Number of the records: 1
Type analysis of laboratory seismic events by convolutional neural networks
- 1.
SYSNO ASEP 0542182 Document Type J - Journal Article R&D Document Type Journal Article Subsidiary J Článek ve WOS Title Type analysis of laboratory seismic events by convolutional neural networks Author(s) Kolář, Petr (GFU-E) ORCID, RID
Petružálek, Matěj (GLU-S) RID, SAI, ORCIDSource Title Acta geodynamica et geomaterialia. - : Ústav struktury a mechaniky hornin AV ČR, v. v. i. - ISSN 1214-9705
Roč. 18, č. 2 (2021), s. 267-277Number of pages 11 s. Publication form Print - P Language eng - English Country CZ - Czech Republic Keywords convolutional neural network ; machine learning ; earthquake identification ; acoustic emission ; seismic signal processing ; Bayesian optimization Subject RIV DC - Siesmology, Volcanology, Earth Structure OECD category Volcanology Subject RIV - cooperation Institute of Geology - Siesmology, Volcanology, Earth Structure R&D Projects GA21-26542S GA ČR - Czech Science Foundation (CSF) Method of publishing Open access Institutional support GFU-E - RVO:67985530 ; GLU-S - RVO:67985831 UT WOS 000661266800011 EID SCOPUS 85109105310 DOI 10.13168/AGG.2021.0019 Annotation In this work, we successfully identified seismic events (observations of earthquakes) in seismograms using a Convolutional Neural Network (CNN). In accordance with past (analogue) seismogram interpretations, we did not treat digital seismograms as a time series, as per the general method, but, rather, converted them into time snaps of continuous data flow. Multichannel seismograms were represented with a time-frequency domain in the form of multilayer images, with each signal channel forming one image layer. Images were then exposed to CNN (composed of three convolutional blocks whose architecture design was justified using Bayesian optimization). To improve reliability, we evaluated the posterior type function (PTP) as a combination of the probabilities of all of the considered classes of signal types (five in our case) which increased robustness of the identification. For data, we used records of acoustic emission (AE) events. The events were generated during laboratory loading experiments originally performed to study material/rock properties. As known, AE events may be studied in the same manner as natural earthquakes and treated in other ways as laboratory earthquake models. AE events are less complex compared to natural earthquakes where many of the physical parameters are known or may be controlled. Based on our results, we concluded that the successful identification of AE events is a necessary step prior to applying the proposed methodology for identifying natural earthquakes in seismograms. Workplace Geophysical Institute Contact Hana Krejzlíková, kniha@ig.cas.cz, Tel.: 267 103 028 Year of Publishing 2022 Electronic address https://www.irsm.cas.cz/index_en.php?page=acta_detail_doi&id=398
Number of the records: 1