Wave hindcasting by coupling numerical model and artificial neural networks

A hybrid genetic algorithm—extreme learning machine approach for accurate significant wave height reconstruction

“…The recurrent neural network approach trained by the conjugate gradient algorithm was found to predict wave height, period, and direction more accurately than the feed forward MLP one. In Malekmohamadi et al (2008) a NN coupled to a numerical prediction model was used to obtain wave height prediction/reconstruction values. Results in buoys located at lake Superior and in the Pacific Ocean were used to validate the model.…”

Statistical models for improving significant wave height predictions in offshore operations

“…The Artificial Neural Networks (ANNs), which are information processing paradigms composed of a large number of highly interconnected processing elements (neurons) working together, have been used extensively in offshore and coastal applications (see e.g. Deo et al, 2001;Tsai et al, 2002;Makarynskyy, 2004;Malekmohamadi et al, 2008;Kumar et al, 2017;Makarynskyy et al, 2005;Londhe et al, 2016;Agrawal and Deo, 2002;Mandal et al, 2005;Londhe and Panchang, 2005;Zhang et al, 2006;Deshmukh et al, 2016;Makarynskyy, 2007;Londhe and Panchang, 2006;Makarynskyy, 2005). Supplementary, Copulas (see e.g.…”

Significant Wave Height Prediction with the CRBM-DBN Model

“…According to the meteorological data, Günaydın (2008) predicted monthly mean significant wave heights by using neural network and regression methods. Malekmohamadi et al (2008), Londhe et al (2016), and Deshmukh et al (2016) combined neural network and numerical models to realize the wave height prediction. To solve the time lag and the lack of extreme wave height prediction ability in the neural network, Deka and Prahlada (2012), Dixit and Londhe (2016), and Dixit et al (2015) added the wavelet into the neural network.…”