Articles | Volume 18, issue 2
https://doi.org/10.5194/os-18-419-2022
https://doi.org/10.5194/os-18-419-2022
Research article
 | 
28 Mar 2022
Research article |  | 28 Mar 2022

Forecasting hurricane-forced significant wave heights using a long short-term memory network in the Caribbean Sea

Brandon J. Bethel, Wenjin Sun, Changming Dong, and Dongxia Wang

Download

Interactive discussion

Status: closed

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
    • AC1: 'Reply on RC1', Brandon Bethel, 10 Dec 2021
  • RC2: 'Comment on os-2021-84', Anonymous Referee #2, 05 Dec 2021
    • AC2: 'Reply on RC2', Brandon Bethel, 10 Dec 2021
  • EC1: 'Comment on os-2021-84', Andrew Moore, 10 Dec 2021
    • AC3: 'Reply on EC1', Brandon Bethel, 11 Dec 2021
    • AC4: 'Reply on EC1', Brandon Bethel, 11 Dec 2021

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision
AR by Brandon Bethel on behalf of the Authors (10 Dec 2021)  Author's response    Author's tracked changes
ED: Referee Nomination & Report Request started (03 Jan 2022) by Andrew Moore
RR by Anonymous Referee #2 (17 Jan 2022)
RR by Anonymous Referee #1 (27 Jan 2022)
ED: Publish as is (06 Feb 2022) by Andrew Moore
Download
Short summary
Ocean surface waves forced by tropical cyclones can cause tremendous damage to offshore structures and coastal communities. As such, forecasting their evolution is of utmost importance. This study investigates the usage of a 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 h at minimal computational expense and even outperform a wave model.