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.
Highlights
Momentum and mechanical energy are transferred to the ocean’s surface from the overlying atmosphere, giving rise to ubiquitous surface gravity waves and other phenomena, under forcing by tropical cyclones (TC), these waves become extreme
When forecasts are performed on a 3-hour horizon, discrepancies between observations and the forecast have grown significantly larger where at different times, forecasted significant wave heights (SWH) both underestimate and overestimate the observations
The results of this study are in strong agreement with those observed by Meng et al (2021) and Wei (2021) that each found that artificial intelligence (AI) was highly effective at predicting hurricane-induced SWHs
Summary
Momentum and mechanical energy are transferred to the ocean’s surface from the overlying atmosphere, giving rise to ubiquitous surface gravity waves and other phenomena, under forcing by tropical cyclones (TC), these waves become extreme. The study of TC-induced extreme significant wave heights (SWH) is at the current forefront of research and is traditionally accomplished by using an array of numerical models (Shao et al, 2019; Chao et al, 2020; Hu et al, 2020). Performed using these models, they are all disadvantaged in that they all require large investments in high-performance computing resources, technical and scientific expertise, and crucially, time. For the Small Island Developing States and coastal communities of the Caribbean Sea (CS), that have yet to significantly invest in numerical modeling capabilities, other computationally cost-effective measures are required for wave height predictions.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
