Discrimination between Earthquake P Waves and Microtremors via a Generative Adversarial Network

Abstract

The accurate and reliable discrimination of earthquakes from background noise is a primary task of earthquake early warning (EEW); however, ubiquitous and complex microtremor signals substantially complicate this task. To mitigate this problem, a generative adversarial network (GAN) is adopted to distinguish between earthquakes and microtremors in this study. We train a GAN based on 52,537 K-NET and KiK-net strong ground motion records from Japan, and use the well-trained discriminator to identify 5373 P waves and 5373 microtremors in the testing set. The results indicate that this algorithm can correctly identify 99.89% of P waves and 99.24% of microtremors with high confidence. In addition, a verification of the proposed algorithm on data from the Great East Japan earthquake confirms that this model can achieve robust results for local records of large events and ultimately discriminate earthquakes from microtremors. This algorithm is an exploratory test of a GAN for identifying earthquake P waves. Though the GAN uses only P waves for training (There are no microtremors in the input data.), it has extensive potential in seismological and EEW applications.

Recent advances in earthquake seismology using machine learning

“…Recently, this has been approached using ML techniques, such as random forest (Hu et al 2023), CNN (Jozinović et al 2020;Zhang et al 2022b), support vector machine , Graph Neural Network (Bloemheuvel et al 2022), and LSTM (Wang et al 2022b(Wang et al , 2023a. Additionally, ML has been applied to discriminate in real-time whether a signal stems from an actual earthquake based on the initial part of ground motions (Li et al 2018;Meier et al 2019;Liu et al 2022). Although these studies adopted a single-station approach where inputs and outputs were closed at one station, Münchmeyer et al (2020) proposed a multiple-station approach that predicts final PGA values at multiple target stations using initial raw records at multiple input stations.…”