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.

• Publication year

  2019

• Venue

  IOP Conference Series: Earth and Environment

• Publication date

  2019-11-05

• Fields of study

  Physics, Computer Science, Engineering, Environmental Science

• Identifiers
  DOI 10.1088/1755-1315/369/1/012001
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• An integrated framework that combines machine learning and numerical models to improve wave-condition forecasts

  2018cited by this paper
• Regional ocean wave height prediction using sequential learning neural networks

  2017cited by this paper
• Application of neural networks and support vector machine for significant wave height prediction

  2017cited by this paper
• Performance evaluation of Wavewatch III in the Mediterranean Sea

  2015cited by this paper
• Numerical Wave Modelling – A Review☆

  2015cited by this paper
• Proceedings of the 2015 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies

  2015cited by this paper
• Convolutional Neural Networks for Sentence Classification

  2014cited by this paper
• Effective Use of Word Order for Text Categorization with Convolutional Neural Networks

  2014cited by this paper
• Speech recognition with deep recurrent neural networks

  2013cited by this paper
• Wave forecasts using wind information and genetic programming

  2012cited by this paper
• ImageNet classification with deep convolutional neural networks

  2012cited by this paper
• Wave height prediction in the Western Mediterranean using genetic algorithms

  2010cited by this paper
• Prediction of significant wave height using regressive support vector machines

  2009cited by this paper
• A hybrid genetic algorithm-adaptive network-based fuzzy inference system in prediction of wave parameters

  2009cited by this paper
• The estimation of monthly mean significant wave heights by using artificial neural network and regression methods

  2008cited by this paper
• Hindcasting of wave parameters using different soft computing methods

  2008cited by this paper
• An alternative approach for the prediction of significant wave heights based on classification and regression trees

  2008cited by this paper
• Forecasting and hindcasting waves with the SWAN model in the Southern California Bight

  2007cited by this paper
• One-Day Wave Forecasts Based on Artificial Neural Networks

  2006cited by this paper
• On-line wave prediction

  2002cited by this paper
• Simulating typhoon waves by SWAN wave model in coastal waters of Taiwan

  2002cited by this paper
• Neural networks for wave forecasting

  2001cited by this paper
• On-line wave prediction

  2001cited by this paper
• Wavelet analysis for processing of ocean surface wave records

  2001cited by this paper
• The spectral wave model, WAM, adapted for applications with high spatial resolution

  2000cited by this paper
• Improvement of the Short-Fetch Behavior in the Wave Ocean Model (WAM)

  1999cited by this paper
• Real time wave forecasting using neural networks

  1998cited by this paper
• Ocean Surface Waves: Their Physics and Prediction

  1996cited by this paper

• Estimating Significant Wave Height from IMU data Using Transformer-Based Time-Series Regression Model

  2025cites this paper
• Physics-informed temporal convolutional network with auto-regressive residual for significant wave height prediction

  2025cites this paper
• Machine Learning in Coastal Engineering: Applications, Challenges, and Perspectives

  2024cites this paper
• The Gulf of Mexico in trouble: Big data solutions to climate change science

  2023cites this paper
• Wave-Height Classification Via Deep Learning Using Monoscopic Ocean Videos

  2023cites this paper
• Statistical modelling of the ocean environment – A review of recent developments in theory and applications

  2022cites this paper
• Reservoir production prediction with optimized artificial neural network and time series approaches

  2022cites this paper
• Coastal zone significant wave height prediction by supervised machine learning classification algorithms

  2021cites this paper
• Significant wave height forecasting using WRF-CLSF model in Taiwan strait

  2021cites this paper
• MASTER Uncertainty quantification of long-term significant wave height forecasts to support marine operations

  year unknowncites this paper