A machine learning approach for forecasting the refractive index structure parameter

Joshua J. Rudiger; Kevin Book; John S. deGrassie; Stephen Hammel; Brook Baker

doi:10.1117/12.2323835

14 November 2018 A machine learning approach for forecasting the refractive index structure parameter

Joshua J. Rudiger, Kevin Book, John S. deGrassie, Stephen Hammel, Brook Baker

Proceedings Volume 10770, Laser Communication and Propagation through the Atmosphere and Oceans VII; 107700P (2018) https://doi.org/10.1117/12.2323835
Event: SPIE Optical Engineering + Applications, 2018, San Diego, California, United States

Abstract

An accurate forecast of atmospheric turbulence is needed to characterize the performance of free-space electro-optical systems. Atmospheric turbulence physics is intricate and stochastic and relies on an assortment of assumptions, making modeling difficult to formulate in a rigorous first principles manner. Machine learning (ML) techniques have been shown to parameterize complex relationships in large datasets and are able to more accurately predict response variables than standard regression methods. This study applies machine learning techniques to develop a model that forecasts the refractive index structure parameter, 𝐶𝑛 2. Measurements of 𝐶𝑛 2 were obtained from a field experiment along with meteorological observations. Several machine learning models were created and compared to optical scintillometer output and current atmospheric turbulence models. The ML based models are shown to generate predictions of 𝐶𝑛 2 that are more highly correlated to observed 𝐶𝑛 2 than physics-based formulations.

Citation Download Citation

Joshua J. Rudiger, Kevin Book, John S. deGrassie, Stephen Hammel, and Brook Baker "A machine learning approach for forecasting the refractive index structure parameter", Proc. SPIE 10770, Laser Communication and Propagation through the Atmosphere and Oceans VII, 107700P (14 November 2018); https://doi.org/10.1117/12.2323835

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