表紙画像

Modeling significant wave heights for multiple time horizons using metaheuristic regression methods

The study examines the applicability of six metaheuristic regression techniques—M5 model tree (M5RT), multivariate adaptive regression spline (MARS), principal component regression (PCR), random forest (RF), partial least square regression (PLSR) and Gaussian process regression (GPR)—for predicting...

詳細記述

保存先:
書誌詳細
主要な著者: Ikram, Rana Muhammad Adnan, Cao, Xinyi, Parmar, Kulwinder Singh, Kisi, Ozgur, Shahid, Shamsuddin, Zounemat Kermani, Mohammad
フォーマット: 論文
言語:English
出版事項: MDPI 2023
主題:
TA Engineering (General). Civil engineering (General)
オンライン･アクセス:http://eprints.utm.my/105675/1/ShamsuddinShahid2023_ModelingSignificantWaveHeights.pdf
http://eprints.utm.my/105675/
http://dx.doi.org/10.3390/math11143141
タグ: タグ追加
タグなし, このレコードへの初めてのタグを付けませんか!
id my.utm.105675
record_format eprints
spelling my.utm.1056752024-05-13T07:15:08Z http://eprints.utm.my/105675/ Modeling significant wave heights for multiple time horizons using metaheuristic regression methods Ikram, Rana Muhammad Adnan Cao, Xinyi Parmar, Kulwinder Singh Kisi, Ozgur Shahid, Shamsuddin Zounemat Kermani, Mohammad TA Engineering (General). Civil engineering (General) The study examines the applicability of six metaheuristic regression techniques—M5 model tree (M5RT), multivariate adaptive regression spline (MARS), principal component regression (PCR), random forest (RF), partial least square regression (PLSR) and Gaussian process regression (GPR)—for predicting short-term significant wave heights from one hour to one day ahead. Hourly data from two stations, Townsville and Brisbane Buoys, Queensland, Australia, and historical values were used as model inputs for the predictions. The methods were assessed based on root mean square error, mean absolute error, determination coefficient and new graphical inspection methods (e.g., Taylor and violin charts). On the basis of root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) statistics, it was observed that GPR provided the best accuracy in predicting short-term single-time-step and multi-time-step significant wave heights. On the basis of mean RMSE, GPR improved the accuracy of M5RT, MARS, PCR, RF and PLSR by 16.63, 8.03, 10.34, 3.25 and 7.78% (first station) and by 14.04, 8.35, 13.34, 3.87 and 8.30% (second station) for the test stage. MDPI 2023-07 Article PeerReviewed application/pdf en http://eprints.utm.my/105675/1/ShamsuddinShahid2023_ModelingSignificantWaveHeights.pdf Ikram, Rana Muhammad Adnan and Cao, Xinyi and Parmar, Kulwinder Singh and Kisi, Ozgur and Shahid, Shamsuddin and Zounemat Kermani, Mohammad (2023) Modeling significant wave heights for multiple time horizons using metaheuristic regression methods. Mathematics, 11 (14). pp. 1-24. ISSN 2227-7390 http://dx.doi.org/10.3390/math11143141 DOI:10.3390/math11143141
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
language English
topic TA Engineering (General). Civil engineering (General)
spellingShingle TA Engineering (General). Civil engineering (General)
Ikram, Rana Muhammad Adnan
Cao, Xinyi
Parmar, Kulwinder Singh
Kisi, Ozgur
Shahid, Shamsuddin
Zounemat Kermani, Mohammad
Modeling significant wave heights for multiple time horizons using metaheuristic regression methods
description The study examines the applicability of six metaheuristic regression techniques—M5 model tree (M5RT), multivariate adaptive regression spline (MARS), principal component regression (PCR), random forest (RF), partial least square regression (PLSR) and Gaussian process regression (GPR)—for predicting short-term significant wave heights from one hour to one day ahead. Hourly data from two stations, Townsville and Brisbane Buoys, Queensland, Australia, and historical values were used as model inputs for the predictions. The methods were assessed based on root mean square error, mean absolute error, determination coefficient and new graphical inspection methods (e.g., Taylor and violin charts). On the basis of root mean square error (RMSE), mean absolute error (MAE), and coefficient of determination (R2) statistics, it was observed that GPR provided the best accuracy in predicting short-term single-time-step and multi-time-step significant wave heights. On the basis of mean RMSE, GPR improved the accuracy of M5RT, MARS, PCR, RF and PLSR by 16.63, 8.03, 10.34, 3.25 and 7.78% (first station) and by 14.04, 8.35, 13.34, 3.87 and 8.30% (second station) for the test stage.
format Article
author Ikram, Rana Muhammad Adnan
Cao, Xinyi
Parmar, Kulwinder Singh
Kisi, Ozgur
Shahid, Shamsuddin
Zounemat Kermani, Mohammad
author_facet Ikram, Rana Muhammad Adnan
Cao, Xinyi
Parmar, Kulwinder Singh
Kisi, Ozgur
Shahid, Shamsuddin
Zounemat Kermani, Mohammad
author_sort Ikram, Rana Muhammad Adnan
title Modeling significant wave heights for multiple time horizons using metaheuristic regression methods
title_short Modeling significant wave heights for multiple time horizons using metaheuristic regression methods
title_full Modeling significant wave heights for multiple time horizons using metaheuristic regression methods
title_fullStr Modeling significant wave heights for multiple time horizons using metaheuristic regression methods
title_full_unstemmed Modeling significant wave heights for multiple time horizons using metaheuristic regression methods
title_sort modeling significant wave heights for multiple time horizons using metaheuristic regression methods
publisher MDPI
publishDate 2023
url http://eprints.utm.my/105675/1/ShamsuddinShahid2023_ModelingSignificantWaveHeights.pdf
http://eprints.utm.my/105675/
http://dx.doi.org/10.3390/math11143141
_version_ 1800082646710091776
score 13.251813

類似資料