Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder
Seismic facies analysis (SFA) is a crucial step in the interpretation of subsurface structures, with the core challenge being the development of automatic approaches for the analysis of 4D prestack seismic data. The dominant isolated learning-based SFA schemes have gained considerable attention and...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2023-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10288056/ |
| _version_ | 1797635422716690432 |
|---|---|
| author | Haowei Hua Feng Qian Gulan Zhang Yuehua Yue |
| author_facet | Haowei Hua Feng Qian Gulan Zhang Yuehua Yue |
| author_sort | Haowei Hua |
| collection | DOAJ |
| description | Seismic facies analysis (SFA) is a crucial step in the interpretation of subsurface structures, with the core challenge being the development of automatic approaches for the analysis of 4D prestack seismic data. The dominant isolated learning-based SFA schemes have gained considerable attention and primarily focus on learning the best representation of prestack data and generating facies maps by clustering the extracted features. However, in isolated learning, the independent nature of feature extraction and clustering leads to the ineffectiveness of clustering loss guidance on feature extraction, thereby resulting in derived features that unnecessarily facilitate the clustering task. As an alternative, we proposed a new unsupervised, end-to-end learning-based SFA method, which is referred to as the lognormal mixture-based variational autoencoder (LMVAE) and enhanced the existing Gaussian mixture variational autoencoder-based deep clustering framework (GMVAE framework). In this approach, both the extraction and clustering of seismic features are simultaneously performed by determining from which mode of the latent mixture distribution the seismic data were generated. Furthermore, the LMVAE extends the Gaussian mixture modeling of seismic features in the GMVAE framework to lognormal mixture modeling, improving the adaptability of SFA to field data. The effective performance of the LMVAE is demonstrated in synthetic and field prestack seismic data. |
| first_indexed | 2024-03-11T12:21:52Z |
| format | Article |
| id | doaj.art-91c26910b6fd46c2984d9612eab85f04 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-11T12:21:52Z |
| publishDate | 2023-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-91c26910b6fd46c2984d9612eab85f042023-11-07T00:00:23ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352023-01-01169831984210.1109/JSTARS.2023.332596910288056Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational AutoencoderHaowei Hua0https://orcid.org/0009-0003-8536-7441Feng Qian1https://orcid.org/0000-0002-4761-3598Gulan Zhang2https://orcid.org/0000-0002-7603-4966Yuehua Yue3School of Information and Communication Engineering, Center for Information Geoscience, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Information and Communication Engineering, Center for Information Geoscience, University of Electronic Science and Technology of China, Chengdu, ChinaSchool of Geoscience and Technology, Southwest Petroleum University, Chengdu, ChinaSatellite Communication Technology Institute, Nanjing Panda Handa Technology Company, Ltd., Nanjing, ChinaSeismic facies analysis (SFA) is a crucial step in the interpretation of subsurface structures, with the core challenge being the development of automatic approaches for the analysis of 4D prestack seismic data. The dominant isolated learning-based SFA schemes have gained considerable attention and primarily focus on learning the best representation of prestack data and generating facies maps by clustering the extracted features. However, in isolated learning, the independent nature of feature extraction and clustering leads to the ineffectiveness of clustering loss guidance on feature extraction, thereby resulting in derived features that unnecessarily facilitate the clustering task. As an alternative, we proposed a new unsupervised, end-to-end learning-based SFA method, which is referred to as the lognormal mixture-based variational autoencoder (LMVAE) and enhanced the existing Gaussian mixture variational autoencoder-based deep clustering framework (GMVAE framework). In this approach, both the extraction and clustering of seismic features are simultaneously performed by determining from which mode of the latent mixture distribution the seismic data were generated. Furthermore, the LMVAE extends the Gaussian mixture modeling of seismic features in the GMVAE framework to lognormal mixture modeling, improving the adaptability of SFA to field data. The effective performance of the LMVAE is demonstrated in synthetic and field prestack seismic data.https://ieeexplore.ieee.org/document/10288056/Deep clusteringend-to-end learninglognormal mixture-based variational autoencoder (LMVAE)Seismic facies analysis (SFA) |
| spellingShingle | Haowei Hua Feng Qian Gulan Zhang Yuehua Yue Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Deep clustering end-to-end learning lognormal mixture-based variational autoencoder (LMVAE) Seismic facies analysis (SFA) |
| title | Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder |
| title_full | Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder |
| title_fullStr | Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder |
| title_full_unstemmed | Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder |
| title_short | Unsupervised Seismic Facies Deep Clustering Via Lognormal Mixture-Based Variational Autoencoder |
| title_sort | unsupervised seismic facies deep clustering via lognormal mixture based variational autoencoder |
| topic | Deep clustering end-to-end learning lognormal mixture-based variational autoencoder (LMVAE) Seismic facies analysis (SFA) |
| url | https://ieeexplore.ieee.org/document/10288056/ |
| work_keys_str_mv | AT haoweihua unsupervisedseismicfaciesdeepclusteringvialognormalmixturebasedvariationalautoencoder AT fengqian unsupervisedseismicfaciesdeepclusteringvialognormalmixturebasedvariationalautoencoder AT gulanzhang unsupervisedseismicfaciesdeepclusteringvialognormalmixturebasedvariationalautoencoder AT yuehuayue unsupervisedseismicfaciesdeepclusteringvialognormalmixturebasedvariationalautoencoder |