Predictions of Missing Wave Data by Recurrent Neuronets

Abstract

Real time wave measurements in Turkey are often interrupted because of operational difficulties encountered. Therefore, the lacking significant wave height, period and directions were simultaneously estimated from the dynamic Elman type recurrent neural networks. Their predictions were compared with the commonly applied static feed-forward multilayer neural networks and with the stochastic Auto Regressive (AR) and Exogenous Input Auto Regressive (ARX) models. Two distinct learning algorithms, the steepest descent with momentum and the conjugate gradient methods were employed to train the neural networks. It was concluded that, the recurrent neural network generally showed better performance than the feed-forward neural network in the concurrent forecasting of multiple wave parameters. Both artificial intelligence techniques demonstrated a good performance when compared to the predictions of AR and ARX models. Prediction methods are also compared using continuous artificial data generated with known properties by measuring their performance in predicting the removed segments of various lengths. The multivariate ENN model successfully predicted the removed segments of artificially generated wave data. Hence, the learning ability of artificial intelligence techniques was verified signifying the robustness and fault-failure tolerance of neural networks.