Inversion of atmospheric turbulence intensity profile based on neural network algorithm

Knowledge of the atmospheric optical turbulence profile (AOTP) is critical for atmospheric optics studies. Meteorological sounding of long-term AOTP observations at seas often comes at an outrageous cost. It is necessary to establish a mathematical model driven by conventional meteorological parameters to predicate the AOTPs at high altitudes. Conventional meteorological parameters TUH (i.e., temperature, wind speed and relative humidity), have an important impact on the sea surface turbulence. AOTPs together with TUHs in Maoming were obtained. Based on the artificial neural network (NN) algorithm, an NN model is established according to the data to predict the upper atmospheric turbulence profile. The AOTPs measurements were used to validate the model predictions with the existing estimation theory. Cross-validation between these methods are performed and evaluated with mean absolute error (MAE), mean variance (MSE) and root mean square variance (RMSE). The results show that the predicted values simulated by the NN algorithm agree well with the real values, which proves that it is feasible and reliable to use the NN to simulate the atmospheric turbulence profile.