EUVIMEDEUVIMED entdecken
Crossref

Deep learning-enabled optical scatterometry technique for high-precision and non-destructive measurement of grating microstructure parameters

Shengquan Nian, Andong Xie, Dapeng Chen, Yuqing Zheng, Shijie Liu, Qi Lu, Yunxia Jin, Zhigang Han, Jianda Shao, Rihong Zhu

Optics Express · 15.06.2026 · 34 (12) · 22723

DOI: 10.1364/oe.596288 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Optics Express, online erschienen am 11.06.2026. Verfasst von Shengquan Nian und 9 weiteren Autor:innen. Die Arbeit nennt 26 Literaturangaben. Gefördert von: Strategic Priority Research Program of CAS, National Key R&D Program of China, International Partnership Program of Chinese Academy of Sciences.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

The non-destructive and high-precision measurement of grating microstructure parameters at the nanoscale presents a significant challenge for conventional techniques in advanced optical manufacturing. This paper proposes a novel optical scatterometry system for non-destructive, high-precision measurement of grating microstructure parameters. The system integrates a custom-designed dual-beam scatterometer with a dedicated deep learning architecture, termed ASPCNN (Adaptive Self-calibrating Physics-constrained CNN), for the analysis engine. The instrument employs a reference-beam design for enhanced stability. At the same time, the ASPCNN model enables rapid parameter retrieval from diffraction spectra via an Adaptive Receptive Field Fusion (ARFF) module for multi-scale feature extraction and a Self-Calibrating Residual Attention (SCRA) module for noise-robust representation. A physics-constrained loss function ensures predictions adhere to physical feasibility. Experimental results demonstrate sub-nanometer accuracy, outperforming established models (e.g., ResNet, U-Net) with the coefficient of determination (R 2 ) > 0.99. The analysis engine achieves a remarkable single-sample inference time of 9.07 ms, enabling real-time metrological capabilities. This work establishes a new paradigm for intelligent, high-speed, and non-destructive optical metrology, offering a robust solution for industrial metrology of grating microstructures.

Förderung

  • Strategic Priority Research Program of CAS
  • National Key R&D Program of China
  • International Partnership Program of Chinese Academy of Sciences
  • Chinese Academy of Sciences President’s International Fellowship Initiative

Zitieren

APA

Nian, S., Xie, A., Chen, D., Zheng, Y., Liu, S., Lu, Q., Jin, Y., Han, Z., Shao, J., & Zhu, R. (2026). Deep learning-enabled optical scatterometry technique for high-precision and non-destructive measurement of grating microstructure parameters. Optics Express, 34(12), 22723. https://doi.org/10.1364/oe.596288

Vancouver

Nian S, Xie A, Chen D, Zheng Y, Liu S, Lu Q, et al. Deep learning-enabled optical scatterometry technique for high-precision and non-destructive measurement of grating microstructure parameters. Optics Express. 2026;34(12):22723. doi:10.1364/oe.596288

BibTeX
@article{Nian2026,
  author = {Nian, Shengquan and Xie, Andong and Chen, Dapeng and Zheng, Yuqing and Liu, Shijie and Lu, Qi and Jin, Yunxia and Han, Zhigang and Shao, Jianda and Zhu, Rihong},
  title = {Deep learning-enabled optical scatterometry technique for high-precision and non-destructive measurement of grating microstructure parameters},
  journal = {Optics Express},
  year = {2026},
  volume = {34},
  number = {12},
  pages = {22723},
  doi = {10.1364/oe.596288}
}
Kostenlos starten →