Classification of Seismic Signals by Evaluating Broadband Network Station in Sumatera Fore-ARC
Marzuki Sinambela1, Kerista Tarigan1, Syahrul Humaidi1, Marhaposan Situmorang1
1Department of Physics, FMIPA, Universitas Sumatera Utara, Jl. Bioteknologi No.1, Padang Bulan, Kec. Medan Baru, Medan, Sumatera Utara 20155, Indonesia
Abstract
Classification of seismic signal waveform is an essential component to realize the characteristics of the signal. The processing of the waveform signal is broadly used for the analysis of the real-time seismic signal. The numerous wavelet filters are developed by spectral synthesis using machine learning python to realize the signal characteristics. Our research aims to generate the performance of seismic signal and processing the waveform from Broadband Network Station by using Wavelet-Based on Machine Learning. In this case, we use Continuous Wavelet Transform (CWT) on Morlet to evaluate and classification the Phase in Tarutung earthquakes January 2019. CWT is also clearly to identify spectral amplitudes and frequency-energy from the component of signal seismic performed by Broadband Network in Indonesia. The characteristic of the digital broadband network in Sumatera Fore-Arc is variance. Our study tries to classification and evaluate the Broadband Seismic Network which deployed in Sumatera Region, Indonesia by using Power Spectral Density Probability Density Function (PSDPDF).
Keywords: Classification, Machine Learning, Morlet, Broadband Network, PSDPDF
Topic: Big Data, Database System, Data Mining and Web Mining