Translator Disclaimer
14 November 2018 A machine learning approach for forecasting the refractive index structure parameter
Author Affiliations +
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, 𝐢𝑛 2. Measurements of 𝐢𝑛 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 𝐢𝑛 2 that are more highly correlated to observed 𝐢𝑛 2 than physics-based formulations.
© (2018) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
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);

Back to Top