ONE DAY AHEAD WAVE PREDICTIONS USING A HYBRID ALGORITHM OF LONG-SHORT TERM MEMORY AND NEURAL NETWORK FOR MARINE CONSTRUCTIONS
ICCE 2022
DOC

How to Cite

Kim, S., Takeda, M., Hara, C., & Mase, H. (2023). ONE DAY AHEAD WAVE PREDICTIONS USING A HYBRID ALGORITHM OF LONG-SHORT TERM MEMORY AND NEURAL NETWORK FOR MARINE CONSTRUCTIONS. Coastal Engineering Proceedings, (37), waves.26. https://doi.org/10.9753/icce.v37.waves.26

Abstract

Recently, marine construction work has increased under complex and strict conditions for large-scale marine sites and facilities. Accurate wave information at the work site is critical to conducting the marine construction safely. In particular, making decisions for the execution of the operation need a significant wave height ranging from 0.5 to 1.0 m as a threshold. However, studies on highly accurate real-time wave height predictions around the threshold are few. The present study developed a hybrid algorithm for real-time wave prediction by combining long-short term memory (LSTM) and artificial neural network (ANN) for the Hitachinaka Port, Japan.
https://doi.org/10.9753/icce.v37.waves.26
DOC
Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

Copyright (c) 2023 Sooyoul Kim, Masahide Takeda, Chisato Hara, Hajime Mase