WaveNet: learning to predict wave height and period from accelerometer data using convolutional neural network

Inertial sensors carried by buoys, such as accelerometers, are widely used in wave characteristics measurement. Traditional methods usually employ numerical integration on the accelerate data for wave height, where the "drifting" errors are intractable. In this paper we propose a novel method to predict wave height and period using machine learning approach, specially a convolutional neural network. The end-to-end 1D convolutional neural network named WaveNet predicts wave height and period from the raw acceleration data directly. We designed a simple device to simulate the motion of the buoy in the wave, and used it to collect data for training and testing our model. The results of the proposed method were compared with traditional numerical integration method and found that the proposed model outperforms existing method in outputting more accurate wave height and period.

[1]  Tong Zhang,et al.  Effective Use of Word Order for Text Categorization with Convolutional Neural Networks , 2014, NAACL.

[2]  Amir Etemad-Shahidi,et al.  An alternative approach for the prediction of significant wave heights based on classification and regression trees , 2008 .

[3]  J. Mahjoobi,et al.  Prediction of significant wave height using regressive support vector machines , 2009 .

[4]  Stanisław Ryszard Massel,et al.  Wavelet analysis for processing of ocean surface wave records , 2001 .

[5]  M. H. Kazeminezhad,et al.  Hindcasting of wave parameters using different soft computing methods , 2008 .

[6]  Peter A. E. M. Janssen,et al.  Improvement of the Short-Fetch Behavior in the Wave Ocean Model (WAM) , 1999 .

[7]  Tai-Wen Hsu,et al.  Simulating typhoon waves by SWAN wave model in coastal waters of Taiwan , 2002 .

[8]  Makarand Deo,et al.  Real time wave forecasting using neural networks , 1998 .

[9]  Geoffrey E. Hinton,et al.  ImageNet classification with deep convolutional neural networks , 2012, Commun. ACM.

[10]  Julia C. Hargreaves,et al.  The spectral wave model, WAM, adapted for applications with high spatial resolution , 2000 .

[11]  M. C. Deo,et al.  Neural networks for wave forecasting , 2001 .

[12]  V. Panchang,et al.  One-Day Wave Forecasts Based on Artificial Neural Networks , 2006 .

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

[14]  Stanisław Ryszard Massel,et al.  Ocean Surface Waves: Their Physics and Prediction , 1996 .

[15]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[16]  Seyed Jamshid Mousavi,et al.  A hybrid genetic algorithm-adaptive network-based fuzzy inference system in prediction of wave parameters , 2009, Eng. Appl. Artif. Intell..

[17]  Salvador Balle,et al.  Wave height prediction in the Western Mediterranean using genetic algorithms , 2010 .

[18]  Yoon Kim,et al.  Convolutional Neural Networks for Sentence Classification , 2014, EMNLP.

[19]  K. C. Khare,et al.  Wave forecasts using wind information and genetic programming , 2012 .

[20]  K. Günaydın.  The estimation of monthly mean significant wave heights by using artificial neural network and regression methods , 2008 .

[21]  James D. Dykes,et al.  Forecasting and hindcasting waves with the SWAN model in the Southern California Bight , 2007 .

[22]  A. Mazzino,et al.  Performance evaluation of Wavewatch III in the Mediterranean Sea , 2015 .

[23]  G. S. Dwarakish,et al.  Numerical Wave Modelling – A Review☆ , 2015 .

[24]  Abdullah Al Mamun,et al.  Regional ocean wave height prediction using sequential learning neural networks , 2017 .

[25]  Jadran Berbić,et al.  Application of neural networks and support vector machine for significant wave height prediction , 2017 .

[26]  Scott C. James,et al.  An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts , 2018, Journal of Marine Systems.