Prediction of Significant Wave Height in Korea Strait Using Machine Learning
The prediction of wave conditions is crucial in the field of marine and ocean engineering. Hence, this study aims to predict the significant wave height through machine learning (ML), a soft computing method. The adopted metocean data, collected from 2012 to 2020, were obtained from the Korea Instit...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
The Korean Society of Ocean Engineers
2021-10-01
|
| Series: | 한국해양공학회지 |
| Subjects: | |
| Online Access: | https://www.joet.org/journal/view.php?doi=10.26748/KSOE.2021.021 |
| _version_ | 1819031205064998912 |
|---|---|
| author | Sung Boo Park Seong Yun Shin Kwang Hyo Jung Byung Gook Lee |
| author_facet | Sung Boo Park Seong Yun Shin Kwang Hyo Jung Byung Gook Lee |
| author_sort | Sung Boo Park |
| collection | DOAJ |
| description | The prediction of wave conditions is crucial in the field of marine and ocean engineering. Hence, this study aims to predict the significant wave height through machine learning (ML), a soft computing method. The adopted metocean data, collected from 2012 to 2020, were obtained from the Korea Institute of Ocean Science and Technology. We adopted the feedforward neural network (FNN) and long-short term memory (LSTM) models to predict significant wave height. Input parameters for the input layer were selected by Pearson correlation coefficients. To obtain the optimized hyperparameter, we conducted a sensitivity study on the window size, node, layer, and activation function. Finally, the significant wave height was predicted using the FNN and LSTM models, by varying the three input parameters and three window sizes. Accordingly, FNN (W48) (i.e., FNN with window size 48) and LSTM (W48) (i.e., LSTM with window size 48) were superior outcomes. The most suitable model for predicting the significant wave height was FNN(W48) owing to its accuracy and calculation time. If the metocean data were further accumulated, the accuracy of the ML model would have improved, and it will be beneficial to predict added resistance by waves when conducting a sea trial test. |
| first_indexed | 2024-12-21T06:42:20Z |
| format | Article |
| id | doaj.art-c1d9252be4fa474ab200c9d6fec95dce |
| institution | Directory Open Access Journal |
| issn | 1225-0767 2287-6715 |
| language | English |
| last_indexed | 2024-12-21T06:42:20Z |
| publishDate | 2021-10-01 |
| publisher | The Korean Society of Ocean Engineers |
| record_format | Article |
| series | 한국해양공학회지 |
| spelling | doaj.art-c1d9252be4fa474ab200c9d6fec95dce2022-12-21T19:12:41ZengThe Korean Society of Ocean Engineers한국해양공학회지1225-07672287-67152021-10-0135533634610.26748/KSOE.2021.021Prediction of Significant Wave Height in Korea Strait Using Machine LearningSung Boo Park0https://orcid.org/0000-0001-9587-2183Seong Yun Shin1https://orcid.org/0000-0001-6665-9092Kwang Hyo Jung2https://orcid.org/0000-0002-8229-6655Byung Gook Lee3https://orcid.org/0000-0003-0725-0355Pusan National UniversityPusan National UniversityPusan National UniversityDongseo UniversityThe prediction of wave conditions is crucial in the field of marine and ocean engineering. Hence, this study aims to predict the significant wave height through machine learning (ML), a soft computing method. The adopted metocean data, collected from 2012 to 2020, were obtained from the Korea Institute of Ocean Science and Technology. We adopted the feedforward neural network (FNN) and long-short term memory (LSTM) models to predict significant wave height. Input parameters for the input layer were selected by Pearson correlation coefficients. To obtain the optimized hyperparameter, we conducted a sensitivity study on the window size, node, layer, and activation function. Finally, the significant wave height was predicted using the FNN and LSTM models, by varying the three input parameters and three window sizes. Accordingly, FNN (W48) (i.e., FNN with window size 48) and LSTM (W48) (i.e., LSTM with window size 48) were superior outcomes. The most suitable model for predicting the significant wave height was FNN(W48) owing to its accuracy and calculation time. If the metocean data were further accumulated, the accuracy of the ML model would have improved, and it will be beneficial to predict added resistance by waves when conducting a sea trial test.https://www.joet.org/journal/view.php?doi=10.26748/KSOE.2021.021machine learningsignificant wave heightkorea straitfeedforward neural networklong short-term memorypearson correlation coefficient |
| spellingShingle | Sung Boo Park Seong Yun Shin Kwang Hyo Jung Byung Gook Lee Prediction of Significant Wave Height in Korea Strait Using Machine Learning 한국해양공학회지 machine learning significant wave height korea strait feedforward neural network long short-term memory pearson correlation coefficient |
| title | Prediction of Significant Wave Height in Korea Strait Using Machine Learning |
| title_full | Prediction of Significant Wave Height in Korea Strait Using Machine Learning |
| title_fullStr | Prediction of Significant Wave Height in Korea Strait Using Machine Learning |
| title_full_unstemmed | Prediction of Significant Wave Height in Korea Strait Using Machine Learning |
| title_short | Prediction of Significant Wave Height in Korea Strait Using Machine Learning |
| title_sort | prediction of significant wave height in korea strait using machine learning |
| topic | machine learning significant wave height korea strait feedforward neural network long short-term memory pearson correlation coefficient |
| url | https://www.joet.org/journal/view.php?doi=10.26748/KSOE.2021.021 |
| work_keys_str_mv | AT sungboopark predictionofsignificantwaveheightinkoreastraitusingmachinelearning AT seongyunshin predictionofsignificantwaveheightinkoreastraitusingmachinelearning AT kwanghyojung predictionofsignificantwaveheightinkoreastraitusingmachinelearning AT byunggooklee predictionofsignificantwaveheightinkoreastraitusingmachinelearning |