PEMODELAN PREDIKSI MAGNITUDO GEMPA BUMI DI INDONESIA BERDASARKAN DATA SPASIAL DAN TEMPORAL MENGGUNAKAN ALGORITMA RANDOM FOREST DAN NEURAL NETWORKS

Safitri, Marsya Adinda (2025) PEMODELAN PREDIKSI MAGNITUDO GEMPA BUMI DI INDONESIA BERDASARKAN DATA SPASIAL DAN TEMPORAL MENGGUNAKAN ALGORITMA RANDOM FOREST DAN NEURAL NETWORKS. S1 thesis, Universitas Mercu Buana Jakarta.

Preview	Text (HAL COVER) 01 COVER.pdf Download (562kB) | Preview
	Text (BAB I) 02 BAB 1.pdf Restricted to Registered users only Download (371kB)
	Text (BAB II) 03 BAB 2.pdf Restricted to Registered users only Download (462kB)
	Text (BAB III) 04 BAB 3.pdf Restricted to Registered users only Download (352kB)
	Text (BAB IV) 05 BAB 4.pdf Restricted to Registered users only Download (415kB)
	Text (BAB V) 06 BAB 5.pdf Restricted to Registered users only Download (149kB)
	Text (DAFTAR PUSTAKA) 07 DAFTAR PUSTAKA.pdf Restricted to Registered users only Download (256kB)
	Text (LAMPIRAN) 08 LAMPIRAN.pdf Restricted to Registered users only Download (338kB)

Abstract

Indonesia is one of the countries with the highest seismic activity in the world due to its location at the convergence of three major tectonic plates. This condition highlights the urgency of earthquake prediction research as a crucial element for disaster mitigation and the development of early warning systems. This study aims to construct a predictive model of earthquake magnitude in Indonesia by utilizing spatial variables (latitude, longitude, depth, phasecount, azimuth gap) and temporal variables (year, month, day, hour) through a machine learning approach. Two main algorithms were employed, namely the Random Forest Regressor and Neural Network (Multilayer Perceptron/MLP). The research process included data preprocessing (handling missing values and duplicates), normalization, dataset splitting, model training, and evaluation using regression metrics (MAE, MSE, RMSE, and R²). The findings indicate that both models are capable of producing reliable predictions, with the Neural Network generally outperforming Random Forest in terms of accuracy. A simulation for the year 2026 shows predicted magnitudes ranging from 1.7 to 2.3 on the Richter Scale, which fall into the minor earthquake category and are unlikely to cause significant impact. These results emphasize the potential of machine learning as a supporting tool for disaster mitigation in Indonesia, while also underscoring the need for further model refinement to enhance predictive performance. Keywords : earthquake, machine learning, Random Forest, Neural Network, magnitude prediction. Indonesia merupakan salah satu negara dengan tingkat aktivitas seismik tertinggi di dunia akibat posisinya yang berada pada pertemuan tiga lempeng tektonik utama. Kondisi ini menjadikan penelitian terkait prediksi gempa bumi sebagai kebutuhan penting, baik untuk mitigasi bencana maupun penguatan sistem peringatan dini. Penelitian ini bertujuan membangun model prediksi magnitudo gempa bumi di Indonesia dengan memanfaatkan data spasial (latitude, longitude, depth, phasecount, azimuth gap) dan temporal (tahun, bulan, hari, jam) menggunakan pendekatan machine learning. Dua algoritma utama digunakan, yaitu Random Forest Regressor dan Neural Network (Multilayer Perceptron/MLP). Tahapan penelitian meliputi pengolahan data awal (penanganan missing values dan duplikat), normalisasi, pembagian dataset, pemodelan, serta evaluasi menggunakan metrik regresi (MAE, MSE, RMSE, dan R²). Hasil penelitian menunjukkan bahwa kedua model mampu melakukan prediksi dengan tingkat akurasi yang memadai, di mana Neural Network cenderung menghasilkan performa lebih baik dibandingkan Random Forest. Simulasi prediksi untuk tahun 2026 menunjukkan rentang magnitudo 1,7–2,3 SR, yang termasuk kategori gempa kecil dan tidak menimbulkan dampak signifikan. Temuan ini menegaskan bahwa pendekatan machine learning berpotensi menjadi instrumen penting dalam mendukung upaya mitigasi bencana di Indonesia, meskipun masih diperlukan pengembangan lebih lanjut untuk meningkatkan akurasi dan cakupan prediksi. Kata kunci : gempa bumi, machine learning, Random Forest, Neural Network, prediksi magnitudo.

Item Type:	Thesis (S1)
Call Number CD:	FIK/SI. 25 101
NIM/NIDN Creators:	41821010113
Uncontrolled Keywords:	gempa bumi, machine learning, Random Forest, Neural Network, prediksi magnitudo.
Subjects:	000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.31 Machine Learning/Pembelajaran Mesin 000 Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 000. Computer Science, Information and General Works/Ilmu Komputer, Informasi, dan Karya Umum > 006 Special Computer Methods/Metode Komputer Tertentu > 006.3 Artificial Intelligence/Kecerdasan Buatan > 006.32 Neural Nets (Neural Network)/Jaringan Saraf Buatan 500 Natural Science and Mathematics/Ilmu-ilmu Alam dan Matematika > 510 Mathematics/Matematika > 518 Numerical Analysis/Analisis Numerik, Analisa Numerik > 518.1 Algorithms/Algoritma
Divisions:	Fakultas Ilmu Komputer > Sistem Informasi
Depositing User:	khalimah
Date Deposited:	24 Sep 2025 07:55
Last Modified:	24 Sep 2025 07:55
URI:	http://repository.mercubuana.ac.id/id/eprint/98441

Actions (login required)

View Item