Development of a warning model for coastal freak wave occurrences using an artificial neural network

Dong-Jiing Doong, Jen Ping Peng, Ying Chih Chen

Research output: Contribution to journalArticle

2 Citations (Scopus)

Abstract

The potential for coastal freak waves (CFWs) represents a threat to people living in coastal areas. CFWs are generated via the evolution of a wave and its interactions with coastal structures or rocks; however, the exact mechanism of their formation is not clear. Here, a data-driven warning model based on an artificial neural network (ANN) is proposed to predict the possibility of CFW occurrence. Seven parameters (significant wave height, peak period, wind speed, wave groupiness factor, Benjamin Feir Index (BFI), kurtosis, and wind-wave direction misalignment) collected prior to the occurrence of the CFW are used to develop the model. The buoy data associated with 40 known CFW events are used for model training, and the data associated with 23 such events are used for validation. The use of data obtained during the 6-h period prior to CFW occurrence combined with the same amount of non-CFW data is shown to produce the best model. Two validations using media-published and camera-recorded CFW events show that the accuracy rate (ACR) exceeds 90% and the recall rate (RCR) exceeds 87%, demonstrating the accuracy of the proposed model. This warning model has been implemented in operational runs since 2016.

Original languageEnglish
Pages (from-to)270-280
Number of pages11
JournalOcean Engineering
Volume169
DOIs
Publication statusPublished - 2018 Dec 1

Fingerprint

Neural networks
Cameras
Rocks

All Science Journal Classification (ASJC) codes

  • Environmental Engineering
  • Ocean Engineering

Cite this

@article{16fa1857fc724041b6748c8833186c87,
title = "Development of a warning model for coastal freak wave occurrences using an artificial neural network",
abstract = "The potential for coastal freak waves (CFWs) represents a threat to people living in coastal areas. CFWs are generated via the evolution of a wave and its interactions with coastal structures or rocks; however, the exact mechanism of their formation is not clear. Here, a data-driven warning model based on an artificial neural network (ANN) is proposed to predict the possibility of CFW occurrence. Seven parameters (significant wave height, peak period, wind speed, wave groupiness factor, Benjamin Feir Index (BFI), kurtosis, and wind-wave direction misalignment) collected prior to the occurrence of the CFW are used to develop the model. The buoy data associated with 40 known CFW events are used for model training, and the data associated with 23 such events are used for validation. The use of data obtained during the 6-h period prior to CFW occurrence combined with the same amount of non-CFW data is shown to produce the best model. Two validations using media-published and camera-recorded CFW events show that the accuracy rate (ACR) exceeds 90{\%} and the recall rate (RCR) exceeds 87{\%}, demonstrating the accuracy of the proposed model. This warning model has been implemented in operational runs since 2016.",
author = "Dong-Jiing Doong and Peng, {Jen Ping} and Chen, {Ying Chih}",
year = "2018",
month = "12",
day = "1",
doi = "10.1016/j.oceaneng.2018.09.029",
language = "English",
volume = "169",
pages = "270--280",
journal = "Ocean Engineering",
issn = "0029-8018",
publisher = "Elsevier BV",

}

Development of a warning model for coastal freak wave occurrences using an artificial neural network. / Doong, Dong-Jiing; Peng, Jen Ping; Chen, Ying Chih.

In: Ocean Engineering, Vol. 169, 01.12.2018, p. 270-280.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Development of a warning model for coastal freak wave occurrences using an artificial neural network

AU - Doong, Dong-Jiing

AU - Peng, Jen Ping

AU - Chen, Ying Chih

PY - 2018/12/1

Y1 - 2018/12/1

N2 - The potential for coastal freak waves (CFWs) represents a threat to people living in coastal areas. CFWs are generated via the evolution of a wave and its interactions with coastal structures or rocks; however, the exact mechanism of their formation is not clear. Here, a data-driven warning model based on an artificial neural network (ANN) is proposed to predict the possibility of CFW occurrence. Seven parameters (significant wave height, peak period, wind speed, wave groupiness factor, Benjamin Feir Index (BFI), kurtosis, and wind-wave direction misalignment) collected prior to the occurrence of the CFW are used to develop the model. The buoy data associated with 40 known CFW events are used for model training, and the data associated with 23 such events are used for validation. The use of data obtained during the 6-h period prior to CFW occurrence combined with the same amount of non-CFW data is shown to produce the best model. Two validations using media-published and camera-recorded CFW events show that the accuracy rate (ACR) exceeds 90% and the recall rate (RCR) exceeds 87%, demonstrating the accuracy of the proposed model. This warning model has been implemented in operational runs since 2016.

AB - The potential for coastal freak waves (CFWs) represents a threat to people living in coastal areas. CFWs are generated via the evolution of a wave and its interactions with coastal structures or rocks; however, the exact mechanism of their formation is not clear. Here, a data-driven warning model based on an artificial neural network (ANN) is proposed to predict the possibility of CFW occurrence. Seven parameters (significant wave height, peak period, wind speed, wave groupiness factor, Benjamin Feir Index (BFI), kurtosis, and wind-wave direction misalignment) collected prior to the occurrence of the CFW are used to develop the model. The buoy data associated with 40 known CFW events are used for model training, and the data associated with 23 such events are used for validation. The use of data obtained during the 6-h period prior to CFW occurrence combined with the same amount of non-CFW data is shown to produce the best model. Two validations using media-published and camera-recorded CFW events show that the accuracy rate (ACR) exceeds 90% and the recall rate (RCR) exceeds 87%, demonstrating the accuracy of the proposed model. This warning model has been implemented in operational runs since 2016.

UR - http://www.scopus.com/inward/record.url?scp=85054684603&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85054684603&partnerID=8YFLogxK

U2 - 10.1016/j.oceaneng.2018.09.029

DO - 10.1016/j.oceaneng.2018.09.029

M3 - Article

AN - SCOPUS:85054684603

VL - 169

SP - 270

EP - 280

JO - Ocean Engineering

JF - Ocean Engineering

SN - 0029-8018

ER -