A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction

Accurate prediction of the height of ocean waves is critical to ensuring maritime safety, optimizing offshore operations, and mitigating coastal hazards. To improve the accuracy of ocean wave height prediction, we developed a hybrid model that integrates decomposition and deep learning. The approach...

Full description

Saved in:
Bibliographic Details
Main Authors: Yelian Sun, Longkun Yu, Dandan Zhu
Format: Article
Language:English
Published: MDPI AG 2025-05-01
Series:Applied Sciences
Subjects:
Online Access:https://www.mdpi.com/2076-3417/15/10/5517
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849327416019779584
author Yelian Sun
Longkun Yu
Dandan Zhu
author_facet Yelian Sun
Longkun Yu
Dandan Zhu
author_sort Yelian Sun
collection DOAJ
description Accurate prediction of the height of ocean waves is critical to ensuring maritime safety, optimizing offshore operations, and mitigating coastal hazards. To improve the accuracy of ocean wave height prediction, we developed a hybrid model that integrates decomposition and deep learning. The approach combines Fourier transform, seasonal and trend decomposition using Loess, and various deep learning models, which can more accurately capture the periodicity, trends, and random fluctuations. The trend, seasonality, and residual components are predicted using the LSTM model, SARIMAX, and 1D-CNN, respectively. The mean square error of the model prediction was calculated to be 0.0087 and the root mean square error was 0.0935. The results show that the hybrid model outperforms the other methods compared in our experiments. This model can accurately predict ocean wave heights and provides a reference for predicting time-series data with seasonal fluctuations.
format Article
id doaj-art-b493ecd592734d5fa602fc98fdad4b35
institution Kabale University
issn 2076-3417
language English
publishDate 2025-05-01
publisher MDPI AG
record_format Article
series Applied Sciences
spelling doaj-art-b493ecd592734d5fa602fc98fdad4b352025-08-20T03:47:53ZengMDPI AGApplied Sciences2076-34172025-05-011510551710.3390/app15105517A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height PredictionYelian Sun0Longkun Yu1Dandan Zhu2School of Advanced Manufacturing, Nanchang University, Nanchang 330031, ChinaSchool of Advanced Manufacturing, Nanchang University, Nanchang 330031, ChinaSchool of Advanced Manufacturing, Nanchang University, Nanchang 330031, ChinaAccurate prediction of the height of ocean waves is critical to ensuring maritime safety, optimizing offshore operations, and mitigating coastal hazards. To improve the accuracy of ocean wave height prediction, we developed a hybrid model that integrates decomposition and deep learning. The approach combines Fourier transform, seasonal and trend decomposition using Loess, and various deep learning models, which can more accurately capture the periodicity, trends, and random fluctuations. The trend, seasonality, and residual components are predicted using the LSTM model, SARIMAX, and 1D-CNN, respectively. The mean square error of the model prediction was calculated to be 0.0087 and the root mean square error was 0.0935. The results show that the hybrid model outperforms the other methods compared in our experiments. This model can accurately predict ocean wave heights and provides a reference for predicting time-series data with seasonal fluctuations.https://www.mdpi.com/2076-3417/15/10/5517deep learningocean wave heightdata decomposition
spellingShingle Yelian Sun
Longkun Yu
Dandan Zhu
A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction
Applied Sciences
deep learning
ocean wave height
data decomposition
title A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction
title_full A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction
title_fullStr A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction
title_full_unstemmed A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction
title_short A Hybrid Deep Learning Model Based on FFT-STL Decomposition for Ocean Wave Height Prediction
title_sort hybrid deep learning model based on fft stl decomposition for ocean wave height prediction
topic deep learning
ocean wave height
data decomposition
url https://www.mdpi.com/2076-3417/15/10/5517
work_keys_str_mv AT yeliansun ahybriddeeplearningmodelbasedonfftstldecompositionforoceanwaveheightprediction
AT longkunyu ahybriddeeplearningmodelbasedonfftstldecompositionforoceanwaveheightprediction
AT dandanzhu ahybriddeeplearningmodelbasedonfftstldecompositionforoceanwaveheightprediction
AT yeliansun hybriddeeplearningmodelbasedonfftstldecompositionforoceanwaveheightprediction
AT longkunyu hybriddeeplearningmodelbasedonfftstldecompositionforoceanwaveheightprediction
AT dandanzhu hybriddeeplearningmodelbasedonfftstldecompositionforoceanwaveheightprediction