Optimasi XGBoost Menggunakan Grey Wolf Optimizer untuk Klasifikasi Status Gempa Bumi di Indonesia

Wisnu Aji Sanjaya

Abstract


Klasifikasi status gempa bumi diperlukan untuk mendukung analisis kejadian gempa secara cepat dan akurat. Penelitian ini melakukan perbandingan performa algoritma Random Forest dan XGBoost serta mengoptimalkan hyperparameter menggunakan Grey Wolf Optimizer (GWO). Dataset yang digunakan berasal dari katalog gempa BMKG periode 2008–2025 dengan variabel lokasi, kedalaman, magnitudo, dan waktu kejadian. Hasil penelitian menunjukkan bahwa Random Forest dan XGBoost memperoleh accuracy sebesar 73%. Setelah dilakukan optimasi, GWO-Random Forest mencapai accuracy sebesar 74%, sedangkan GWO-XGBoost menjadi model terbaik dengan accuracy 75%, precision 75%, recall 74%, macro F1-score 74%, dan AUC 0,820. Hasil tersebut menunjukkan bahwa GWO mampu meningkatkan performa klasifikasi status gempa bumi.


Keywords


BMKG; Grey Wolf Optimizer; Klasifikasi Gempa; Random Forest; XGBoost.

References


I. Keilmuan, “PEMETAAN DAN ANALISIS DISTRIBUSI GEMPA BUMI PADA WILAYAH PUSAT GEMPA REGIONAL (PGR) IV MAKASSAR,” Sains,Teknologi, Integr. Keilmuan dan Komput., vol. 3, no. 4, pp. 179–186, 2025.

S. Wahyuningsi, A. Budianta, R. Awalia, and R. Mardin, “Arahan Mitigasi Terhadap Penurunan Tingkat Risiko Bencana Gempabumi Pada Permukiman Di Sekitar Jalur Sesar Palu ‐ Koro,” J. Urban Reg. Plan. Tadulako, vol. 3, pp. 71–81, 2024, doi: https://doi.org/10.22487/peweka.v3i1.32.

I. Hanif, C. Sulaiman, and A. Zaenudin, “Seminar Nasional Ilmu Teknik dan Aplikasi Industri Mikrozonasi Potensi Bahaya Gempa Bumi Daerah Singaraja Berdasarkan Analisis Studi Mikrotremor,” SeminarNasionalIlmuTeknikdanAplikasiIndustri, vol. 7, no. 2024, pp. 149–158, 2025, doi: https://doi.org/10.23960/prosidingsinta.v7i.155.

M. P. Isken et al., “Qseek : A Data-Driven Framework for Automated Earthquake Detection , Localization and Characterization,” Seismica, vol. 4, 2025, doi: 10.26443/seismica.v4i1.1283.

M. Cocco et al., “Fracture Energy and Breakdown Work During Earthquakes,” Annu. Rev. Earth Planet. Sci., vol. 51, pp. 217–252, 2023, doi: https://doi.org/10.1146/annurev-earth-071822-100304.

N. H. Fahim, A. U. Muhib, R. A. Tanvir, and A. Al Noman, “Real-Time Earthquake Magnitude Classification from Initial P-Waves : Models , Dataset , and Comparative Analysis for South Asia,” 2025 28th Int. Conf. Comput. Inf. Technol., 2025, doi: 10.1109/ICCIT68739.2025.11489542.that.

A. Navarro-rodríguez et al., “Recent Advances in Early Earthquake Magnitude Estimation by Using Machine Learning Algorithms: A Systematic Review,” Appl. Sci., vol. 15, no. 7, pp. 1–33, 2025, doi: https://doi.org/10.3390/app15073492.

Y. Zhao, S. Lv, and P. Liu, “Advances in Earthquake Prevention and Reduction Based on Machine Learning : A Scoping Review,” IEEE Access, vol. 12, no. October, pp. 143908–143929, 2024, doi: 10.1109/ACCESS.2024.3467149.

M. Sun, J. Yang, C. Yang, and W. Wang, “Heliyon Research on prediction of PPV in open-pit mine used RUN-XGBoost model,” Heliyon, vol. 10, no. 7, p. e28246, 2024, doi: 10.1016/j.heliyon.2024.e28246.

Y. Hu, W. Wang, L. Li, and F. Wang, “Applying Machine Learning to Earthquake Engineering : A Scientometric Analysis of World Research,” buildings, vol. 14, no. 5, 2024, doi: https://doi.org/10.3390/buildings14051393.

A. Ismail, A. S. A. Rashid, T. Amhadi, R. Nazir, M. Irsyam, and L. Faizal, “Exploring the Evolution of Seismic Hazard and Risk Assessment Research : A Bibliometric Analysis,” Sustain., vol. 16, no. 7, 2024, doi: https://doi.org/10.3390/su16072687.


Refbacks

  • There are currently no refbacks.


Editorial Office :

Prosiding SENDIKO (Seminar Nasional Hasil Penelitian & Pengabdian Masyarakat Bidang Ilmu Komputer)
Published by Universitas PGRI Madiun
Managed by Program Studi Sistem Informasi Fakultas Teknik Universitas PGRI Madiun
Address Jl. Auri 14-16 Kota Madiun Kampus III Universitas PGRI Madiun 63118
Website http://prosiding.unipma.ac.id/index.php/sendiko/index
Email [email protected]

e-ISSN:  3025-4604