How to Cite

Peach, L., Carthwright, N., & Strauss, D. (2020). INVESTIGATING MACHINE LEARNING FOR VIRTUAL WAVE MONITORING. Coastal Engineering Proceedings, (36v), papers.46.


Wave monitoring is a time consuming and costly endeavour which, despite best e orts, can be subject to occasional periods of missing data. This paper investigates the application of machine learning to create "virtual" wave height (Hs), period (Tz) and direction (Dp) parameters. Two supervised machine learning algorithms were applied using long term wave parameter datasets sourced from four wave monitoring stations in relatively close geographic proximity. The machine learning algorithms demonstrated reasonable performance for some parameters through testing, with Hs performing best overall followed closely by Tz; Dp was the most challenging to predict and performed relatively the poorest. The creation of such "virtual" wave monitoring stations could be used to hindcast wave conditions, fill observation gaps or extend data beyond that collected by the physical instrument.

Recorded Presentation from the vICCE (YouTube Link):


P. Abhigna, S. Jerritta, R. Srinivasan, and V. Rajendran. Analysis of feed forward and recurrent neural networks in predicting the significant wave height at the Moored Buoys in Bay Of Bengal. In Proceedings of the 2017 IEEE International Conference on Communication and Signal Processing, ICCSP 2017, volume 2018-Janua, pages 1856–1860. Institute of Electrical and Electronics Engineers Inc., feb 2018. ISBN 9781509038008. doi: 10.1109/ICCSP.2017.8286717.

E. Alexandre, L. Cuadra, J. C. Nieto-Borge, G. Candil-García, M. Del Pino, and S. Salcedo-Sanz. A hybrid genetic algorithm-extreme learning machine approach for accurate significant wave height reconstruction. Ocean Modelling, 92:115–123, 2015. doi: 10.1016/j.ocemod.2015.06.010. URL

E. Andrews and L. Peach. Wave Monitoring Equipment Comparison: A comparison between in-situ wave measurement equipment. Technical report, Queensland Government, Department of Environment and Science, Brisbane, Queensland, 2019. URL https: //{_}download/wave-monitoring-equipment-comparison.pdf.

M. Barnes, I. Teakle, P. Wood, and C. Voisey. Assessment of capital works options to mitigate shoaling at Mooloolaba Harbour Entrance. Technical report, nov 2015. URL

J. Berbi´c, E. Ocvirk, D. Carevi´c, and G. Lonˇcar. Application of neural networks and support vector machine for significant wave height prediction. Oceanologia, 59(3):331–349, 2017. ISSN 23007370. doi: 10.1016/j.oceano.2017.03.007.

N. Booij, R. C. Ris, and L. H. Holthuijsen. A third-generation wave model for coastal regions: 1. Model description and validation. Journal of Geophysical Research, 104(C4):7649–7666, 1999. ISSN 0148-0227. doi: 10.1029/98JC02622. URL

L. Cornejo-Bueno, J. C. Nieto-Borge, P. García-Díaz, G. Rodríguez, and S. Salcedo-Sanz. Significant wave height and energy flux prediction for marine energy applications: A grouping genetic algorithm - Extreme Learning Machine approach. Renewable Energy, 97:380–389, nov 2016. ISSN 18790682. doi:10.1016/j.renene.2016.05.094.

Datawell. Directional Waverider MkIII Datawell-Oceanographic Instruments The Directional Waverider DWR-MkIII: Over three years of continuous operation. Technical report, Datawell, Haarlem, Netherlands, 2012a. URL

Datawell. Directional Waverider GPS Datawell-Oceanographic Instruments Measuring waves with GPS. Technical report, Datawell, Haarlem, Netherlands, 2012b. URL

Datawell. DWR4 with ACM Datawell-Oceanographic Instruments. Technical report, Datawell, Haarlem, Netherlands, 2012c. URL

M. C. Deo, A. Jha, A. S. Chaphekar, and K. Ravikant. Neural networks for wave forecasting. Ocean Engineering, 28(7):889–898, 2001. ISSN 00298018. doi: 10.1016/S0029-8018(00)00027-5.

DES. Wave Monitoring Annual Summary 2016 - 2017. Technical Report November 2016, Department of Environment and Science, Queensland Governemnt, Brisbane, Queensland, 2017. URL

DES. Queensland wave climate, wave monitoring annual summary, November 2016-October 2017. Technical report, Queensland Government, Department of Environment and Science, 2018.

K. Hatalis, P. Pradhan, S. Kishore, R. S. Blum, and A. J. Lamadrid. Multi-step forecasting of wave power using a nonlinear recurrent neural network. In IEEE Power and Energy Society General Meeting, volume 2014-Octob. IEEE Computer Society, oct 2014. doi: 10.1109/PESGM.2014.6939370.

S. C. James, Y. Zhang, and F. O’Donncha. A Machine Learning Framework to Forecast Wave Conditions. Coastal Engineering, 2017.

S. N. Londhe and V. Panchang. Correlation of wave data from buoy networks. 2007. doi: 10.1016/j.ecss.2007.05.003. URL

F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blondel, P. Prettenhofer, R.Wiess, V. Dubourg, and J. Vanderplas. Scikit-learn: Machine Learning in Python. Journal of Machine Learning Research, 12(1):1–5, 2011. ISSN 0717-6163. doi: 10.1007/s13398-014-0173-7.2. URL

M. Pirhooshyaran and L. V. Snyder. Forecasting, hindcasting and feature selection of ocean waves via recurrent and sequence-to-sequence networks. Ocean Engineering, 207, 2020. ISSN 00298018. doi:10.1016/j.oceaneng.2020.107424. URL

A. D. Rao, M. Sinha, and S. Basu. Bay of Bengal wave forecast based on genetic algorithm: A comparison of univariate and multivariate approaches. Applied Mathematical Modelling, 37(6):4232–4244, mar 2013. ISSN 0307904X. doi: 10.1016/j.apm.2012.09.001.

P. Salah, A. Reisi-Dehkordi, and B. Kamranzad. A hybrid approach to estimate the nearshore wave characteristics in the Persian Gulf. Applied Ocean Research, 57:1–7, 2016. doi: 10.1016/j.apor.2016.02.005. URL

A. Saulter. Current and future verification of operational wave models. (June):25–27, 2012. URL

H. L. Tolman andW. D. Group. User manual and system documentation of WAVEWATCH III version 4.18. NOAA / NWS / NCEP / MMAB Technical Note, (333):311, 2014.

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.