Neural-Network-Based Data Assimilation to Improve Numerical Ocean Wave Forecast

This paper demonstrates the skill level of a wavelet neural network in improving numerical ocean wave predictions of significant wave height (H8) and peak wave period (Tp) having practical applications in operational centers. The study uses data of H8 and Tp for a coastal region off Puducherry located in the east coast of India, and obtained from a high-resolution wave model resulting from nesting of the SWAN model with the WW3 model. A wave rider buoy located off Puducherry provided data for a period of 25 months during the period from June 2007 until July 2009 used in this study. The time series of error between numerical and corresponding measured values was first constructed, and using a wavelet neural network, the errors were predicted for future time steps. The predicted errors when incorporated into the model values provided the updated prediction of H8 and Tp. The study signifies that numerical estimations could be significantly improved using this procedure. The results provide quite satisfactory predictions with a lead time varying from 3 to 24 h. The study points out that adequate training of the neural network is an essential prerequisite to obtain good performance and skill levels. A comparison between the suggested prediction method with the standalone neural network model trained with measured data off Puducherry showed that the former approach is preferred over the latter in obtaining a sustained prediction performance.

[1]  Hendrik L. Tolman,et al.  Source Terms in a Third-Generation Wind Wave Model , 1996 .

[2]  Luigi Cavaleri,et al.  WAVE MODELING Where to Go in the Future , 2006 .

[3]  D. Labat,et al.  Rainfall-runoff relations for karstic springs. Part II: Continuous wavelet and discrete orthogonal multiresolution analyses. , 2000 .

[4]  O. Makarynskyy,et al.  Improving wave predictions with artificial neural networks , 2004 .

[5]  Vladan Babovic,et al.  Wave data assimilation using ensemble error covariances for operational wave forecast , 2006 .

[6]  F. Jose,et al.  A coupled hydrodynamic modeling system for PHAILIN cyclone in the Bay of Bengal , 2014 .

[7]  S. Dube,et al.  Sea State Hindcast with ECMWF Data Using a Spectral Wave Model for Typical Monsoon Months , 2004 .

[8]  S. Mallat.  A wavelet tour of signal processing , 1998 .

[9]  Hendrik L. Tolman,et al.  A Third-Generation Model for Wind Waves on Slowly Varying, Unsteady, and Inhomogeneous Depths and Currents , 1991 .

[10]  Jiwen Dong,et al.  Time-series prediction using a local linear wavelet neural network , 2006, Neurocomputing.

[11]  Prasad K. Bhaskaran,et al.  Application of wave model for weather routing of ships in the North Indian Ocean , 2008 .

[12]  Prasad K. Bhaskaran,et al.  Wave forecasting system for operational use and its validation at coastal Puducherry, east coast of India , 2014 .

[13]  Vladan Babovic,et al.  Local model approximation in the real time wave forecasting , 2005 .

[14]  R. Venkatesan,et al.  Near-shore wave induced setup along Kalpakkam coast during an extreme cyclone event in the Bay of Bengal , 2012 .

[15]  N. Booij,et al.  A third‐generation wave model for coastal regions: 2. Verification , 1999 .

[16]  J. D. Agrawal,et al.  On-line wave prediction , 2002 .

[17]  R. Venkatesan,et al.  Modulation of local wind-waves at Kalpakkam from remote forcing effects of Southern Ocean swells , 2013 .

[18]  S. Dube,et al.  Extreme Wave Conditions Over the Bay of Bengal During Severe Cyclone?Simulation Experiment With Two Spectral Wave Models , 2000 .

[19]  N. Booij,et al.  Assimilation of buoy and satellite data in wave forecasts with integral control variables , 1997 .

[20]  Vladan Babovic,et al.  Error correction of a predictive ocean wave model using local model approximation , 2005 .

[21]  H. Tolman.  The numerical model WAVEWATCH , 1989 .

[22]  P. Bhaskaran,et al.  Parameterization of bottom friction under combined wave-tide action in the Hooghly estuary, India , 2012 .