or repair. In this paper, we propose a machine learning framework to predict the geometric parameters of multilayer defects on EUV mask blanks. With the proposed inception modules and cycle-consistent learning techniques, the framework enables a novel way of defect characterization with high accuracy.
极紫外（EUV）光刻掩膜缺陷可能会在先进节点中导致严重的反射率变形和相移，尤其是多层缺陷。几何参数表征对于掩膜缺陷补偿或修复至关重要。在本文中，我们提出了一种机器学习框架，用于预测EUV掩膜坯料上多层缺陷的几何参数。借助所提出的初始模块和循环一致学习技术，该框架实现了一种具有高精度的新型缺陷表征方法。
