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

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

doi:https://doi.org/10.5194/os-18-419-2022

Articles | Volume 18, issue 2

https://doi.org/10.5194/os-18-419-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/os-18-419-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 18, issue 2

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

Supplement

https://doi.org/10.5194/os-18-419-2022-supplement

Data sets

Meteorological and oceanographic data collected from the National Data Buoy Center Coastal-Marine Automated Network (C-MAN) and moored (weather) buoys, Moored Buoys National Data Buoy Center https://www.ndbc.noaa.gov/

The revised Atlantic hurricane database (HURDAT2) Chris Landsea, James Franklin, and Jack Beven http://www.nhc.noaa.gov/data/hurdat/hurdat2-format-atlantic.pdf

WaveWatch III (WW3) Samoa Regional Wave Model K. F. Cheung https://coastwatch.pfeg.noaa.gov/

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.