Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16
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...
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Micromachines |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-666X/16/5/541 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849326964432699392 |
|---|---|
| author | Hala Mohammad Jiawei Li Bochao Li Jamilu Tijjani Baraya Sana Kone Zhenlong Zhao Xiaowei Song Jingquan Lin |
| author_facet | Hala Mohammad Jiawei Li Bochao Li Jamilu Tijjani Baraya Sana Kone Zhenlong Zhao Xiaowei Song Jingquan Lin |
| author_sort | Hala Mohammad |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-c827de89e7d54b6d858f463692ae957a |
| institution | Kabale University |
| issn | 2072-666X |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Micromachines |
| spelling | doaj-art-c827de89e7d54b6d858f463692ae957a2025-08-20T03:48:01ZengMDPI AGMicromachines2072-666X2025-04-0116554110.3390/mi16050541Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16Hala Mohammad0Jiawei Li1Bochao Li2Jamilu Tijjani Baraya3Sana Kone4Zhenlong Zhao5Xiaowei Song6Jingquan Lin7School of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaSchool of Physics, Changchun University of Science and Technology, Changchun 130022, ChinaExtracting 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.https://www.mdpi.com/2072-666X/16/5/541EUV lithographymultilayer defectstransfer learningfine-tuningVGG-16 |
| spellingShingle | Hala Mohammad Jiawei Li Bochao Li Jamilu Tijjani Baraya Sana Kone Zhenlong Zhao Xiaowei Song Jingquan Lin Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16 Micromachines EUV lithography multilayer defects transfer learning fine-tuning VGG-16 |
| title | Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16 |
| title_full | Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16 |
| title_fullStr | Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16 |
| title_full_unstemmed | Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16 |
| title_short | Extreme Ultraviolet Multilayer Defect Profile Parameters Reconstruction via Transfer Learning with Fine-Tuned VGG-16 |
| title_sort | extreme ultraviolet multilayer defect profile parameters reconstruction via transfer learning with fine tuned vgg 16 |
| topic | EUV lithography multilayer defects transfer learning fine-tuning VGG-16 |
| url | https://www.mdpi.com/2072-666X/16/5/541 |
| work_keys_str_mv | AT halamohammad extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT jiaweili extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT bochaoli extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT jamilutijjanibaraya extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT sanakone extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT zhenlongzhao extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT xiaoweisong extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 AT jingquanlin extremeultravioletmultilayerdefectprofileparametersreconstructionviatransferlearningwithfinetunedvgg16 |