Prediksi Gelombang Laut Menggunakan Jaringan Saraf Tiruan

Firmansyah, Hikmal Akbar Firmansyah (2026) Prediksi Gelombang Laut Menggunakan Jaringan Saraf Tiruan. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5020221082_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (3MB) | Request a copy

Abstract

Perairan Semarang sebagai bagian dari Laut Jawa merupakan jalur pelayaran strategis yang menghubungkan pelabuhan-pelabuhan utama di Jawa dengan wilayah Indonesia Timur, namun memiliki karakteristik gelombang yang dinamis dan berpotensi membahayakan keselamatan pelayaran. Gelombang tinggi di perairan ini telah menyebabkan beberapa kecelakaan maritim dalam beberapa tahun terakhir, sehingga prediksi parameter gelombang yang akurat menjadi kebutuhan penting untuk mendukung keselamatan pelayaran. Penelitian ini mengembangkan model prediksi time series gelombang laut menggunakan metode Jaringan Saraf Tiruan (JST) dengan arsitektur feedforward Multi-Layer Perceptron (MLP) multi-input multi-output untuk memprediksi empat parameter gelombang secara simultan, yaitu tinggi gelombang signifikan (Hs), tinggi gelombang maksimum (Hmax), periode lintas nol (Tz), dan periode puncak (Tp) di Perairan Semarang. Data yang digunakan merupakan data reanalysis ERA5 dari European Centre for Medium-Range Weather Forecasts (ECMWF). Model dievaluasi menggunakan metrik Mean Absolute Percentage Error (MAPE) dengan target MAPE <= 50% sebagai indikator kelayakan model untuk aplikasi operasional. Hasil penelitian menunjukkan bahwa model JST mampu memprediksi keempat parameter gelombang secara simultan pada berbagai forecast horizon (3 jam, 6 jam, 12 jam, dan 24 jam ke depan) dengan performa yang baik. Model ini diharapkan dapat diintegrasikan ke dalam sistem peringatan dini keselamatan navigasi pelayaran di Perairan Semarang dengan memberikan informasi prediksi kondisi gelombang berbahaya (Hs > 2 meter) beberapa jam ke depan, sehingga dapat mendukung pengambilan keputusan operasional pelayaran dan mengurangi risiko kecelakaan maritim di wilayah tersebut.
================================================================================================================================
Semarang waters as part of the Java Sea are a strategic shipping lane connecting major ports in Java with Eastern Indonesia, but have dynamic wave characteristics and have the potential to endanger shipping safety. High waves in these waters have caused several maritime accidents in recent years, so accurate wave parameter prediction is a crucial need to support shipping safety. This study develops a time series prediction model of ocean waves using the Artificial Neural Network (ANN) method with a multi-input multi-output feedforward Multi-Layer Perceptron (MLP) architecture to predict four wave parameters simultaneously, namely significant wave height (Hs), maximum wave height (Hmax), zero crossing period (Tz), and peak period (Tp) in Semarang waters. The data used is ERA5 reanalysis data from the European Centre for Medium-Range Weather Forecasts (ECMWF). The model is evaluated using the Mean Absolute Percentage Error (MAPE) metric with a MAPE target of <= 50% as an indicator of model feasibility for operational applications. The results of the study indicate that the ANN model is able to predict all four wave parameters simultaneously at various forecast horizons (3 hours, 6 hours, 12 hours, and 24 hours ahead) with good performance. This model is expected to be integrated into the early warning system for navigation safety in Semarang Waters by providing information on predictions of dangerous wave conditions (Hs > 2 meters) several hours in advance, thereby supporting operational decision-making in shipping and reducing the risk of maritime accidents in the region.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Kata kunci : Jaringan Saraf Tiruan, Prediksi Gelombang Laut, Time Series Forecasting, Tinggi Gelombang Signifikan, Perairan Semarang Keywords: Artificial Neural Network, Ocean Wave Prediction, Time Series Forecasting, Significant Wave Height, Semarang Waters
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.
Divisions:	Faculty of Marine Technology (MARTECH) > Ocean Engineering > 38201-(S1) Undergraduate Thesis
Depositing User:	Hikmal Akbar Firmansyah
Date Deposited:	21 Jul 2026 08:49
Last Modified:	21 Jul 2026 08:49
URI:	http://repository.its.ac.id/id/eprint/135829

Actions (login required)

View Item