A method to build digital twin of atmospheric turbulence phase screens with comprehensible deep neural networks

Xiang Zhang; Peng Jia; Weihua Wang

doi:10.1117/12.2630029

29 August 2022 A method to build digital twin of atmospheric turbulence phase screens with comprehensible deep neural networks

Xiang Zhang, Peng Jia, Weihua Wang

Author Affiliations +

Proceedings Volume 12185, Adaptive Optics Systems VIII; 121853C (2022) https://doi.org/10.1117/12.2630029
Event: SPIE Astronomical Telescopes + Instrumentation, 2022, Montréal, Québec, Canada

Conference Poster

Abstract

Atmospheric turbulence phase screens are important for performance test of adaptive optics systems and image restoration algorithms. In recent years, more and more model based adaptive optics control algorithms, wave-front reconstruction algorithms and image restoration algorithms have been proposed. These algorithms have very strong prior information about properties of turbulence. Ordinary atmospheric turbulence phase screen generation methods would become inappropriate to test these methods, because these phase screen generation methods are also developed according to prior information of turbulence. In this paper, we will report our recent progress in building a digital twin of atmospheric turbulence phase screen, which automatically obtain models of atmospheric turbulence and generates phase screens directly. Our method has no prior assumptions about the statistical properties of turbulence phase screens, which make it adequate to test the performance of model based algorithms.

Conference Presentation

Citation Download Citation

Xiang Zhang, Peng Jia, and Weihua Wang "A method to build digital twin of atmospheric turbulence phase screens with comprehensible deep neural networks", Proc. SPIE 12185, Adaptive Optics Systems VIII, 121853C (29 August 2022); https://doi.org/10.1117/12.2630029

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available