Processing and preparation of observation data in the interests of highlighting the features of the dynamics of the characteristics of geoacoustic emission

Yu.I. Senkevich

Vestnik KRAUNC. Fiziko-matematičeskie nauki, Tome 47 (2024) no. 2, pp. 75-94

Résumé

The lithospheric layer deformation under the action of seismic processes affects the characteristics of geoacoustic emission. The study of the geoacoustic emission dynamics is aimed at finding signs of preseismic events. There is a problem obtained for the high-quality processing of geoacoustic emission signals and the results classification. The study is aimed at finding the best combination of pre-processing and clustering tools for the pulse flow of geoacoustic emission to identify the features of the characteristics dynamics of such a signal. The processed signals were obtained during long-term measurements in the surface lithosphere layers of the seismically active region of the Kamchatka Peninsula. To identify the variability features of geoacoustic emission signals characteristics they are converted by sructurno-linguistic into a three-dimensional image. The images are processed, compared and clustered using convolutional neural networks of various architectures. The best result is assessed by three selected quality criteria. A technique has been developed for finding the best preprocessing and clustering result. The experimental result analisys are presented.

Détail

Keywords: signal processing, pattern recognition, cluster analysis, signal characteristics dynamics display, neural networks.
Mots-clés : geoacoustic emission

Bibliographie

[1] Marapulets Yu. V. i dr., Kompleksnyi analiz akusticheskikh i elektromagnitnykh signalov dlya otsenki urovnya seismicheskoi opasnosti, Uchebnoe posobie dlya studentov, obuchayuschikhsya po spetsialnosti 011200 – geofizika., v. 2 (Seismologiya), Dalnauka, Vladivostok, 2020, 120 pp.

[2] Gapeev M. I., Marapulets Yu. V., “Modelirovanie zon otnositelnykh sdvigovykh deformatsii pered silnymi zemletryaseniyami na Kamchatke, proizoshedshimi v period 2018-2021 gg”, Vestnik KRAUNTs. Fiz.-mat. nauki., 37:4 (2021), 53-66 \href {DOI: 10.26117/2079-6641-2021-37-4-53-66} | DOI | MR | Zbl

[3] Senkevich Yu. I. “Search for Hidden Patterns in Acoustic and Electromagnetic Pulse Signals”, IEEE, 2020 \href {DOI: 10.1109/SCM50615.2020.9198754}

[4] Senkevich Yu. I., Lukovenkova O. O., Solodchuk A. A., “Metodika formirovaniya Reestra geofizicheskikh signalov na primere signalov geoakusticheskoi emissii”, Geosistemy perekhodnykh zon, 2 (2018), 409-418 \href {DOI: 10.30730/2541-8912.2018.2.4.409-418}

[5] Senkevich Yu. I. i dr., “Sposob obnaruzheniya kompleksnogo predvestnika zemletryasenii”, Ros. Federatsiya G01V 11/00, G01V 1/00, G01V 3/12, pat. \number 2758582 (FGBUN IKIR DVO RAN. # 2020138668; 26.11.2020, Byul. # 31. 9 s.)

[6] Senkevich Yu. I., Mischenko M. A., “Metodika otsenki sostoyaniya pripoverkhnostnykh osadochnykh porod po rezultatam nablyudenii dinamicheskikh kharakteristik geoakusticheskoi emissii”, Vestnik KRAUNTs. Fiz.-mat. nauki, 45:4 (2023), 109-121, \href {DOI: 10.26117/2079-6641-2023-45-4-109-121} | DOI

[7] Mischenko M.A., Senkevich Yu.I., Scherbina A.O., “Sovremennye metody obrabotki i analiza impulsnykh geofizicheskikh signalov”, Vestnik KRAUNTs. Fiz.-mat. nauki, 41:4 (2022), 120-136 \href {DOI: 10/26117/2079-6641} | MR

[8] Senkevich Yu., Marapulets Yu., Lukovenkova O., Solodchuk A., “Technique of informative features selection in geoacoustic emission signals”, SPIIRAS, 18:5 (2022), 1066-1092 \href {DOI: 10.1051/e3sconf/201912702005} | DOI

[9] Senkevich Yu. I., “Auto clustering of the variety of pulse signals based on their symbolic description”, E3S Web of Conferences, 19 (2019), 14

[10] Yang Z., Algesheimer R., Tessone C. J., A Comparative Analysis of Community Detection Algorithms on Artificial Networks \href {{\tt https://www.nature.com/articles/srep30750}}

[11] Keras library \href {{\tt https://keras.io/why-this-name-keras}}

[12] Markov L. S., Teoretiko-metodologicheskie osnovy klasternogo podkhoda, IEOPP SO RAN, Novosibirsk, 2015, 300 pp.

[13] Alsova O. K., “Algoritmy klasterizatsii raznotipnykh dannykh na primere resheniya meditsinskoi zadachi”, trudy SPIIRAN, 6:37 (2014), 156-169 DOI: 10.15622/sp.37.10 | DOI

[14] Milewski P., PCA decomposition and Keras neural network, https://www.kaggle.com/code/pmmilewski/pca-decomposition-and-keras-neural-network

[15] VGG16 and VGG19

[16] Building Autoencoders in Keras

[17] Keras Metrics – A Complete Guide

[18] Performance Evaluation Metrics

[19] Calinski harabasz score scikit-learn developers \href {{ https://scikit-learn.org/stable/modules/generated/sklearn.metrics.calinski-harabasz-score.html}}

[20] Dunn index and DB index – Cluster Validity indices

[21] Senkevich Yu. I, Duke V. A., Mishchenko M. A., Solodchuk A. A., “Information approach to the analysis of acoustic and electromagnetic signals”, E3S Web of Conferences, 20:02012 (2017), 9 \href {{DOI:10.1051/e3sconf/2017200201}}