Abstract
Using advanced deep learning (DL) algorithms for forecasting significant wave height of coastal sea waves over a relatively short period can generate important information on its impact and behaviour. This is vital for prior planning and decision making for events such as search and rescue and wave surges along the coastal environment. Short-term 24 h forecasting could provide adequate time for relevant groups to take precautionary action. This study uses features of ocean waves such as zero up crossing wave period (Tz), peak energy wave period (Tp), sea surface temperature (SST) and significant lags for significant wave height (Hs) forecasting. The dataset was collected from 2014 to 2019 at 30 min intervals along the coastal regions of major cities in Queensland, Australia. The novelty of this study is the development and application of a highly accurate hybrid Boruta random forest (BRF)–ensemble empirical mode decomposition (EEMD)–bidirectional long short-term memory (BiLSTM) algorithm to predict significant wave height (Hs). The EEMD–BiLSTM model outperforms all other models with a higher Pearson’s correlation (R) value of 0.9961 (BiLSTM—0.991, EEMD-support vector regression (SVR)—0.9852, SVR—0.9801) and comparatively lower relative mean square error (RMSE) of 0.0214 (BiLSTM—0.0248, EEMD-SVR—0.043, SVR—0.0507) for Cairns and similarly a higher Pearson’s correlation (R) value of 0.9965 (BiLSTM—0.9903, EEMD–SVR—0.9953, SVR—0.9935) and comparatively lower RMSE of 0.0413 (BiLSTM—0.075, EEMD-SVR—0.0481, SVR—0.057) for Gold Coast.
Highlights
There are no set criteria for data partition, datasets are normally divided into training, validation and testing
The partial autocorrelation function (PACF) analysis method is widely used as it provides partial correlation of the stationary time series with its own lagged values
The results have shown that the hyin providing ocean wave predictions and assessment
Summary
Publisher’s Note: MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations. The recent development in artificial intelligence models have led to the increase in accuracy and reliability of these forecasts This has been shown in many recent studies where classical machine learning methods have been used to forecast wave features [14,15,16]. The main objective of using such an advanced framework is to overcome limitations of conventional data-driven models These models do not efficiently capture short and long-term dependencies between the predictors and the target. A bidirectional long short-term memory (BiLSTM)-based DL model can overcome the common vanishing gradient issue in many classical models This is facilitated by its ability to use 3 unique gates: input, forget and output [19]. The importance of input selection by BRF for data-driven streamflow forecasting is demonstrated in [45]
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
