Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques

Accurate prediction of significant wave height (SWH) is critical for coastal safety, marine operations, and disaster management. Traditional numerical models for wave prediction are computationally intensive and often lack accuracy, prompting a shift towards data-driven methods. This study explores...

Full description

Saved in:
Bibliographic Details
Main Author: Ahmet Durap
Format: Article
Language:English
Published: Elsevier 2024-12-01
Series:Results in Engineering
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2590123024018164
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1846115717055774720
author Ahmet Durap
author_facet Ahmet Durap
author_sort Ahmet Durap
collection DOAJ
description Accurate prediction of significant wave height (SWH) is critical for coastal safety, marine operations, and disaster management. Traditional numerical models for wave prediction are computationally intensive and often lack accuracy, prompting a shift towards data-driven methods. This study explores the efficacy of machine learning (ML) models in forecasting SWH in the coastline of North Stradbroke Island, Queensland, Australia. Using a dataset spanning 2010 to 2022, the study employs wave characteristics such as maximum wave height (Hmax), wave periods (Tz, Tp), peak direction, and sea surface temperature (SST) as predictors. Three ML models—Linear Regression, Decision Tree, and Random Forest—were trained and evaluated using performance metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²). The Random Forest model demonstrated the best predictive accuracy with the lowest MSE (0.0074) and highest R² (0.958), outperforming both Linear Regression and Decision Tree models. This improvement in prediction accuracy supports the model's application for coastal management, ensuring better forecasting of wave conditions. The proposed approach shows significant advantages, including better handling of non-linearities and reduced computational costs compared to conventional numerical methods, such as SWAN and WAM, making it highly applicable for real-time wave forecasting, particularly for regions with complex coastal dynamics such as North Stradbroke Island.
format Article
id doaj-art-0c968d7b35364734ae1233e71fb4d283
institution Kabale University
issn 2590-1230
language English
publishDate 2024-12-01
publisher Elsevier
record_format Article
series Results in Engineering
spelling doaj-art-0c968d7b35364734ae1233e71fb4d2832024-12-19T10:59:59ZengElsevierResults in Engineering2590-12302024-12-0124103573Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniquesAhmet Durap0Engineering and Natural Sciences Faculty, Istanbul Medipol University, 34181, Beykoz, İstanbul, Turkey; Division of Coastal Sciences and Engineering, Civil Engineering Department, Civil Engineering Faculty, Istanbul Technical University, Maslak 34469, Istanbul, Turkey; Division of Civil Engineering, The University of Queensland, Brisbane, 4072, Australia; Corresponding author.Accurate prediction of significant wave height (SWH) is critical for coastal safety, marine operations, and disaster management. Traditional numerical models for wave prediction are computationally intensive and often lack accuracy, prompting a shift towards data-driven methods. This study explores the efficacy of machine learning (ML) models in forecasting SWH in the coastline of North Stradbroke Island, Queensland, Australia. Using a dataset spanning 2010 to 2022, the study employs wave characteristics such as maximum wave height (Hmax), wave periods (Tz, Tp), peak direction, and sea surface temperature (SST) as predictors. Three ML models—Linear Regression, Decision Tree, and Random Forest—were trained and evaluated using performance metrics like Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R-squared (R²). The Random Forest model demonstrated the best predictive accuracy with the lowest MSE (0.0074) and highest R² (0.958), outperforming both Linear Regression and Decision Tree models. This improvement in prediction accuracy supports the model's application for coastal management, ensuring better forecasting of wave conditions. The proposed approach shows significant advantages, including better handling of non-linearities and reduced computational costs compared to conventional numerical methods, such as SWAN and WAM, making it highly applicable for real-time wave forecasting, particularly for regions with complex coastal dynamics such as North Stradbroke Island.http://www.sciencedirect.com/science/article/pii/S2590123024018164Comparative machine learning techniquesSignificant wave height (SWH) predictionDynamic coastlinesWave characteristicsStradbroke IslandQueensland
spellingShingle Ahmet Durap
Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques
Results in Engineering
Comparative machine learning techniques
Significant wave height (SWH) prediction
Dynamic coastlines
Wave characteristics
Stradbroke Island
Queensland
title Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques
title_full Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques
title_fullStr Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques
title_full_unstemmed Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques
title_short Data-driven models for significant wave height forecasting: Comparative analysis of machine learning techniques
title_sort data driven models for significant wave height forecasting comparative analysis of machine learning techniques
topic Comparative machine learning techniques
Significant wave height (SWH) prediction
Dynamic coastlines
Wave characteristics
Stradbroke Island
Queensland
url http://www.sciencedirect.com/science/article/pii/S2590123024018164
work_keys_str_mv AT ahmetdurap datadrivenmodelsforsignificantwaveheightforecastingcomparativeanalysisofmachinelearningtechniques