Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal IJOCE (International Journal of Offshore and Coastal Engineering)
Fajar Sebastian
Unknown Affiliation
Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Wave Simulation Based Recurrent Neural Network Long-Short Term Memory (RNN-LSTM) Wimala Lalitya Dhanistha; Fajar Sebastian; Haryo Dwito Armono
International Journal of Offshore and Coastal Engineering Vol. 10 No. 1 (2026):
Publisher : Department of Ocean Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962//j225800914.v10i1.9913

Abstract

The Recurrent Neural Network Long-Short Term Memory (RNN-LSTM) algorithm was used to perform 6-hour time series forecasting for the variables significant wave height (Hs), maximum wave height (Hmax), zero-crossing period (Tz), and peak period (Tp) in a sea wave simulation using five datasets, each with a duration of ten years and from various locations. The ability of the RNN-LSTM algorithm to simulate sequential data, including time series, led to its selection. According to the research findings, the five RNN LSTM simulations produced fairly good forecasts for Tz (MAPE below 11%) and good forecasts for Hs and Hmax (MAPE below 9%). However, they had trouble simulating Tp (MAPE up to 34.06%). The tendency for Tp data to have a higher standard deviation (up to 2) than other variables and Tp's lower correlation with the other variables are factors that make Tp forecasting challenging. We find that RNN-LSTM can forecast Tp with moderate accuracy, but it can produce dependable forecasts for Hs, Hmax, and Tz
Co-Authors Haryo Dwito Armono Wimala Lalitya Dhanistha