Oral Presentation

Inverse design of terahertz phase grating based on deep learning

Author(s): Yilong Zhang, Yuan Ren, Wei Miao, Wen Zhang, Shengcai Shi(Purple Mountain Observatory, CAS)

Presenter: Yilong Zhang (Purple Mountain Observatory, CAS)

The terahertz phase grating could provide coherent local oscillators for the terahertz coherent detection array, which is one of the key technologies to realize high-sensitivity terahertz coherent detection. Traditional iterative design algorithms based on various prior constraints have always faced difficulties such as low accuracy, low reconstruction efficiency, and long iteration time. Using the deep learning framework based on data-driven and automatic extraction of data features, this paper proposes a deep learning-based inverse design method for terahertz phase gratings. Theoretical and experimental analysis proves that the proposed method could complete the inverse design of terahertz phase grating in data-driven and automatic features extraction mode, achieving advantages in terms of design efficiency and accuracy.