English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools annual

Global: Zendy Free Plan

Global: Zendy Tools monthly

Global: Zendy Plus monthly

. A long short-term memory (LSTM) neural network isproposed to predict hurricane-forced significant wave heights (SWHs) in theCaribbean Sea (CS) based on a dataset of 20 CS, Gulf of Mexico, and westernAtlantic hurricane events collected from 10 buoys from 2010–2020. SWHnowcasting and forecasting are initiated using LSTM on 0, 3, 6, 9, and12 h horizons. Through examining study cases Hurricanes Dorian (2019),Sandy (2012), and Igor (2010), results illustrate that the model is wellsuited to forecast hurricane-forced wave heights much morerapidly at a significantly cheaper computational cost compared tonumerical wave models, with much less required expertise. Forecasts arehighly accurate with regards to observations. For example, Hurricane Doriannowcasts had correlation (R), root mean square error (RMSE), and meanabsolute percentage error (MAPE) values of 0.99, 0.16 m, and 2.6 %,respectively. Similarly, on the 3, 6, 9, and 12 h forecasts, resultsproduced 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. In general, the model can provide accurate predictions within12 h (R≥0.8) and errors can be maintained at under 1 m within6 h of forecast lead time. However, the model also consistentlyoverpredicted the maximum observed SWHs. From a comparison of LSTM with athird-generation wave model, Simulating Waves Nearshore (SWAN), it wasdetermined that when using Hurricane Dorian as a case example, nowcasts werefar more accurate with regards to the observations. This demonstrates thatLSTM can be used to supplement, but perhaps not replace, computationallyexpensive numerical wave models for forecasting extreme wave heights. Assuch, addressing the fundamental problem of phase shifting and other errorsin LSTM or other data-driven forecasting should receive greater scrutinyfrom Small Island Developing States. To improve models results, additionalresearch should be geared towards improving single-point LSTM neural networktraining datasets by considering hurricane track and identifying thehurricane quadrant in which buoy observations are made.

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