Recent studies have shown that incorporating phase information alongside registered intensity distribution enhances Deep Neural Networks (DNNs) based predictions of refractive index structure function, Cn2, which characterizes turbulence strength. In this study, we conducted numerical simulations to analyze the impact of received phase information on Cn2 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 Cn2 predictions. We also considered the impact of presence of localized turbulence layer on accuracy of DNN-based Cn2 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.
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.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
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.