1887
Volume 74, Issue 1
  • E-ISSN: 1365-2478

Abstract

ABSTRACT

We present deep learning (DL) networks for three‐dimensional (3D) joint inversion of active seismic full waveform and passive seismic traveltime data to image reservoirs and their properties and quantify imaging uncertainties. Active seismic full‐waveform data can provide high‐resolution monitoring images but are collected only intermittently because of their high acquisition cost. In contrast, passive seismic data can be gathered at relatively low cost between regular active surveys, although their imaging quality can be compromised by factors such as low signal‐to‐noise ratios and limited ray coverage of the target. Although these datasets are routinely acquired together at CO storage sites, their combined inversion within a 3D DL framework has not been previously demonstrated. To our knowledge, this is the first study to address this gap, combining the strength of both data types. For efficient data storage and DL training with large 3D seismic datasets, we use a 3D data matrix in which a random number of passive seismic traveltime data are stored as parabolic envelopes using one‐hot encoding and a 3D full‐waveform data matrix in which multiple shot gathers are summed. Two network architectures are evaluated: a single‐encoder U‐Net for single‐data type inversion and a dual‐encoder U‐Net for joint inversion of active and passive seismic data. We also evaluate the single‐encoder U‐Net for joint inversion by concatenating full‐waveform data and traveltime data. We propose a systematic approach for selecting an optimal dropout rate that balances regularization during training and Monte Carlo dropout‐based uncertainty quantification during prediction by examining the correlation coefficient between standard deviation and prediction error, along with the training misfit, across a range of dropout rates. 3D DL inversion experiments include five different network configurations, with evaluations under ideal, noisy and dropout‐enabled conditions. Both model and data uncertainties are assessed, as well as their combined effects. Across all conditions, the networks consistently predict accurate CO saturation models with low prediction errors, such as a structural similarity index of 0.993 and CO difference of 1.1%. Uncertainty estimates show strong spatial correlation with prediction errors, confirming the effectiveness of the proposed dropout selection approach. The results demonstrate that our DL approach, utilizing compact data representations and appropriate uncertainty quantification, yields accurate subsurface images under various inversion conditions and provides valuable insights into the reliability of predictions.

© 2026 European Association of Geoscientists & Engineers. Published 2026. This article is a U.S. Government work and is in the public domain in the USA.
Loading

Article metrics loading...

/content/journals/10.1111/1365-2478.70126
2026-01-05
2026-02-06

  • From This Site

    /content/journals/10.1111/1365-2478.70126
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Abadi, M., P.Barham, J.Chen, et al. 2016. “TensorFlow: A System for Large‐Scale Machine Learning.” In 12th USENIX Symposium on Operating Systems Design and Implementation (OSDI 16). USENIX.
  2. Alkhalifah, T., and S.Fomel. 2001. “Implementing the Fast Marching Eikonal Solver: Spherical Versus Cartesian Coordinates.” Geophysical Prospecting49: 165–178.
     [Google Scholar]
  3. Alumbaugh, D., E.Gasperikova, D.Crandall, et al. 2024. “The Kimberlina Synthetic Multiphysics Dataset for CO2 Monitoring Investigations.” Geoscience Data Journal11: 216–234.
     [Google Scholar]
  4. Alumbaugh, D. L., J.Correa, P.Jordan, B.Petras, S.Chundur, and W.Abriel. 2024. “An Assessment of the Role of Geophysics in Future US Geologic Carbon Storage Projects.” Leading Edge43: 72–83.
     [Google Scholar]
  5. Araya‐Polo, M., J.Jennings, A.Adler, and T.Dahlke. 2018. “Deep‐Learning Tomography.” Leading Edge37: 58–66.
     [Google Scholar]
  6. Celaya, A., and M.Araya‐Polo. 2024. “Deep Learning‐Based Joint Inversion of Time‐Lapse Surface Gravity and Seismic Data for Monitoring of 3D CO2 Plumes.” In Fourth International Meeting for Applied Geoscience & Energy. Society of Exploration Geophysicists and American Association of Petroleum Geologists.
  7. Chollet, F.2015. Keras. https://keras.io.
  8. Chollet, F.2021. Deep Learning With Python: Simon and Schuster.
     [Google Scholar]
  9. Çiçek, Ö., A.Abdulkadir, S. S.Lienkamp, T.Brox, and O.Ronneberger. 2016. “3D U‐Net: Learning Dense Volumetric Segmentation From Sparse Annotation.” In Medical Image Computing and Computer‐Assisted Intervention—MICCAI 2016. Springer.
  10. Dai, Q., Y. H.Lee, H. H.Sun, G.Ow, M. L. M.Yusof, and A. C.Yucel. 2023. “3DInvNet: A Deep Learning‐Based 3D Ground‐Penetrating Radar Data Inversion.” IEEE Transactions on Geoscience and Remote Sensing61: 1–16.
     [Google Scholar]
  11. Feng, S., Y.Lin, and B.Wohlberg. 2021. “Multiscale Data‐Driven Seismic Full‐Waveform Inversion With Field Data Study.” IEEE Transactions on Geoscience and Remote Sensing60: 1–14.
     [Google Scholar]
  12. Fichtner, A.2010. Full Seismic Waveform Modelling and Inversion. Springer.
     [Google Scholar]
  13. Gal, Y., and Z.Ghahramani. 2016. “Dropout as a Bayesian Approximation: Representing Model Uncertainty in Deep Learning.” In Proceedings of the 33rd International Conference on Machine Learning (ICML). PMLR.
  14. Goodfellow, I., Y.Bengio, and A.Courville. 2016. Deep Learning: MIT Press.
     [Google Scholar]
  15. Guo, R., H.Zhou, X.Wei, et al. 2025. “Deep Joint Inversion of Multiple Geophysical Data With U‐Net Reparameterization.” Geophysics90, no. 3: WA61–WA75.
     [Google Scholar]
  16. Hicks, E., H.Hoeber, M.Houbiers, S. P.Lescoffit, A.Ratcliffe, and V.Vinje. 2016. “Time‐Lapse Full‐Waveform Inversion as a Reservoir‐Monitoring Tool—A North Sea Case Study.” Leading Edge35: 850–858.
     [Google Scholar]
  17. Hu, Y., X.Wei, X.Wu, et al. 2023. “A Deep Learning‐Enhanced Framework for Multiphysics Joint Inversion.” Geophysics88, no. 1: K13–K26.
     [Google Scholar]
  18. Hüllermeier, E., and W.Waegeman. 2021. “Aleatoric and Epistemic Uncertainty in Machine Learning: An Introduction to Concepts and Methods.” Machine Learning110: 457–506.
     [Google Scholar]
  19. James, G., D.Witten, T.Hastie, and R.Tibshirani. 2013. An Introduction to Statistical Learning. Springer.
     [Google Scholar]
  20. Jin, P., Y.Feng, S.Feng, et al. 2024. “An Empirical Study of Large‐Scale Data‐Driven Full Waveform Inversion.” Scientific Reports14: 20034.
     [Google Scholar]
  21. Kallivokas, L. F., A.Fathi, S.Kucukcoban, K. H.StokoeII, J.Bielak, and O.Ghattas. 2013. “Site Characterization Using Full Waveform Inversion.” Soil Dynamics and Earthquake Engineering47: 62–82.
     [Google Scholar]
  22. Kingma, D. P., and J.Ba. 2014. “Adam: A Method for Stochastic Optimization.” Preprint, arXiv, December 22.
  23. Li, T., A. K.Sahu, A.Talwalkar, and V.Smith. 2020. “Federated Learning: Challenges, Methods, and Future Directions.” IEEE Signal Processing Magazine37, no. 3: 50–60.
     [Google Scholar]
  24. Lin, Y., J.Theiler, and B.Wohlberg. 2023. “Physics‐Guided Data‐Driven Seismic Inversion: Recent Progress and Future Opportunities in Full‐Waveform Inversion.” IEEE Signal Processing Magazine40, no. 1: 115–133.
     [Google Scholar]
  25. Moczo, P., J. O.Robertsson, and L.Eisner. 2007. “The Finite‐Difference Time‐Domain Method for Modeling of Seismic Wave Propagation.” Advances in Geophysics48: 421–516.
     [Google Scholar]
  26. Nocedal, J., and S. J.Wright. 2006. Numerical Optimization. Springer New York.
     [Google Scholar]
  27. Oh, S., and J.Byun. 2021. “Bayesian Uncertainty Estimation for Deep Learning Inversion of Electromagnetic Data.” IEEE Geoscience and Remote Sensing Letters19: 1–5.
     [Google Scholar]
  28. Petrov, P. V., and G. A.Newman. 2014. “Three‐Dimensional Inverse Modelling of Damped Elastic Wave Propagation in the Fourier Domain.” Geophysical Journal International198: 1599–1617.
     [Google Scholar]
  29. Queißer, M., and S. C.Singh. 2013. “Full Waveform Inversion in the Time Lapse Mode Applied to CO2 Storage at Sleipner.” Geophysical Prospecting61: 537–555.
     [Google Scholar]
  30. Rojas‐Gómez, R., J.Yang, Y.Lin, J.Theiler, and B.Wohlberg. 2020. “Physics‐Consistent Data‐Driven Waveform Inversion With Adaptive Data Augmentation.” IEEE Geoscience and Remote Sensing Letters19: 1–5.
     [Google Scholar]
  31. Ronneberger, O., P.Fischer, and T.Brox. 2015. “U‐Net: Convolutional Networks for Biomedical Image Segmentation.” Medical Image Computing and Computer‐Assisted Intervention—MICCAI 201518: 234–241.
     [Google Scholar]
  32. Rutqvist, J., A. P.Rinaldi, F.Cappa, et al. 2016. “Fault Activation and Induced Seismicity in Geological Carbon Storage–Lessons Learned From Recent Modeling Studies.” Journal of Rock Mechanics and Geotechnical Engineering8: 789–804.
     [Google Scholar]
  33. Shin, C., and Y.Ho Cha. 2009. “Waveform Inversion in the Laplace–Fourier Domain.” Geophysical Journal International177: 1067–1079.
     [Google Scholar]
  34. Srivastava, N., G.Hinton, A.Krizhevsky, I.Sutskever, and R.Salakhutdinov. 2014. “Dropout: A Simple Way to Prevent Neural Networks From Overfitting.” Journal of Machine Learning Research15: 1929–1958.
     [Google Scholar]
  35. Um, E. S., D.Alumbaugh, M.Commer, et al. 2023. “Deep Learning Multiphysics Network for Imaging CO2 Saturation and Estimating Uncertainty in Geological Carbon Storage.” Geophysical Prospecting72: 183–198.
     [Google Scholar]
  36. Um, E. S., D.Alumbaugh, Y.Lin, and S.Feng. 2023. “Real‐Time Deep‐Learning Inversion of Seismic Full Waveform Data for CO2 Saturation and Uncertainty in Geological Carbon Storage Monitoring.” Geophysical Prospecting72: 199–212.
     [Google Scholar]
  37. Um, E. S., M.Commer, and G. A.Newman. 2014. “A Strategy for Coupled 3D Imaging of Large‐Scale Seismic and Electromagnetic Data Sets: Application to Subsalt Imaging.” Geophysics79: ID1–ID13.
     [Google Scholar]
  38. Um, E. S., J. M.Harris, and D. L.Alumbaugh. 2012. “An Iterative Finite Element Time‐Domain Method for Simulating Three‐Dimensional Electromagnetic Diffusion in Earth.” Geophysical Journal International190: 871–886.
     [Google Scholar]
  39. Virieux, J., A.Asnaashari, R.Brossier, L.Métivier, A.Ribodetti, and W.Zhou. 2017. “An Introduction to Full Waveform Inversion.” In Encyclopedia of Exploration Geophysics. SEG.
     [Google Scholar]
  40. Virieux, J., and S.Operto. 2009. “An Overview of Full‐Waveform Inversion in Exploration Geophysics.” Geophysics74: WCC1–WCC26.
     [Google Scholar]
  41. Wainwright, H. M., S.Finsterle, Q.Zhou, and J. T.Birkholzer. 2013. “Modeling the Performance of Large‐Scale CO2 Storage Systems: A Comparison of Different Sensitivity Analysis Methods.” International Journal of Greenhouse Gas Control17: 189–205.
     [Google Scholar]
  42. Wang, Z., A. C.Bovik, H. R.Sheikh, and E. P.Simoncelli. 2004. “Image Quality Assessment: From Error Visibility to Structural Similarity.” IEEE Transactions on Image Processing13, no. 4: 600–612.
     [Google Scholar]
  43. Wu, Y., and Y.Lin. 2019. “InversionNet: An Efficient and Accurate Data‐Driven Full Waveform Inversion.” IEEE Transactions on Computational Imaging6: 419–433.
     [Google Scholar]
  44. Yang, F., and J.Ma. 2019. “Deep‐Learning Inversion: A Next‐Generation Seismic Velocity Model Building Method.” Geophysics84: R583–R599.
     [Google Scholar]
  45. Zeng, Q., S.Feng, B.Wohlberg, and Y.Lin. 2021. “InversionNet3D: Efficient and Scalable Learning for 3‐D Full‐Waveform Inversion.” IEEE Transactions on Geoscience and Remote Sensing60: 1–16.
     [Google Scholar]
  46. Zhou, Q., and J. T.Birkholzer. 2011. “On Scale and Magnitude of Pressure Build‐Up Induced by Large‐Scale Geologic Storage of CO2.” Greenhouse Gases: Science and Technology1: 11–20.
     [Google Scholar]
  47. Zhu, W., K.Xu, E.Darve, B.Biondi, and G. C.Beroza. 2022. “Integrating Deep Neural Networks With Full‐Waveform Inversion: Reparameterization, Regularization, and Uncertainty Quantification.” Geophysics87: R93–R109.
     [Google Scholar]
/content/journals/10.1111/1365-2478.70126
Loading
3D Deep Learning Joint Inversion of Active Seismic Full Waveform and Passive Seismic Traveltime Data for Reservoir Imaging and Uncertainty Quantification
Geophysical Prospecting 74, e70126 (2026); https://doi.org/10.1111/1365-2478.70126
/content/journals/10.1111/1365-2478.70126
/content/journals/10.1111/1365-2478.70126
Loading

Data & Media loading...

  • Article Type: Research Article

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error