Dr. Artem M. Vorontsov Profile

Dr. Artem M. Vorontsov

at AI Science & Technologies LLC

SPIE Involvement:

Author

Publications (1)

This will count as one of your downloads.

You will have access to both the presentation and article (if available).

DOWNLOAD NOW

This content is available for download via your institution's subscription. To access this item, please sign in to your personal account.

Email or Username Forgot your username?

Password Forgot your password?

Show

Keep me signed in

No SPIE account? Create an account

Proceedings Article | 7 October 2024 Presentation + Paper

Predicting atmospheric turbulence (Cn2) with deep neural networks: leveraging laser beam phase and turbulence profiling

Victor Kulikov, Artem Vorontsov

Proceedings Volume 13149, 131490Y (2024) https://doi.org/10.1117/12.3027226

KEYWORDS: Turbulence, Sensors, Data modeling, Profiling, Neural networks, Atmospheric turbulence, Numerical simulations, Atmospheric sensing

Read Abstract +

Recent studies have shown that incorporating phase information alongside registered intensity distribution enhances Deep Neural Networks (DNNs) based predictions of refractive index structure function, C_n², which characterizes turbulence strength. In this study, we conducted numerical simulations to analyze the impact of received phase information on C_n² recovery error depending on properties of the used sensor and atmospheric conditions. We examined the size and number of lenses required to form an intensity pattern in the focal plane and its impact on C_n² predictions. We also considered the impact of presence of localized turbulence layer on accuracy of DNN-based C_n² predictions, ways to eliminate this impact, and locate the layer. We used wave-optics numerical simulations to generate datasets of short-exposure intensity distributions. The atmospheric propagation of a collimated Gaussian beam over the considered distance was simulated using the split-step method. The atmospheric turbulence followed von Karman’s power spectrum and was represented by a set of phase screens. These datasets were then used for training, validating, and testing the DNN models. The DNN architecture consisted of feature extracting blocks each containing three convolutional and max-pooling layers, and a single perceptron layer with 20 neurons. The model featured 16 feature extracting blocks with identical topology and weights, simultaneously receiving sequential frames from the dataset.

My Library

You currently do not have any folders to save your paper to! Create a new folder below.

Folder Name

Folder Description

View contact details

UPDATE YOUR PROFILE

Is this your profile? Update it now.

Sign into your SPIE.org account

Don’t have a profile and want one?

Create an account on SPIE.org

Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks. You are receiving this notice because your organization may not have SPIE eBooks access.*

*Shibboleth/Open Athens users─please sign in to access your institution's subscriptions.

To obtain this item, you may purchase the complete book in print or electronic format on SPIE.org.

ORGANIZATIONAL
Sign in with credentials provided by your organization.

Organizational Username

Organizational Password

Show/Hide Password

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

Members:

Non-members: ADD TO CART

Keywords/Phrases

Search In:

Publication Years