1887

Abstract

Summary

Utilizing time lapse seismic for determining pore pressure and saturation effects is relevant for hydrocarbon production as well as natural gas and CO storage. Its quantitative interpretation enables a detailed understanding of 4D evolution of fluid/gas migration. We focus on the rock physics model to invert for rock physical parameters. A training dataset is generated with a forward modeling operator, with parameters adapted from a 65 m deep unconsolidated high porosity reservoir from the Svelvik field laboratory, Norway. Two independent rock physical formulations are considered and multiple deep fully connected neural networks conditioned and trained to invert for different rock physics parameters. The network can rapidly derive rock physical parameters such as pressure, saturation, and porosity from seismic attributes, thus acting as an inversion tool. Subsets of the input parameters can be preset based on prior knowledge of a site. Utilizing neural networks in discriminating pressure and saturation allows real time field site conformance verification during seismic campaigns targeting 4D effects in an operations scenario.

Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202032007
2020-11-30
2024-03-29
Loading full text...

Full text loading...

References

  1. Avseth, P., Mukerji, T., and Mavko, G.
    [2010] Quantitative seismic interpretation: Applying rock physics tools to reduce interpretation risk: Cambridge university press.
    [Google Scholar]
  2. Biot, M. A.
    [1956] Theory of elastic waves in a fluid-saturated porous solid. 1. Low frequency range. J. Acoust. Soc. Am., 28, 168–178.
    [Google Scholar]
  3. Bhowmick, D., Gupta, D. K., Maiti, S., and Shankar, U.
    [2018] Velocity-porosity supermodel: A deep neural networks based concept: arXiv preprint arXiv:1804.07112.
    [Google Scholar]
  4. Carman, P. C.
    [1961] L’écoulement des gaz à travers les milieux poreux: Institut national des sciences et techniques nucléaires.
    [Google Scholar]
  5. Gal, Y., and Ghahramani, Z.
    [2016] Dropout as a bayesian approximation: Representing model uncertainty in deep learning: International Conference on Machine Learning, 1050–1059.
    [Google Scholar]
  6. Gassmann, F.
    [1951] Elasticity of porous media: Vierteljahresschrift der Naturforschenden Gesselschaft, 96, 1–23.
    [Google Scholar]
  7. Grana, D., Fjeldstad, T., and Omre, H.
    [2017] Bayesian gaussian mixture linear inversion for geophysical inverse problems: Mathematical Geosciences, 49, 493–515.
    [Google Scholar]
  8. Landrø, M.
    [2001] Discrimination between pressure and fluid saturation changes from time-lapse seismic data: Geophysics, 66, 836–844.
    [Google Scholar]
  9. Lang, X., and Grana, D.
    [2019] Rock physics modelling and inversion for saturation-pressure changes in time-lapse seismic studies: Geophysical Prospecting.
    [Google Scholar]
  10. Weinzierl, W., Wiese, B., Jordan, M., Schmidt-Hattenberger, C., Eliasson, P., Ringstad, C., Lüth, S., and Grimstad, A.
    [2018] Pre-operational considerations in a poro-elastic site assessment for the svelvik field lab: Presented at the Fifth CO2 Geological Storage Workshop.
    [Google Scholar]
  11. Xue, Y., Araujo, M., Lopez, J., Wang, K., and Kumar, G.
    [2019] Machine learning to reduce cycle time for time-lapse seismic data assimilation into reservoir management: Interpretation, 7, SE123–SE130.
    [Google Scholar]
  12. Zhang, W., and Stewart, R.
    [2019] Using fwi and deep learning to characterize velocity anomalies in crosswell seismic data, in SEG Technical Program Expanded Abstracts 2019: Society of Exploration Geophysicists, 2313–2317.
    [Google Scholar]
http://instance.metastore.ingenta.com/content/papers/10.3997/2214-4609.202032007
Loading
/content/papers/10.3997/2214-4609.202032007
Loading

Data & Media loading...

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