Preprints
https://doi.org/10.5194/os-2021-84
https://doi.org/10.5194/os-2021-84

  08 Sep 2021

08 Sep 2021

Review status: this preprint is currently under review for the journal OS.

Forecasting Hurricane-forced Significant Wave Heights using the Long Short-Term Memory Network in the Caribbean Sea

Brandon Justin Bethel1, Wenjin Sun1,2, and Changming Dong1,2,3 Brandon Justin Bethel et al.
  • 1School of Marine Sciences, Nanjing University of Information Science and Technology, Nanjing 210044, China
  • 2Southern Ocean Science and Engineering Guangdong Laboratory (Zhuhai), Zhuhai 519000, China
  • 3Department of Atmospheric and Oceanic Sciences, University of California, Los Angeles, CA 90095, USA

Abstract. A Long Short-Term Memory (LSTM) neural network is proposed to predict hurricane-forced significant wave heights (SWH) in the Caribbean Sea (CS) based on a dataset of 20 CS, Gulf of Mexico, and Western Atlantic hurricane events collected from 10 buoys from 2010–2020. SWH nowcasting and forecasting are initiated using LSTM on 0-, 3-, 6-, 9-, and 12-hour horizons. Through examining study cases Hurricanes Dorian (2019), Sandy (2012), and Igor (2010), results illustrate that the model is well suited to forecast hurricane-forced wave heights. Forecasts are highly accurate with regard to observations. For example, Hurricane Dorian nowcasts had correlation (R), root mean square error (RMSE), and mean absolute percentage error (MAPE) values of 0.99, 0.16 m, and 2.6 %, respectively. Similarly, on the 3-, 6-, 9-, and 12-hour forecasts, results produced R (RMSE; MAPE) values of 0.95 (0.51 m; 7.99 %), 0.92 (0.74 m; 10.83 %), 0.85 (1 m; 13.13 %), and 0.84 (1.24 m; 14.82 %), respectively. However, the model also consistently over-predicted the maximum observed SWHs. To improve models results, additional research should be geared towards improving single-point LSTM neural network training datasets by considering hurricane track and identifying the hurricane quadrant in which buoy observations are made.

Brandon Justin Bethel et al.

Status: open (extended)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on os-2021-84', Anonymous Referee #1, 10 Nov 2021 reply

Brandon Justin Bethel et al.

Brandon Justin Bethel et al.

Viewed

Total article views: 370 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
323 41 6 370 32 2 1
  • HTML: 323
  • PDF: 41
  • XML: 6
  • Total: 370
  • Supplement: 32
  • BibTeX: 2
  • EndNote: 1
Views and downloads (calculated since 08 Sep 2021)
Cumulative views and downloads (calculated since 08 Sep 2021)

Viewed (geographical distribution)

Total article views: 354 (including HTML, PDF, and XML) Thereof 354 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 26 Nov 2021
Download
Short summary
Ocean surface waves forced by tropical cyclones can cause tremendous damage to offshore structures and coastal communities and as such, forecasting their evolution is of the utmost importance. this study investigates the usage of the Long Short-Term Memory neural network to forecast hurricane-forced waves in the Caribbean Sea. Results strongly suggest that forecasts can be performed to a high degree of accuracy up to 12 hours at minimal computational expense.