An Improved Estimation and Gap-Filling Technique for Sea Surface Wind Speeds Using NARX Neural Networks

This work presents the use of a nonlinear autoregressive neural network to obtain an improved estimate of sea surface winds, taking Placentia Bay, Newfoundland and Labrador, Canada, as a study case. The network inputs and delays were chosen through cross correlation with the target variable. The proposed method was compared with five other wind speed estimation techniques, outperforming them in correlation, precision, accuracy, and bias levels. As an extension, the temporal gap filling of missing wind speed data during a storm has been considered. Data containing a measurement gap from a 40-yr windstorm that hit the same location has been used. The proposed method filled the gaps in the dataset with a high degree of correlation with measurements obtained by surrounding stations. The method presented in this work showed promising results that could be extended to estimate wind speeds in other locations and filling gaps in other datasets.