Electro-Optical Sensors for Atmospheric Turbulence Strength Characterization with Embedded Edge AI Processing of Scintillation Patterns

This study introduces electro-optical (EO) sensors (TurbNet sensors) that utilize a remote laser beacon (either coherent or incoherent) and an optical receiver with CCD camera embedded edge AI computer (Jetson Xavier Nx) for in situ evaluation of the path-averaged atmospheric turbulence refractive index structure parameter Cn2 at high temporal rate. Evaluation values was performed using deep neural network (DNN)-based real-time processing short-exposure laser-beacon light intensity scintillation patterns (images) captured by TurbNet sensor receiver. Several pre-trained DNN models were loaded onto used performance set propagation inference trials under diverse meteorological conditions. model training, validation, testing datasets comprised large number instances frames corresponding reference (“true”) measured side-by-side commercial scintillometer (BLS 2000). Generation University Dayton’s (UD) 7-km test range. The results demonstrated 70–90% correlation between obtained those scintillometer.