Machine learning on waveform spectral analysis of nuclear explosion from broadband seismic station in Indonesia

Abstract

Machine learning of seismic waveform is core component to realize the characteristics of signal. The nuclear explosion is Wavelet signal processing is broadly used for analysis of real time seismic signal. The numerous wavelet filters are developed by spectral synthesis using machine learning python to realize the signal characteristics. Our paper aims to solve and evaluating the frequencies-energy characteristic of nuclear explosion. The wavelet method by Continuous Wavelet Transform (CWT) is clearly to identify of amplitudes and frequency-energy from component of nuclear test performed by the North Korea that occurred on September 03, 2017. Finally, by machine learning python with Morlet wavelet allows good time resolution for identified and performed of Broadband Seismic from Comprehensive Nuclear-Test Ban Treaty Organization (CTBTO) in Indonesia.