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

Cited articles

Ali, M. and Prasad, R.: SWH forecasting via an extreme learning machine model integrated with improved complete ensemble empirical mode decomposition, Renew. Sustain. Energy Rev., 104, 281–295,, 2019. 
Alina, A. I., Rusu, L., and Catalin, A.: Nearshore Wave Dynamics at Mangalia Beach Simulated by Spectral Models, J. Mar. Sci. Eng., 7, 206,, 2019. 
Allahdadi, M. N., He, R., and Neary, V. S.: Predicting ocean waves along the US east coast during energetic winter storms: sensitivity to whitecapping parameterizations, Ocean Sci., 15, 691–715,, 2019. 
Arzani, A., Wang, J., and D'Souza, R. M.: Uncovering near-wall blood flow from sparse data with physics-informed neural networks, Phys. Fluids, 33, 071905,, 2021. 
Avila-Alonso, D., Baetens, J. M., Cardenas, R., and De Baets, B.: Oceanic response to the consecutive Hurricanes Dorian and Humberto (2019) in the Sargasso Sea, Nat. Hazards Earth Syst. Sci., 21, 837–859,, 2021. 
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.