Using an artificial neural network approach to estimate surface-layer optical turbulence at Mauna Loa, Hawaii

In this Letter, an artificial neural network (ANN) approach is proposed for the estimation of optical turbulence (Cn2) in the atmospheric surface layer. Five routinely available meteorological variables are used as the inputs. Observed Cn2 data near the Mauna Loa Observatory, Hawaii are utilized for validation. The proposed approach has demonstrated its prowess by capturing the temporal evolution of Cn2 remarkably well. More interestingly, this ANN approach is found to outperform a widely used similarity theory-based conventional formulation for all the prevalent atmospheric conditions (including strongly stratified conditions).