Premium
SeismoGen: Seismic Waveform Synthesis Using GAN With Application to Seismic Data Augmentation
Author(s) -
Wang Tiantong,
Trugman Daniel,
Lin Youzuo
Publication year - 2021
Publication title -
journal of geophysical research: solid earth
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.983
H-Index - 232
eISSN - 2169-9356
pISSN - 2169-9313
DOI - 10.1029/2020jb020077
Subject(s) - computer science , synthetic data , waveform , set (abstract data type) , data set , task (project management) , data mining , data quality , training set , machine learning , noise (video) , quality (philosophy) , artificial intelligence , event (particle physics) , image (mathematics) , engineering , telecommunications , metric (unit) , radar , operations management , philosophy , systems engineering , epistemology , programming language , physics , quantum mechanics
Detecting earthquake arrivals within seismic time series can be a challenging task. Visual, human detection has long been considered the gold standard but requires intensive manual labor that scales poorly to large data sets. In recent years, automatic detection methods based on machine learning have been developed to improve the accuracy and efficiency. However, the accuracy of those methods relies on access to a sufficient amount of high‐quality labeled training data, often tens of thousands of records or more. We aim to resolve this dilemma by answering two questions: (1) provided with a limited amount of reliable labeled data, can we use them to generate additional, realistic synthetic waveform data? and (2) can we use those synthetic data to further enrich the training set through data augmentation, thereby enhancing detection algorithms? To address these questions, we use a generative adversarial network (GAN), a type of machine learning model which has shown supreme capability in generating high‐quality synthetic samples in multiple domains. Once trained, our GAN model is capable of producing realistic seismic waveforms of multiple labels (noise and event classes). Applied to real Earth seismic data sets in Oklahoma, we show that data augmentation from our GAN‐generated synthetic waveforms can be used to improve earthquake detection algorithms in instances when only small amounts of labeled training data are available.