Successive variational mode decomposition-based enhanced Wigner-Ville distribution for seismo-volcanic events identification

被引:9
作者
Faisal, Kazi Newaj [1 ]
Sharma, Rishi Raj [1 ]
机构
[1] Def Inst Adv Technol, Dept Elect Engn, Pune 411025, India
关键词
Seismo-volcanic events identification; Successive variational mode decomposition; (SVMD); Wigner-Ville distribution (WVD); Cross -term reduction; Time -frequency analysis; Seismic signal processing; TIME-FREQUENCY ANALYSIS; AUTOMATIC CLASSIFICATION; CROSS-TERMS; EIGENVALUE DECOMPOSITION; ATTENUATION; INFORMATION; SIGNALS; SERIES; EMD;
D O I
10.1016/j.jvolgeores.2023.107847
中图分类号
P [天文学、地球科学];
学科分类号
07 ;
摘要
Seismicity offers valuable information on the internal activity of volcanoes and the interpretation of seismic signals is crucial for volcano monitoring. As the seismic signal is multi-component & non-stationary, the timefrequency analysis like Wigner-Ville distribution (WVD) has played a significant role, but the presence of cross-term limits the applicability of WVD and other bilinear time-frequency representations (TFRs). This paper introduces a successive variational mode decomposition (SVMD)-based cross-term reduction method in WVD. The proposed method is robust and accurate due to reduced sensitivity to initialization parameters, lesser computational burden, and automatic selection of the number of decomposed modes. SVMD-based WVD outperforms other related signal decomposition-based methods for removing cross-terms and reconstructing autoterms, as demonstrated by similarity and concentration-based performance measures for synthetic multicomponent and seismic signals. SVMD-based WVD is also applied for the seismo-volcanic events identification system development and evaluated on the Llaima volcano dataset to find the applicability of the proposed method in real-world field data. Novel TFR-based features are extracted based on 3-D segmentation of TFR and 2D normalized correlation between the segments. Feature ranking and SVM classifier optimization result in an overall classification accuracy of 97.10%, surpassing previous approaches on the same dataset.
引用
收藏
页数:15
相关论文
共 66 条
  • [1] [Anonymous], 2006, Leading Edge, DOI DOI 10.1190/1.2172314
  • [2] Archdeacon T.J., 1994, CORRELATION REGRESSI
  • [3] Measuring time-frequency information content using the Renyi entropies
    Baraniuk, RG
    Flandrin, P
    Janssen, AJEM
    Michel, OJJ
    [J]. IEEE TRANSACTIONS ON INFORMATION THEORY, 2001, 47 (04) : 1391 - 1409
  • [4] Random and coherent noise attenuation by empirical mode decomposition
    Bekara, Maiza
    van der Baan, Mirko
    [J]. GEOPHYSICS, 2009, 74 (05) : V89 - V98
  • [5] Boashash B, 2003, TIME FREQUENCY SIGNAL ANALYSIS AND PROCESSING: A COMPREHENSIVE REFERENCE, P627
  • [6] Principles of time-frequency feature extraction for change detection in non-stationary signals: Applications to newborn EEG abnormality detection
    Boashash, Boualem
    Azemi, Ghasem
    Khan, Nabeel Ali
    [J]. PATTERN RECOGNITION, 2015, 48 (03) : 616 - 627
  • [7] Bosman C., 1993, SEG TECHN PROGR EXP, P1261, DOI DOI 10.1190/1.1822354
  • [8] Brusil C, 2019, 2019 IEEE LATIN AMERICAN CONFERENCE ON COMPUTATIONAL INTELLIGENCE (LA-CCI), P81
  • [9] In-depth comparison of deep artificial neural network architectures on seismic events classification
    Canario, Joao Paulo
    Mello, Rodrigo
    Curilem, Millaray
    Huenupan, Fernando
    Rios, Ricardo
    [J]. JOURNAL OF VOLCANOLOGY AND GEOTHERMAL RESEARCH, 2020, 401
  • [10] Llaima volcano dataset: In-depth comparison of deep artificial neural network architectures on seismic events classification
    Canario, Joao Paulo
    de Mello, Rodrigo Fernandes
    Curilem, Millaray
    Huenupan, Ferno
    Rios, Ricardo Araujo
    [J]. DATA IN BRIEF, 2020, 30