Seismic fault detection with progressive transfer learning

• Autorzy: Zhou Ruoshui , Yao Xingmiao , Wang Yaojun , Hu Guangmin , Yu Fucai

Identyfikatory

DOI

10.1007/s11600-021-00668-5

• Języki publikacji: EN

Abstrakty

EN

Fault detection of seismic data is a key step in seismic data interpretation. Many techniques have got good seismic fault detection results by supervised deep learning, which assumes that the training data and the prediction data have a similar data distribution. However, the seismic data distributions are different when the prediction data is far away from the training data set even in the same work area, which results in an irrational fault detection result. In order to solve this problem, we first propose a progressive learning framework to update the training data set, which can reduce the difference between the training data set and the prediction data. In addition, we propose a fault label correctness measure index to improve the stability of the framework. Finally, we introduce domain-adversarial neural network to reduce the impact of data distribution differences and integrate it into the progressive learning framework. We perform fault detection on actual seismic data: compared with the traditional deep learning model, our method can improve the fault continuity and obtain more fault details.

Słowa kluczowe

EN

fault detection; transfer learning; deep learning; fault similarity index; adversarial mechanism

PL

wykrywanie uszkodzeń; transfer nauki; głęboka nauka

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2021
• Tom: Vol. 69, no. 6
• Strony: 2187--2203
• Opis fizyczny: Bibliogr. 23 poz.

Twórcy

autor

Zhou Ruoshui

• University of Electronic Science and Technology of China, Chengdu, China

autor

Yao Xingmiao

• University of Electronic Science and Technology of China, Chengdu, China

autor

Wang Yaojun

• University of Electronic Science and Technology of China, Chengdu, China

autor

Hu Guangmin

• University of Electronic Science and Technology of China, Chengdu, China

autor

Yu Fucai

• University of Electronic Science and Technology of China, Chengdu, China

Bibliografia

• 1. Bahorich M, Farmer S (1995) 3-D seismic discontinuity for faults and stratigraphic features: the coherence cube[J]. Lead Edge 14(10):1053–1058
• 2. Ben-David S, Blitzer J, Crammer K et al (2010) A theory of learning from different domains[J]. Mach Learn 79(1):151–175
• 3. Di H, Gao D (2014) Gray-level transformation and Canny edge detection for 3D seismic discontinuity enhancement[J]. Comput Geosci 72:192–200
• 4. Feng R, Grana D, Balling N (2021) Uncertainty quantification in fault detection using convolutional neural networks[J]. Geophysics 86(3):M41–M48
• 5. Ganin Y, Ustinova E, Ajakan H et al (2016) Domain-adversarial training of neural networks[J]. J Mach Learn Res 17(1):2096–2030
• 6. Gao J, Song Z, Gui J, et al. (2020) Gas-bearing prediction using transfer learning and CNNs: an application to a deep tight Dolomite Reservoir[J]. IEEE Geoscience and Remote Sensing Letters
• 7. Guillon S, Joncour F, Goutorbe P et al (2019) Reducing training dataset bias for automatic fault detection[M]//SEG technical program expanded abstracts. Soc Explor Geophys 2019:2423–2427
• 8. Huang L, Dong X, Clee TE (2017) A scalable deep learning platform for identifying geologic features from seismic attributes[J]. Lead Edge 36(3):249–256
• 9. Jebara T (2004) Multi-task feature and kernel selection for SVMs[C]//Proceedings of the twenty-first international conference on Machine learning. 55
• 10. Marfurt KJ, Kirlin RL, Farmer SL et al (1998) 3-D seismic attributes using a semblance-based coherency algorithm[J]. Geophysics 63(4):1150–1165
• 11. Marfurt KJ, Sudhaker V, Gersztenkorn A et al (1999) Coherency calculations in the presence of structural dip[J]. Geophysics 64(1):104–111
• 12. Pan SJ, Yang Q (2009) A survey on transfer learning[J]. IEEE Trans Knowl Data Eng 22(10):1345–1359
• 13. Randen T, Pedersen SI, Sønneland L (2001) Automatic extraction of fault surfaces from three-dimensional seismic data[M]//SEG technical program expanded abstracts. Soc Explor Geophys 2001:551–554
• 14. Van Bemmel PP, Pepper REF (2000) Seismic signal processing method and apparatus for generating a cube of variance values. U.S. Patent 6,151,555
• 15. Wang Z, Li B, Liu N et al. (2020) Distilling knowledge from an ensemble of convolutional neural networks for seismic fault detection[J]. IEEE Geoscience and Remote Sensing Letters
• 16. Williams C, Bonilla EV, Chai KM (2007) Multi-task Gaussian process prediction[J]. Adv Neural Inf Process Syst, 153–160
• 17. Wu X (2017) Directional structure-tensor-based coherence to detect seismic faults and channels[J]. Geophysics 82(2):A13–A17
• 18. Wu X, Fomel S (2018) Automatic fault interpretation with optimal surface voting[J]. Geophysics 83(5):O67–O82
• 19. Wu X, Shi Y, Fomel S et al (2018) Convolutional neural networks for fault interpretation in seismic images[M]//SEG technical program expanded abstracts. Soc Explor Geophys 2018:1946–1950
• 20. Wu X, Liang L, Shi Y et al (2019) FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation[J]. Geophysics 84(3):IM35–IM45
• 21. Wu B, Meng D, Wang L et al (2020) Seismic impedance inversion using fully convolutional residual network and transfer learning[J]. IEEE Geosci Remote Sens Lett 17(12):2140–2144
• 22. Xiong W, Ji X, Ma Y et al (2018) Seismic fault detection with convolutional neural network[J]. Geophysics 83(5):O97–O103
• 23. Yuan S, Wang J, Liu T et al (2020) 6D phase-difference attributes for wide-azimuth seismic data interpretation[J]. Geophysics 85(6):IM37–IM49