Mohammad Hala, Li Jiawei, Li Bochao, Baraya Jamilu Tijjani, Kone Sana, Zhao Zhenlong, Song Xiaowei, Lin Jingquan
School of Physics, Changchun University of Science and Technology, Changchun 130022, China.
Zhongshan Research Institute, Changchun University of Science and Technology, Zhongshan 528400, China.
Micromachines (Basel). 2025 Apr 30;16(5):541. doi: 10.3390/mi16050541.
Extracting defect profile parameters from measured defect images poses a significant challenge in extreme ultraviolet (EUV) multilayer defect metrologies, because these parameters are crucial for assessing defect printing behavior and determining appropriate repair strategies. This paper proposes to reconstruct defect profile parameters from reflected field intensity images of a phase defect assisted by transfer learning with fine-tuning. These images are generated through simulations using the rigorous finite-difference time-domain (FDTD) method. The VGG-16 pre-trained model, known for its robust feature extraction capability, is adopted and fine-tuned to map the intensity images to the defect profile parameters. The results demonstrate that the proposed approach accurately reconstructs multilayer defect profile parameters, thus providing important information for mask repair strategies.
从测量的缺陷图像中提取缺陷轮廓参数在极紫外（EUV）多层缺陷计量学中是一项重大挑战，因为这些参数对于评估缺陷印刷行为和确定合适的修复策略至关重要。本文提出在微调的迁移学习辅助下，从相位缺陷的反射场强图像中重建缺陷轮廓参数。这些图像是通过使用严格的时域有限差分（FDTD）方法进行模拟生成的。采用以强大特征提取能力著称的VGG - 16预训练模型并进行微调，以将强度图像映射到缺陷轮廓参数。结果表明，所提出的方法能够准确重建多层缺陷轮廓参数，从而为掩膜修复策略提供重要信息。
