SpringerLink
Log in

SeisGAN: Improving Seismic Image Resolution and Reducing Random Noise Using a Generative Adversarial Network

  • Published:
Mathematical Geosciences Aims and scope Submit manuscript

Abstract

Seismic images are essential for understanding the subsurface geological structure and resource distribution. However, the accuracy and certainty of geological analysis using seismic images are limited by the resolution and signal-to-noise ratio. Simultaneously improving resolution and suppressing random noise with traditional methods can be quite challenging. This research proposes a new approach called SeisGAN which leverages a generative adversarial network to address the challenge at hand. Due to the lack of high-resolution noiseless and low-resolution noisy seismic data, stochastic parameter control is employed to simulate a vast range of diverse, paired seismic data for SeisGAN training. The results on the synthetic dataset demonstrate that the proposed method is effective in enhancing the resolution and suppressing the random noise in the original images. Spectrum analysis shows that the proposed method increases the bandwidth of the original data, primarily at high frequencies. Ablation experiments reveal that, under similar conditions, SeisGAN outperforms traditional convolutional neural networks. Incorporating the VGG loss in the generator loss function improves the model’s ability to recover high-frequency details. The application of the technique on two publicly available field seismic datasets indicates SeisGAN’s excellent generalizability, despite being trained only on synthetic seismic data. Compared with bicubic interpolation and traditional noise suppression and resolution enhancement methods, SeisGAN is capable of effectively suppressing the random noise and enhancing the dominant frequency of field seismic data, making it easier to identify adjacent thin layers and fault features, even for small-scale faults. The zoomed images are clearer and easier to interpret. Furthermore, an example of automatic machine fault identification demonstrates the significant contribution of the SeisGAN-enhanced image to accurate fault recognition.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13

Similar content being viewed by others

Data Availability

The codes, training data, trained models, and application examples in this study are all available on https://github.com/leilin1995/SeisGAN-Improving-Seismic-Image-Resolution-and-Reducing-Noise.

References

  • Abma R, Claerbout J (1995) Lateral prediction for noise attenuation by tx and fx techniques. Geophysics 60(6):1887–1896

    Google Scholar 

  • Alaei N, Roshandel Kahoo A, Kamkar Rouhani A, Soleimani M (2018) Seismic resolution enhancement using scale transform in the time-frequency domain. Geophysics 83(6):V305–V314

    Google Scholar 

  • AlBinHassan NM, Luo Y, Al-Faraj MN (2006) 3d edge-preserving smoothing and applications. Geophysics 71(4):P5–P11

    Google Scholar 

  • Anderson DL, Kanamori H, Hart RS, Liu HP (1977) The earth as a seismic absorption band. Science 196(4294):1104–1106

    CAS  Google Scholar 

  • Anvari R, Mohammadi M, Kahoo AR, Khan NA, Abdullah AI (2020) Random noise attenuation of 2d seismic data based on sparse low-rank estimation of the seismic signal. Comput Geosci 135:104376

    Google Scholar 

  • Arjovsky M, Chintala S, Bottou L (2017) Wasserstein generative adversarial networks. In: International conference on machine learning, PMLR, pp 214–223

  • Basile C, Mascle J, Popoff M, Bouillin J, Mascle G (1993) The ivory coast-ghana transform margin: a marginal ridge structure deduced from seismic data. Tectonophysics 222(1):1–19

    Google Scholar 

  • Beckouche S, Ma J (2014) Simultaneous dictionary learning and denoising for seismic data. Geophysics 79(3):A27–A31

    Google Scholar 

  • Canales LL (1984) Random noise reduction. In: SEG technical program expanded abstracts 1984, Society of Exploration Geophysicists, pp 525–527

  • Chen S, Wang Y (2018) Seismic resolution enhancement by frequency-dependent wavelet scaling. IEEE Geosci Remote Sens Lett 15(5):654–658

    Google Scholar 

  • Chen Z, Wang Y, Chen X, Li J (2013) High-resolution seismic processing by gabor deconvolution. J Geophys Eng 10(6):065002

    CAS  Google Scholar 

  • Colman SM, Karabanov E, Nelson C III (2003) Quaternary sedimentation and subsidence history of lake Baikal, Siberia, based on seismic stratigraphy and coring. J Sediment Res 73(6):941–956

    Google Scholar 

  • Dong C, Loy CC, He K, Tang X (2015) Image super-resolution using deep convolutional networks. IEEE Trans Pattern Anal Mach Intell 38(2):295–307

    Google Scholar 

  • Ebrom D, Li X, McDonald J, Lu L (1995) Bin spacing in land 3-d seismic surveys and horizontal resolution in time slices. Lead Edge 14(1):37–40

    Google Scholar 

  • Ecker C, Dvorkin J, Nur AM (2000) Estimating the amount of gas hydrate and free gas from marine seismic data. Geophysics 65(2):565–573

    Google Scholar 

  • Faleide TS, Braathen A, Lecomte I, Mulrooney MJ, Midtkandal I, Bugge AJ, Planke S (2021) Impacts of seismic resolution on fault interpretation: insights from seismic modelling. Tectonophysics 816:229008

    Google Scholar 

  • Fehmers GC, Höcker CF (2003) Fast structural interpretation with structure-oriented filtering. Geophysics 68(4):1286–1293

    Google Scholar 

  • Feng R, Grana D, Mukerji T, Mosegaard K (2022) Application of Bayesian generative adversarial networks to geological facies modeling. Math Geosci 54(5):831–855

    Google Scholar 

  • Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, Courville A, Bengio Y (2014) Generative adversarial networks. ar**v e-prints ar**v:1406.2661

  • Hale D (2009) Structure-oriented smoothing and semblance. CWP report 635(635)

  • Hale D (2011) Structure-oriented bilateral filtering. CWP Rep 695:239–248

    Google Scholar 

  • He K, Zhang X, Ren S, Sun J (2015) Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In: Proceedings of the IEEE international conference on computer vision, pp 1026–1034

  • He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770–778

  • Higuchi Y, Yanagimoto Y, Hoshi K, Unou S, Akiba F, Tonoike K, Koda K (2007) Cenozoic stratigraphy and sedimentation history of the Northern Philippine sea based on multichannel seismic reflection data. Island Arc 16(3):374–393

    Google Scholar 

  • Huang L, Liu C, Kusky TM (2015) Cenozoic evolution of the tan-lu fault zone (East China)-constraints from seismic data. Gondwana Res 28(3):1079–1095

    Google Scholar 

  • Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: International conference on machine learning, PMLR, pp 448–456

  • Jia Y, Ma J (2017) What can machine learning do for seismic data processing? An interpolation application. Geophysics 82(3):V163–V177

    Google Scholar 

  • Karras T, Aila T, Laine S, Lehtinen J (2017) Progressive growing of gans for improved quality, stability, and variation. ar**v preprint ar**v:1710.10196

  • Kazemi N, Sacchi MD (2014) Sparse multichannel blind deconvolution. Geophysics 79(5):V143–V152

    Google Scholar 

  • Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. ar**v preprint ar**v:1412.6980

  • Kjartansson E (1979) Constant q-wave propagation and attenuation. J Geophys Res Solid Earth 84(B9):4737–4748

    Google Scholar 

  • Ledig C, Theis L, Huszár F, Caballero J, Cunningham A, Acosta A, Aitken A, Tejani A, Totz J, Wang Z et al (2017) Photo-realistic single image super-resolution using a generative adversarial network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4681–4690

  • Lei C, Alves TM, Ren J, Tong C (2020) Rift structure and sediment infill of hyperextended continental crust: insights from 3d seismic and well data (**sha Trough, South China sea). J Geophys Res Solid Earth 125(5):e2019JB018610

    Google Scholar 

  • Li J, Wu X, Hu Z (2021) Deep learning for simultaneous seismic image super-resolution and denoising. IEEE Trans Geosci Remote Sens 60:1–11

    Google Scholar 

  • Lim B, Son S, Kim H, Nah S, Mu LK (2017) Enhanced deep residual networks for single image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 136–144

  • Liu Y, Li B (2018) Streaming orthogonal prediction filter in the t-x domain for random noise attenuation. Geophysics 83(4):F41–F48

    Google Scholar 

  • Liu M, Mukerji T (2022) Multiscale fusion of digital rock images based on deep generative adversarial networks. Geophys Res Lett 49(9):e2022GL098342

    Google Scholar 

  • Liu G, Fomel S, ** L, Chen X (2009) Stacking seismic data using local correlation. Geophysics 74(3):V43–V48

    Google Scholar 

  • Liu GC, Chen XH, Li JY, Du J, Song JW (2011) Seismic noise attenuation using nonstationary polynomial fitting. Appl Geophys 8(1):18–26

    Google Scholar 

  • Lin L, Zhong Z, Cai Z, Sun AY, Li C (2022) Automatic geologic fault identification from seismic data using 2.5 d channel attention u-net. Geophysics 87(4):IM111–IM124

    Google Scholar 

  • Mafakheri J, Kahoo AR, Anvari R, Mohammadi M, Radad M, Monfared MS (2022) Expand dimensional of seismic data and random noise attenuation using low-rank estimation. IEEE J Sel Top Appl Earth Obs Remote Sens 15:2773–2781

    Google Scholar 

  • Margrave GF, Lamoureux MP, Henley DC (2011) Gabor deconvolution: estimating reflectivity by nonstationary deconvolution of seismic data. Geophysics 76(3):W15–W30

    Google Scholar 

  • Mondol NH (2010) Seismic exploration. Pet Geosci 1:375–402

    Google Scholar 

  • Mosser L, Dubrule O, Blunt MJ (2020) Stochastic seismic waveform inversion using generative adversarial networks as a geological prior. Math Geosci 52:53–79

    Google Scholar 

  • Moulin M, Aslanian D, Olivet JL, Contrucci I, Matias L, Géli L, Klingelhoefer F, Nouzé H, Réhault JP, Unternehr P (2005) Geological constraints on the evolution of the Angolan margin based on reflection and refraction seismic data (Zaïango project). Geophys J Int 162(3):793–810

    Google Scholar 

  • Nazari Siahsar MA, Gholtashi S, Kahoo AR, Chen W, Chen Y (2017) Data-driven multitask sparse dictionary learning for noise attenuation of 3d seismic data. Geophysics 82(6):V385–V396

    Google Scholar 

  • Oliveira DA, Ferreira RS, Silva R, Brazil EV (2019) Improving seismic data resolution with deep generative networks. IEEE Geosci Remote Sens Lett 16(12):1929–1933

    Google Scholar 

  • Perez G, Marfurt KJ (2007) Improving lateral and vertical resolution of seismic images by correcting for wavelet stretch in common-angle migration. Geophysics 72(6):C95–C104

    Google Scholar 

  • Perez L, Wang J (2017) The effectiveness of data augmentation in image classification using deep learning. ar**v preprint ar**v:1712.04621

  • Porsani MJ (1997) Seismic trace interpolation in the fx domain using half-step prediction filters. In: SEG technical program expanded abstracts 1997, Society of Exploration Geophysicists, pp 1985–1988

  • Reilly JM, Aharchaou M, Neelamani R (2023) A brief overview of seismic resolution in applied geophysics. Lead Edge 42(1):8–15

    Google Scholar 

  • Ricker N (1953) Wavelet contraction, wavelet expansion, and the control of seismic resolution. Geophysics 18(4):769–792

    Google Scholar 

  • Robinson EA (1967) Predictive decomposition of time series with application to seismic exploration. Geophysics 32(3):418–484

    Google Scholar 

  • Robinson EA, Treitel S (1967) Principles of digital wiener filtering. Geophys Prospect 15(3):311–332

    Google Scholar 

  • Sheriff RE (1997) Seismic resolution a key element. AAPG Explor 18(10):44–51

    Google Scholar 

  • Shi W, Caballero J, Huszár F, Totz J, Aitken AP, Bishop R, Rueckert D, Wang Z (2016) Real-time single image and video super-resolution using an efficient sub-pixel convolutional neural network. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1874–1883

  • Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. ar**v preprint ar**v:1409.1556

  • Song S, Mukerji T, Hou J, Zhang D, Lyu X (2022) Gansim-3d for conditional geomodeling: theory and field application. Water Resour Res 58(7):e2021WR031865

    Google Scholar 

  • Song S, Mukerji T, Hou J (2021a) Bridging the gap between geophysics and geology with generative adversarial networks. IEEE Trans Geosci Remote Sens 60:1–11

  • Song S, Mukerji T, Hou J (2021b) Gansim: conditional facies simulation using an improved progressive growing of generative adversarial networks (gans). Math Geosci 53:1413–1444

  • Song S, Mukerji T, Hou J (2021c) Geological facies modeling based on progressive growing of generative adversarial networks (gans). Comput Geosci 25:1251–1273

  • Spitz S (1991) Seismic trace interpolation in the fx domain. Geophysics 56(6):785–794

    Google Scholar 

  • Ulfers A, Zeeden C, Wagner B, Krastel S, Buness H, Wonik T (2022) Borehole logging and seismic data from lake Ohrid (North Macedonia/Albania) as a basis for age-depth modelling over the last one million years. Quatern Sci Rev 276:107295

    Google Scholar 

  • Wang Y (2006) Inverse q-filter for seismic resolution enhancement. Geophysics 71(3):V51–V60

    Google Scholar 

  • Wang S, Lin C (2004) The analysis of seismic data structure and oil and gas prediction. Appl Geophys 1(2):75–82

    Google Scholar 

  • Wang Z, Bovik AC, Sheikh HR, Simoncelli EP (2004) Image quality assessment: from error visibility to structural similarity. IEEE Trans Image Process 13(4):600–612

    Google Scholar 

  • Wang X, Yu K, Wu S, Gu J, Liu Y, Dong C, Qiao Y, Change Loy C (2018) Esrgan: enhanced super-resolution generative adversarial networks. In Proceedings of the European conference on computer vision (ECCV) workshops, pp 0–0

  • Wang Q, Liu Y, Liu C, Zheng Z (2021) Multichannel adaptive deconvolution based on streaming prediction-error filter. J Geophys Eng 18(6):825–833

    Google Scholar 

  • Wu X, Liang L, Shi Y, Fomel S (2019) Faultseg3d: using synthetic data sets to train an end-to-end convolutional neural network for 3d seismic fault segmentation. Geophysics 84(3):IM35–IM45

    Google Scholar 

  • Wu X, Geng Z, Shi Y, Pham N, Fomel S, Caumon G (2020) Building realistic structure models to train convolutional neural networks for seismic structural interpretation. Geophysics 85(4):WA27–WA39

    Google Scholar 

  • Zhang YG, Wang Y, Yin JJ (2010) Single point high density seismic data processing analysis and initial evaluation. Shiyou Diqiu Wuli Kantan (Oil Geophys Prospect) 45(2):201–207

    Google Scholar 

  • Zhang Y, Tian Y, Kong Y, Zhong B, Fu Y (2018) Residual dense network for image super-resolution. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2472–2481

  • Zhang C, Sun Z, Manatschal G, Pang X, Qiu N, Su M, Zheng J, Li H, Gu Y, Zhang J, Zhao Y (2021) Syn-rift magmatic characteristics and evolution at a sediment-rich margin: insights from high-resolution seismic data from the South China Sea. Gondwana Res 91:81–96

    Google Scholar 

  • Zheng Q, Zhang D (2022) Digital rock reconstruction with user-defined properties using conditional generative adversarial networks. Transp Porous Media 144(1):255–281

    Google Scholar 

  • Zhong Z, Carr TR, Wu X, Wang G (2019) Application of a convolutional neural network in permeability prediction: a case study in the Jacksonburg–Stringtown oil field, West Virginia, USA. Geophysics 84(6):B363–B373

    Google Scholar 

  • Zhong Z, Sun AY, Wu X (2020) Inversion of time-lapse seismic reservoir monitoring data using cyclegan: a deep learning-based approach for estimating dynamic reservoir property changes. J Geophys Res Solid Earth 125(3):e2019JB018408

    CAS  Google Scholar 

  • Zhu L, Liu E, McClellan JH (2015) Seismic data denoising through multiscale and sparsity-promoting dictionary learning. Geophysics 80(6):WD45–WD57

    Google Scholar 

  • Zhu JY, Park T, Isola P, Efros AA (2017) Unpaired image-to-image translation using cycle-consistent adversarial networks. In: Proceedings of the IEEE international conference on computer vision, pp 2223–2232

  • Zhu W, Mousavi SM, Beroza GC (2019) Seismic signal denoising and decomposition using deep neural networks. IEEE Trans Geosci Remote Sens 57(11):9476–9488

    Google Scholar 

Download references

Acknowledgements

This study was financially supported by the Strategic Priority Research Program of the Chinese Academy of Sciences (Grant No. XDA14010302). We thank the editors and reviewers for their helpful comments and suggestions.

Author information

Authors and Affiliations

  1. Key Laboratory of Theory and Technology of Petroleum Exploration and Development in Hubei Province, China University of Geosciences, Wuhan, China

    Lei Lin, Zhi Zhong, Chenglong Li & Heng Zhang

  2. Monash University, Melbourne, Australia

    Chuyang Cai

Authors
  1. Lei Lin
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhi Zhong
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Chuyang Cai
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Chenglong Li
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Heng Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Zhi Zhong.

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Lin, L., Zhong, Z., Cai, C. et al. SeisGAN: Improving Seismic Image Resolution and Reducing Random Noise Using a Generative Adversarial Network. Math Geosci 56, 723–749 (2024). https://doi.org/10.1007/s11004-023-10103-8

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11004-023-10103-8

Keywords

Search

Navigation