Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory
This paper investigates the possibility of using machine learning technology to correct wave height series numerical predictions. This is done by incorporating numerical predictions into long short-term memory (LSTM). Specifically, a novel ocean wave height series prediction framework, referred to a...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-05-01
|
| Series: | Journal of Marine Science and Engineering |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2077-1312/9/5/514 |
| _version_ | 1797534838247391232 |
|---|---|
| author | Xiaoyu Zhang Yongqing Li Song Gao Peng Ren |
| author_facet | Xiaoyu Zhang Yongqing Li Song Gao Peng Ren |
| author_sort | Xiaoyu Zhang |
| collection | DOAJ |
| description | This paper investigates the possibility of using machine learning technology to correct wave height series numerical predictions. This is done by incorporating numerical predictions into long short-term memory (LSTM). Specifically, a novel ocean wave height series prediction framework, referred to as numerical long short-term memory (N-LSTM), is introduced. The N-LSTM takes a combined wave height representation, which is formed of a current wave height measurement and a subsequent Simulating Waves Nearshore (SWAN) numerical prediction, as the input and generates the corrected numerical prediction as the output. The correction is achieved by two modules in cascade, i.e., the LSTM module and the Gaussian approximation module. The LSTM module characterizes the correlation between measurement and numerical prediction. The Gaussian approximation module models the conditional probabilistic distribution of the wave height given the learned LSTM. The corrected numerical prediction is obtained by sampling the conditional probabilistic distribution and the corrected numerical prediction series is obtained by iterating the N-LSTM. Experimental results validate that our N-LSTM effectively lifts the accuracy of wave height numerical prediction from SWAN for the Bohai Sea and Xiaomaidao. Furthermore, compared with the state-of-the-art machine learning based prediction methods (e.g., residual learning), the N-LSTM achieves better prediction accuracy by 10% to 20% for the prediction time varying from 3 to 72 h. |
| first_indexed | 2024-03-10T11:35:09Z |
| format | Article |
| id | doaj.art-f51768f5b7494634b3781225df043eb0 |
| institution | Directory Open Access Journal |
| issn | 2077-1312 |
| language | English |
| last_indexed | 2024-03-10T11:35:09Z |
| publishDate | 2021-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Journal of Marine Science and Engineering |
| spelling | doaj.art-f51768f5b7494634b3781225df043eb02023-11-21T18:56:45ZengMDPI AGJournal of Marine Science and Engineering2077-13122021-05-019551410.3390/jmse9050514Ocean Wave Height Series Prediction with Numerical Long Short-Term MemoryXiaoyu Zhang0Yongqing Li1Song Gao2Peng Ren3College of Oceanography and Space Informatics, China University of Petroleum, Qingdao 266580, ChinaCollege of Control Science and Engineering, China University of Petroleum, Qingdao 266580, ChinaNorth Sea Marine Forecast Center of State Oceanic Administration, Qingdao 266061, ChinaCollege of Oceanography and Space Informatics, China University of Petroleum, Qingdao 266580, ChinaThis paper investigates the possibility of using machine learning technology to correct wave height series numerical predictions. This is done by incorporating numerical predictions into long short-term memory (LSTM). Specifically, a novel ocean wave height series prediction framework, referred to as numerical long short-term memory (N-LSTM), is introduced. The N-LSTM takes a combined wave height representation, which is formed of a current wave height measurement and a subsequent Simulating Waves Nearshore (SWAN) numerical prediction, as the input and generates the corrected numerical prediction as the output. The correction is achieved by two modules in cascade, i.e., the LSTM module and the Gaussian approximation module. The LSTM module characterizes the correlation between measurement and numerical prediction. The Gaussian approximation module models the conditional probabilistic distribution of the wave height given the learned LSTM. The corrected numerical prediction is obtained by sampling the conditional probabilistic distribution and the corrected numerical prediction series is obtained by iterating the N-LSTM. Experimental results validate that our N-LSTM effectively lifts the accuracy of wave height numerical prediction from SWAN for the Bohai Sea and Xiaomaidao. Furthermore, compared with the state-of-the-art machine learning based prediction methods (e.g., residual learning), the N-LSTM achieves better prediction accuracy by 10% to 20% for the prediction time varying from 3 to 72 h.https://www.mdpi.com/2077-1312/9/5/514wave height predictionnumerical modellong short-term memory |
| spellingShingle | Xiaoyu Zhang Yongqing Li Song Gao Peng Ren Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory Journal of Marine Science and Engineering wave height prediction numerical model long short-term memory |
| title | Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory |
| title_full | Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory |
| title_fullStr | Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory |
| title_full_unstemmed | Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory |
| title_short | Ocean Wave Height Series Prediction with Numerical Long Short-Term Memory |
| title_sort | ocean wave height series prediction with numerical long short term memory |
| topic | wave height prediction numerical model long short-term memory |
| url | https://www.mdpi.com/2077-1312/9/5/514 |
| work_keys_str_mv | AT xiaoyuzhang oceanwaveheightseriespredictionwithnumericallongshorttermmemory AT yongqingli oceanwaveheightseriespredictionwithnumericallongshorttermmemory AT songgao oceanwaveheightseriespredictionwithnumericallongshorttermmemory AT pengren oceanwaveheightseriespredictionwithnumericallongshorttermmemory |