DENTIFICATION OF VOLCANIC EARTHQUAKE TYPES BASED ON SEISMIC RECORDING DATA FROM MOUNT SINABUNG USING PRINCIPAL COMPONENT ANALYSIS: IDENTIFIKASI JENIS GEMPA VULKANIK BERDASARKAN DATA REKAMAN SEISMIK PADA GUNUNG SINABUNG MENGGUNAKAN PRINCIPAL COMPONENT ANALYSIS

Bagas Anwar Arif Nur; Bambang Heru Iswanto; Mohammad Hasib; Ahmad Basuki

doi:10.21009/03.1301.FA11

Authors

Bagas Anwar Arif Nur Program Studi Fisika, Universitas Negeri Jakarta
Bambang Heru Iswanto Program Studi Fisika, FMIPA Universitas Negeri Jakarta
Mohammad Hasib Pusat Riset Kebencanaan Geologi, Badan Riset dan Inovasi Nasional, Bandung, Indonesia
Ahmad Basuki Pusat Vulkanologi dan Mitigasi Bencana Geologi, Bandung, Indonesia

DOI:

https://doi.org/10.21009/03.1301.FA11

Abstract

Volcanic eruptions are natural events that have the potential for significant damage to humans and the environment. Identifying the type of volcano earthquake is key in disaster risk mitigation by providing information on the process and the location of magma activity beneath the volcano. In this research, we propose an approach using Principal Component Analysis (PCA) to identify types of volcanic earthquakes based on seismic recording data. Identification begins by reducing feature dimensions using Principal Component Analysis (PCA). The PCA results were then clustered and then evaluated Silhoutte Score, ARI, CH-Indeks, DB-Indeks. Experiments were carried out using recorded data totaling 329 samples. For each recording, feature extraction was carried out in the form of statistical features, entropy features and shape features with a total of 16 features in the time and frequency domains. PCA results on the two main components PC1 explained 49.2741% and PC2 24.5507% of the data variance and evaluation results using Silhouette Score were equal to 0.53, ARI 0.8, CH-Index 529.34, and DB- Index 0.6

References

[1] L. C. Gosal, R. C. Tarore, and H. H. Karongkong, “Analisis Spasial Tingkat Kerentanan Bencana Gunung Api Lokon Di Kota Tomohon,” Spasial, vol. 5, no. 2, pp. 229–237, 2018.

[2] A. Nugroho, “Pengembangan model pembelajaran mitigasi bencana gunung meletus di sekolah dasar lereng gunung slamet,” J. Pengabdi. Masy. Multidisiplin, vol. 1, no. 2, pp. 131– 137, 2018.

[3] A. L. Madden-Nadeau et al., “The magmatic and eruptive evolution of the 1883 caldera-forming eruption of Krakatau: Integrating field-to crystal-scale observations,” J. Volcanol.Geotherm. Res., vol. 411, p. 107176, 2021.

[4] T. Trirahayu, “Manajemen bencana erupsi gunung merapi oleh badan penanggulangan bencana daerah kabupaten sleman,” J. Public Policy Adm. Res., vol. 1, no. 6, pp. 1138–1151,2016.

[5] S. B. Kusumayudha, P. Lestari, and E. T. Paripurno, “Eruption characteristic of the sleeping volcano, Sinabung, North Sumatera, Indonesia, and SMS gateway for disaster early warning system,” Indones. J. Geogr., vol. 50, no. 1, pp. 70–77, 2018.

[6] R. S. J. Sparks, J. Biggs, and J. W. Neuberg, “Monitoring volcanoes,” Science (80-. )., vol. 335, no. 6074, pp. 1310–1311, 2012.

[7] M. Hasib et al., “Event classification of volcanic earthquakes based on K-Means clustering: Application on Anak Krakatau Volcano, Sunda Strait,” in IOP Conference Series: Earth and Environmental Science, 2024, p. 12045.

[8] S. R. McNutt and D. C. Roman, “Volcanic seismicity,” in The encyclopedia of volcanoes, Elsevier, 2015, pp. 1011–1034.

[9] E. Program., Global Volcanism. compiled by Venzke, “Sinabung (261080),” [Database] Volcanoes World (v. 5.1.7; 26 Apr 2024).

[10] H. Gunawan et al., “Overview of the eruptions of Sinabung Volcano, 2010 and 2013--present and details of the 2013 phreatomagmatic phase,” J. Volcanol. Geotherm. Res., vol. 382, pp. 103–119, 2019.

[11] M. A. Abdillah, B. H. Iswanto, and H. Suhendar, “EKSTRAKSI FITUR BUNYI KETUKAN BUAH KELAPA BERBASIS POWER-NORMALIZED CEPSTRAL COEFFICIENTS (PNCC),” in PROSIDING SEMINAR NASIONAL FISIKA (E-JOURNAL), 2024.

[12] K. P. Sinaga and M.-S. Yang, “Unsupervised K-means clustering algorithm,” IEEE access, vol. 8, pp. 80716–80727, 2020.

[13] D. Xu and Y. Tian, “A comprehensive survey of clustering algorithms,” Ann. data Sci., vol. 2, pp. 165–193, 2015.

[14] R. Xu and D. Wunsch, “Survey of clustering algorithms,” IEEE Trans. neural networks, vol. 16, no. 3, pp. 645–678, 2005.

[15] A. G. Jondya and B. H. Iswanto, “Indonesian’s traditional music clustering based on audio features,” Procedia Comput. Sci., vol. 116, pp. 174–181, 2017.

[16] F. Pedregosa et al., “Scikit-learn: Machine Learning in {P}ython,” J. Mach. Learn. Res., vol. 12, pp. 2825–2830, 2011