LAUSR

Because systematic direct measurements of the refractive index structure constant ($C_n^2$Cn2) are not available for many climates and seasons, we developed an indirect method to forecast optical turbulence. The $C_n^2$Cn2 was estimated from a backpropagation neural network optimized by an adaptive niche-genetic algorithm. The estimated result was validated against the corresponding six-day $C_n^2$Cn2 data from a field campaign of the 30th Chinese National Antarctic Research Expedition. We also compared the correlation coefficient, root mean square error, and systematic error bias of the proposed model with the weather research and forecasting model. The results suggest that our model shows better correlation and reliably estimates $C_n^2$Cn2.