Geodesic
Question on the preparation of geoacoustic observation data for identification of pre- and post-seismic anomalies
Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 49 (2024) no. 4, pp. 125-134 Cet article a éte moissonné depuis la source Math-Net.Ru

Voir la notice de l'article

The paper proposes a method for improvement of the quality of geophysical data preparation on the example of geoacoustic observations to train neural networks when solving the problem of identification of pre- and post-seismic anomalies. The method is based on the transformation of geoacoustic emission signal associated with deformation processes in near-surface rocks into three-dimensional images. A series of such images contains the information on signal characteristics dynamics. Thee-dimensional images are the matrices consisting of the the distribution vectors of selected characteristics (spectral, structural, statistical and so on). The structure, data tensor, is formed from a series of such images. It is supplied to the neural network input. Due to external factors impact (weather, industrial), a recorded geoacoustic signal is distorted. Thus, it is necessary to clean the initial data. In order to do this, we suggest using a neural network which clusters the prepared images and removes outliers in the obtained clusters. A new tensor is formed from the remaining images. It undergoes the cleaning procedure again. This process continues until no outliers are observed in the output data as the result of clustering. When the cleaning is over, the second neural network will be trained to identify common features and differences, as well as hidden patterns in the geoacoustic pulse flux. Application of the developed method for tensor cleaning, based on artificial intelligence technologies, allows us to improve significantly the quality of data preparation. The obtained results will be useful for the investigations in the fields of identification and classification of pre- and postseismic anomalies in geoacoutstic emission signals associated with deformation processes in near-surface rocks in a seismically active region.
Mots-clés : geoacoustic emission
Keywords: near-surface rocks, signal characteristics dynamics, clustering, neural networks, pre-seismic anomalies, postseismic anomalies. 
@article{VKAM_2024_49_4_a8,
     author = {Yu.I. Senkevich and M. A. Mishenko},
     title = {Question on the preparation of geoacoustic observation data for identification of pre- and post-seismic anomalies},
     journal = {Vestnik KRAUNC. Fiziko-matemati\v{c}eskie nauki},
     pages = {125--134},
     year = {2024},
     volume = {49},
     number = {4},
     language = {ru},
     url = {http://geodesic.mathdoc.fr/item/VKAM_2024_49_4_a8/}
}
TY  - JOUR
AU  - Yu.I. Senkevich
AU  - M. A. Mishenko
TI  - Question on the preparation of geoacoustic observation data for identification of pre- and post-seismic anomalies
JO  - Vestnik KRAUNC. Fiziko-matematičeskie nauki
PY  - 2024
SP  - 125
EP  - 134
VL  - 49
IS  - 4
UR  - http://geodesic.mathdoc.fr/item/VKAM_2024_49_4_a8/
LA  - ru
ID  - VKAM_2024_49_4_a8
ER  - 
%0 Journal Article
%A Yu.I. Senkevich
%A M. A. Mishenko
%T Question on the preparation of geoacoustic observation data for identification of pre- and post-seismic anomalies
%J Vestnik KRAUNC. Fiziko-matematičeskie nauki
%D 2024
%P 125-134
%V 49
%N 4
%U http://geodesic.mathdoc.fr/item/VKAM_2024_49_4_a8/
%G ru
%F VKAM_2024_49_4_a8
Yu.I. Senkevich; M. A. Mishenko. Question on the preparation of geoacoustic observation data for identification of pre- and post-seismic anomalies. Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 49 (2024) no. 4, pp. 125-134. http://geodesic.mathdoc.fr/item/VKAM_2024_49_4_a8/

[1] Marapulets Yu.V., Shevtsov B.M., Mezomasshtabnaya akusticheskaya emissiya, Dalnauka, Vladivostok, 2012, 126 pp.

[2] Perezhogin A. S., Shevtsov B. M., “Modeli napryazhenno-deformirovannogo sostoyaniya gornykh porod pri podgotovke zemletryasenii i ikh svyaz s geoakusticheskimi nablyudeniyami”, Vychislitelnye tekhnologii, 14:3 (2009), 48–57 | Zbl

[3] Marapulets Yu. V. i dr., “Otklik geoakusticheskoi emissii na aktivizatsiyu deformatsionnykh protsessov pri podgotovke zemletryasenii”, Tikhookeanskaya geologiya, 31:6 (2012), 59–67

[4] Morgunov V. A. i dr., “Geoakusticheskii predvestnik Spitakskogo zemletryaseniya”, Vulkanologiya i seismologiya, 1991, no. 4, 104–106

[5] Dolgikh G.I. i dr., “Deformatsionnye i akusticheskie predvestniki zemletryasenii”, Doklady akademii nauk, 413:1 (2007), 96–100 | DOI

[6] Saltykov V. A., Kugaenko Yu. A., “Razvitie pripoverkhnostnykh zon dilatansii kak vozmozhnaya prichina anomalii v parametrakh seismicheskoi emissii pered silnymi zemletryaseniyami”, Tikhookeanskaya geologiya, 31:1 (2012), 96–106

[7] Gregori G. P., et. al., ““Storms of crustal stress” and AE earthquake precursors”, Natural Hazards and Earth System Sciences, 10:2 (2010), 319–337 | DOI

[8] Gapeev M., Marapulets Y., “Modeling Locations with Enhanced Earth’s Crust Deformation during Earthquake Preparation near the Kamchatka Peninsula”, Appl. Sci., 13:1 (2022), 290, 1–14 | DOI | MR

[9] Marapulets Y., et al., “Sound Range AE as a Tool for Diagnostics of Large Technical and Natural Objects”, Sensors, 23:3 (2023), 1269, 1–14 | DOI

[10] Senkevich Yu.I. i dr., “Metodika vydeleniya informativnykh priznakov v signalakh geoakusticheskoi emissii”, Trudy SPIIRAN, 18:5 (2019), 1066–1092 DOI: 10.15622/sp.2019.18.5.1066-1092 | DOI

[11] Katalog zemletryasenii Kamchatki i Komandorskikh ostrovov, Kamchatskii filial FITs EGS RAN,[Elektronnyi resurs]. URL: (data obrascheniya: 20.11.24) http://sdis.emsd.ru/info/earthquakes/catalogue.php

[12] Chebrova A. Yu. i dr., “Edinaya informatsionnaya sistema seismologicheskikh dannykh v Kamchatskom filiale FITs EGS RAN: printsipy organizatsii, osnovnye elementy, klyuchevye funktsii”, Geofizicheskie issledovaniya, 21:3 (2020), 66–91

[13] Dobrovolskii I. P., Matematicheskaya teoriya prognoza i podgotovki tektonicheskogo zemletryaseniya, FIZMATLIT, M., 2009, 240 pp.

[14] Pedregosa F., et al., “Scikit-learn: Machine Learning in Python”, Journal of Machine Learning Research, 12:85 (2011), 2825–2830 | MR | Zbl