Prediksi Gelombang Menggunakan RNN-LSTM dalam Mendukung Keselamatan Operasi Maritim di Nusa Tenggara Barat

Pratama, Raihan Hekta (2026) Prediksi Gelombang Menggunakan RNN-LSTM dalam Mendukung Keselamatan Operasi Maritim di Nusa Tenggara Barat. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5020221059-Undergraduated_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (4MB) | Request a copy

Abstract

Nusa Tenggara Barat (NTB) merupakan salah satu pusat pariwisata bahari strategis di Indonesia dengan aktivitas operasi maritim yang tinggi. Karakteristik gelombang yang kompleks dan variatif serta masih tingginya angka kecelakaan laut akibat gelombang tinggi menjadi latar belakang pentingnya sistem prediksi gelombang yang akurat dan real-time untuk mendukung keselamatan maritim di NTB. Penelitian ini mengembangkan model prediksi gelombang menggunakan metode RNN-LSTM di dua lokasi dengan kondisi oseanografi berbeda, yaitu Pantai Kuta, Lombok Selatan sebagai representasi perairan terbuka dan Gili Trawangan sebagai representasi perairan semi-tertutup. Data yang digunakan adalah data reanalisis ERA5 dari ECMWF dengan rentang waktu 10 tahun (2015–2024), mencakup tinggi gelombang signifikan (Hs), tinggi gelombang maksimum (Hmax), periode puncak (Tp), dan periode lintas nol (Tz). Model dirancang dengan matriks input X berukuran [30, 4] yang merepresentasikan 30 timestep sekarang dan masa lalu dengan 4 variabel gelombang, serta matriks output Y berukuran [1, 4] yang merepresentasikan 1 timestep di masa depan. Dataset dibagi menjadi training (81.7%%), validasi (17,5%), dan testing (0,8%). Evaluasi model menggunakan metrik MAPE dengan batas maksimum MAPE sebesar 50%. Prediksi operasional dilakukan secara rolling forecast. Hasil penelitian ini diharapkan berkontribusi dalam pengembangan metode machine learning untuk prediksi oseanografi di Indonesia serta menjadi dasar pengembangan sistem peringatan dini untuk mendukung keselamatan operasi maritim di NTB.
======================================================================================================================================
West Nusa Tenggara (NTB) is one of Indonesia's strategic marine tourism centers with high maritime operational activities. The complex and variable wave characteristics combined with the persistently high rate of maritime accidents caused by high waves underscore the urgent need for an accurate and real-time wave prediction system to support maritime safety in NTB. This study develops a wave prediction model RNN-LSTM at two locations with contrasting oceanographic conditions: Kuta Beach, South Lombok representing open water, and Gili Trawangan representing semi-enclosed water. ERA5 reanalysis data from ECMWF spanning 10 years (2015–2024) is used, covering significant wave height (Hs), maximum wave height (Hmax), peak period (Tp), and zero-crossing period (Tz). The model is designed with input matrix X of [30, 4] representing 30 current and past timesteps with 4 wave variables, and output matrix Y of [1, 4] representing 1 future timestep. The dataset is split into training (81,7%), validation (17,5%), and testing (0,8%). Model performance is evaluated using MAPE with a maximum MAPE threshold of 50% based on the WMO 1998 standard. Operational predictions are performed using a rolling forecast approach. The results are expected to contribute to the development of machine learning-based oceanographic prediction in Indonesia and serve as a foundation for early warning systems to support maritime operational safety in NTB.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	RNN-LSTM, prediksi gelombang, Nusa Tenggara Barat, Lombok Selatan, Gili Trawangan, keselamatan maritim, RNN-LSTM, wave prediction, West Nusa Tenggara, South Lombok, Gili Trawangan, maritime safety
Subjects:	Q Science > QA Mathematics > QA336 Artificial Intelligence T Technology > T Technology (General) > T174 Technological forecasting T Technology > TC Hydraulic engineering. Ocean engineering T Technology > TC Hydraulic engineering. Ocean engineering > TC147 Ocean wave power. T Technology > TC Hydraulic engineering. Ocean engineering > TC424 Water levels
Divisions:	Faculty of Marine Technology (MARTECH) > Ocean Engineering > 38201-(S1) Undergraduate Thesis
Depositing User:	Raihan Hekta Pratama
Date Deposited:	21 Jul 2026 01:26
Last Modified:	21 Jul 2026 01:26
URI:	http://repository.its.ac.id/id/eprint/135846

Actions (login required)

View Item