Seismic waveform classification via a new similarity measure
- Chengyun Song (School of Computer Science and Engineering, Chongqing University of Technology) | Zhining Liu (Center for Information Geoscience, University of Electronic Science and Technology of China) | Bin She (Center for Information Geoscience, University of Electronic Science and Technology of China) | Kunhong Li (Center for Information Geoscience, University of Electronic Science and Technology of China) | Guangmin Hu (Center for Information Geoscience, University of Electronic Science and Technology of China)
- Document ID
- Society of Exploration Geophysicists
- SEG International Exposition and Annual Meeting, 15-20 September, San Antonio, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Exploration Geophysicists
- Algorithm, Machine learning, Interpretation
- 5 in the last 30 days
- 8 since 2007
- Show more detail
Seismic waveform classification is an important technique for seismic facies analysis. The most existing methods use a fixed time window to extract seismic data along the interpretation horizon and then classify them. However, when the thickness of target layer has a large change at different points, an appropriate time window size is difficult to choose. Instead, by using both the top and bottom horizons to extract seismic waveforms, we propose a new similarity measure called dynamic sub-windows matching (DSWM) for calculating directly the distance between two waveforms with different lengths in this paper. DSWM is the average distance of multiple short signals and uses dynamic programming to find the best matching sub-windows. Furthermore, the KNN (K-Nearest Neighbors)-DSWM method is developed for supervised seismic facies analysis. The comparison and analysis of the results from the synthetic and real field data demonstrate that the proposed approach is suitable for reservoir with varying thickness, and provides an effective seismic interpretation tool.
Presentation Date: Monday, September 16, 2019
Session Start Time: 1:50 PM
Presentation Time: 2:15 PM
Location: Poster Station 2
Presentation Type: Poster
|File Size||1 MB||Number of Pages||5|
de Matos,M. C.,P. L.Osorio, andP. R.Johann,2006,Unsupervised seismic facies analysis using wavelet transform and self-organizing maps:Geophysics,72,no.1,P9–P21,doi:10.1190/1.2392789.
Du,H.-K.,J.Cao,Y.Xue, andX.Wang,2015,Seismic facies analysis based on self-organizing map and empirical mode decomposition:Journal of Applied Geophysics,112,52–61,doi:10.1016/j.jappgeo.2014.11.007.
Lemire,D.,2009,Faster retrieval with a two-pass dynamic-time-warping lower bound:Pattern Recognition,42,9169–2180,doi:10.1016/j.patcog.2008.11.030.
Saggaf,M. M.,M.Nafi Toksöz, andM. I.Marhoon,2003,Seismic facies classification and identification by competitive neural networks:Geophysics,68,1984–1999,doi:10.1190/1.1635052.
Song,C., andJ.Ferguson,2018,Adaptive phase k-means algorithm for waveform classification:Exploration Geophysics,49,213–219,doi:10.1071/EG16111.
Song,C.,Z.Liu,Y.Wang,X.Li, andG.Hu,2017,Multi-waveform classification for seismic facies analysis:Computers & Geosciences,101,1–9,doi:10.1016/j.cageo.2016.12.014.
Xie,T.,X.Zheng, andY.Zhang,2017,Seismic facies analysis based on speech recognition feature parameters:Geophysics,82,no.3,O23–O35,doi:10.1190/geo2016-0121.1.