Learning from data for wind-wave forecasting

Learning from data for wind-wave forecasting

Zamani Foroushani , A.R., Solomatine, D. ,  Azimian, A. R., Heeming, A.

 Ocean Engineering, Vol. 35, July 2008

Abbstract :

Along with existing numerical process models describing the wind-wave intraction the relatively recent development in the area of machine learning make the so-called data-driven models more and popular . This paper  presents a number of data-driven models for wind-wave process at the Caspian Sea. The problem assiciated with these models is to forecast simplificant wave heights for sveral hours ahead using Buoy measurements. Models are based on artificial neural network (ANN) and instance-based learning past time data describing the phenomenon in question. Three feed-forward ANN models have been built for time horizon of 1-3 and 6h with different inputs. The relevant inputs are selected by analyzing the average mutual information (AMI) . The inputs consist of priori knowledge of wind and significant wave height. The other six models are based on BL method for the same forecast horizons. weighted k-nearest neighbors (ANN) and locally weighted regression (LNR) with Caussian kernel were used in IBL-based model, forecast is made directly by combining instances from the  training data that are close (in the input Space) to the new incoming input  vector. These methods are applied to two sets of data at the Caspian Sea . Experiment show that the ANNs yield slightly better agrement with the measured data that IBL-ANNs can also predict extreme wave conditions better than the other existing methods.