Skip to main content
Log in

Prediction of gas hydrate saturation using machine learning and optimal set of well-logs

  • Original Paper
  • Published:
Computational Geosciences Aims and scope Submit manuscript

Abstract

Resistivity and acoustic logs are widely used to estimate gas hydrate saturation in various sedimentary systems using one of the two popular methods ((1) acoustic velocity and (2) electrical resistivity), but the limitations of these two methods are often overlooked, which include (i) well-specific calibration of empirical exponents in the electrical resistivity method, (ii) assumption of known pore morphology for gas hydrates in the acoustic velocity method, and (iii) presence of unknown mineralogy and bulk modulus terms in the acoustic velocity method. NMR-density porosity-derived gas hydrate saturation based on the analysis of the transverse magnetization relaxation time (T2) is considered the most precise method, but acquisition of NMR-based logs is limited at relatively recent drilled sites; additionally, its use in conventional oil and gas reservoirs is not that common due to higher cost and operational deployment limitations associated with acquiring NMR well-logs. This study proposes a new method that predicts gas hydrate saturation (Sh) for any well using porosity, bulk density, and compressional wave (P wave) velocity well-logs with neural network (or stochastic gradient descent regression) without any well-specific calibration and/or other aforementioned shortcomings of the existing methods. The method is developed by examining the underlying dependency between Sh and different combinations of well-logs, chosen from 6 routine logs, with 12 different machine learning (ML) algorithms. The accuracy of the proposed method in predicting Sh is ~ 84%, which is better than the accuracy of seismic and electrical resistivity methods (≤ 75%) per the results reported by three different studies. The robustness of the method in the specific case of permafrost-associated gas hydrates is demonstrated with well-log data from two wells drilled on the Alaska North Slope.

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

Access this article

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

Instant access to the full article PDF.

Institutional subscriptions

Similar content being viewed by others

Data availability

Well-log data used in this study can be downloaded from the following link: https://edx.netl.doe.gov/dataset/answelllogs. Other data generated or used in this study are included in this paper.

References

  1. Coates, G.R., Xiao, L., Prammer, M.G.: NMR logging: principles and applications. Haliburton Energy Services. (1999)

  2. Mohaghegh, S., Richardson, M., Ameri, S.: Virtual magnetic imaging logs: generation of synthetic MRI logs from conventional well logs. Society of Petroleum Engineers. (1998)

  3. Jamshidian, M., Hadian, M., Zadeh, M.M., Kazempoor, Z., Bazargan, P., Salehi, H.: Prediction of free flowing porosity and permeability based on conventional well logging data using artificial neural networks optimized by imperialist competitive algorithm – a case study in the south pars gas field. J. Nat. Gas Sci. Eng. 24, 89–98 (2015). https://doi.org/10.1016/j.jngse.2015.02.026

    Article  Google Scholar 

  4. Li, H., Misra, S., He, J.: Neural network modeling of in situ fluid-filled pore size distributions in subsurface shale reservoirs under data constraints. Neural Comput. Applic. 32, 3873–3885 (2019). https://doi.org/10.1007/s00521-019-04124-w

    Article  Google Scholar 

  5. Akkurt, R., Conroy, T.T., Psaila, D., Paxton, A., Low, J., Spaans, P.: Accelerating and enhancing petrophysical analysis with machine learning: a case study of an automated system for well log outlier detection and reconstruction. Society of Petrophysicists and Well-Log Analysts. (2018)

  6. Wu, P.-Y., Jain, V., Kulkarni, M.S., Abubakar, A.: Machine learning-based method for automated well-log processing and interpretation. In SEG Technical Program Expanded Abstracts 2018; SEG Technical Program Expanded Abstracts; Society of Exploration Geophysicists, pp. 2041–2045 (2018)

  7. Alvarado, V., Ranson, A., Hernandez, K., Manrique, E., Matheus, J., Liscano, T., Prosperi, N.: Selection of EOR/IOR opportunities based on machine learning. Society of Petroleum Engineers, (2002)

  8. Kamari, A., Nikookar, M., Sahranavard, L., Mohammadi, A.H.: Efficient screening of enhanced oil recovery methods and predictive economic analysis. Neural Comput. Applic. 25, 815–824 (2014). https://doi.org/10.1007/s00521-014-1553-9

    Article  Google Scholar 

  9. Tarrahi, M., Afra, S., Surovets, I.: A novel automated and probabilistic EOR screening method to integrate theoretical screening criteria and real field EOR practices using machine learning algorithms. Society of Petroleum Engineers. (2015)

  10. Khazali, N., Sharifi, M., Ahmadi, M.A.: Application of fuzzy decision tree in EOR screening assessment. J. Petrol. Sci. Eng. 177, 167–180 (2019). https://doi.org/10.1016/j.petrol.2019.02.001

    Article  Google Scholar 

  11. Noshi, C.I., Assem, A.I., Schubert, J.J.: The role of big data analytics in exploration and production: a review of benefits and applications. Society of Petroleum Engineers. (2018)

  12. Aizenberg, I., Sheremetov, L., Villa-Vargas, L., Martinez-Muñoz, J.: Multilayer neural network with multi-valued neurons in time series forecasting of oil production. Neurocomputing. 175, 980–989 (2016). https://doi.org/10.1016/j.neucom.2015.06.092

    Article  Google Scholar 

  13. Cao, Q., Banerjee, R., Gupta, S., Li, J., Zhou, W., Jeyachandra, B.: Data driven production forecasting using machine learning. Society of Petroleum Engineers. (2016)

  14. Ma, X., Liu, Z.: Predicting the oil production using the novel multivariate nonlinear model based on Arps decline model and kernel method. Neural Comput. Applic. 29, 579–591 (2018). https://doi.org/10.1007/s00521-016-2721-x

    Article  Google Scholar 

  15. Ristanto, T.: Machine learning applied to multiphase production problems. Stanford University, MS Thesis (2018)

    Google Scholar 

  16. Spesivtsev, P., Sinkov, K., Sofronov, I., Zimina, A., Umnov, A., Yarullin, R., Vetrov, D.: Predictive model for bottomhole pressure based on machine learning. J. Petrol. Sci. Eng. 166, 825–841 (2018). https://doi.org/10.1016/j.petrol.2018.03.046

    Article  Google Scholar 

  17. Tian, C., Horne, R.: Applying machine-learning techniques to interpret flow-rate, pressure, and temperature data from permanent downhole gauges. SPE Reserv. Eval. Eng. 22, 386–401 (2019). https://doi.org/10.2118/174034-PA

    Article  Google Scholar 

  18. Lee, M.W., Hutchinson, D.R., Collett, T.S., Dillon, W.P.: Seismic velocities for hydrate-bearing sediments using weighted equation. J. Geophys. Res. Solid Earth. 101, 20347–20358 (1996). https://doi.org/10.1029/96JB01886

    Article  Google Scholar 

  19. Helgerud, M.B., Dvorkin, J., Nur, A., Sakai, A., Collett, T.: Elastic-wave velocity in marine sediments with gas hydrates: effective medium modeling. Geophys. Res. Lett. 2021–2024, 26–2024 (1999). https://doi.org/10.1029/1999GL900421

    Article  Google Scholar 

  20. Chand, S., Minshull, T.A., Gei, D., Carcione, J.M.: Elastic velocity models for gas-hydrate-bearing sediments—a comparison. Geophys. J. Int. 159, 573–590 (2004). https://doi.org/10.1111/j.1365-246X.2004.02387.x

    Article  Google Scholar 

  21. Kumar, D., Sen, M.K., Bangs, N.L.: Gas hydrate concentration and characteristics within hydrate ridge inferred from multicomponent seismic reflection data. J. Geophys. Res. Solid Earth. 112, (2007). https://doi.org/10.1029/2007JB004993

  22. Kumar, D., Dash, R., Dewangan, P.: Methods of gas hydrate concentration estimation with field examples. Society of Petroleum Geophysicists. 76, (2009)

  23. Collett, T.S., Lee, M.W.: Well log characterization of natural gas-hydrates. Petrophysics. 53, 348–367 (2012)

    Google Scholar 

  24. Helgerud, M.B.: Wave speeds in gas hydrate and sediments containing gas hydrate: a laboratory and modeling study. Ph.D. Thesis. (2001)

  25. Dvorkin, J., Nur, A.: Time-average equation revisited. Geophysics. 63, 460–464 (1998). https://doi.org/10.1190/1.1444347

    Article  Google Scholar 

  26. Dvorkin, J., Nur, A., Yin, H.: Effective properties of cemented granular materials. Mech. Mater. 18, 351–366 (1994). https://doi.org/10.1016/0167-6636(94)90044-2

    Article  Google Scholar 

  27. Dvorkin, J., Nur, A.: Elasticity of high-porosity sandstones: theory for two North Sea data sets. GEOPHYSICS. 61, 1363–1370 (1996). https://doi.org/10.1190/1.1444059

    Article  Google Scholar 

  28. Ecker, C., Dvorkin, J., Nur, A.: Sediments with gas hydrates: internal structure from seismic AVO. GEOPHYSICS. 1998, 63 (1659–1669). https://doi.org/10.1190/1.1444462

    Article  Google Scholar 

  29. Singh, H., Myshakin, E.M., Seol, Y.: A non-empirical relative permeability model for three phases in hydrate bearing sediments. SPE Journal 2018, SPE-193996-PA, doi:SPE-193996-PA

  30. Singh, H., Mahabadi, N., Myshakin, E.M., Seol, Y.: A mechanistic model for relative permeability of gas and water flow in hydrate-bearing porous media with capillarity. Water Resour. Res. 2019, 0, doi:https://doi.org/10.1029/2018WR024278, 55, 3414, 3432

  31. Dugarov, G.A., Duchkov, A.A., Duchkov, A.D., Drobchik, A.N.: Laboratory validation of effective acoustic velocity models for samples bearing hydrates of different type. J. Nat. Gas Sci. Eng. 63, 38–46 (2019). https://doi.org/10.1016/j.jngse.2019.01.007

    Article  Google Scholar 

  32. Archie, G.E.: The electrical resistivity log as an aid in determining some reservoir characteristics. Transactions of the AIME. 146, 54–62 (1942). https://doi.org/10.2118/942054-G

    Article  Google Scholar 

  33. Lu, S., McMechan, G.A.: Estimation of gas hydrate and free gas saturation, concentration, and distribution from seismic data. GEOPHYSICS. 67, 582–593 (2002). https://doi.org/10.1190/1.1468619

    Article  Google Scholar 

  34. Worthington, P.F.: Recognition and evaluation of low-resistivity pay. Pet. Geosci. 6, 77–92 (2000). https://doi.org/10.1144/petgeo.6.1.77

    Article  Google Scholar 

  35. Kleinberg, R.L., Flaum, C., Collett, T.S.: Magnetic resonance log of JAPEX/JNOC/GSC et al. Mallik 5L-38 gas hydrate production research well: gas hydrate saturation, growth habit, and relative permeability. Bulletin-Geological Survey of Canada. 585, 114 (2005)

  36. Lee, M.W.: Models for gas hydrate-bearing sediments inferred from hydraulic permeability and elastic Velocities: USGS scientific investigations report 2008–5219, p. 14 (2008)

  37. Collett, T.S., Lewis, R.E., Dallimore, S.R.: Mallik 5L-38 gas hydrate production research well downhole well-log and core montages. Bulletin-Geological Survey of Canada. 585, 111 (2005)

    Google Scholar 

  38. Dallimore, S.R., Collett, T.S., Taylor, A.E., Uchida, T., Weber, M., Chandra, A., Mroz, T.H., Caddel, E.M., Inoue, T.: Scientific results from the Mallik 2002 gas hydrate production research well program, Mackenzie Delta, northwest territories. Canada: Preface. Geological Survey of Canada. 585, 1–16 (2005)

  39. Jain, V., Saumya, S., Vij, J., Singh, J., Singh, B., Pattnaik, S., Oli, A., Kumar, P., Collett, T.S.: New technique for accurate porosity estimation from logging-while-drilling nuclear magnetic resonance data, NGHP-02 expedition, offshore. India. Marine and Petroleum Geology. 108, 570–580 (2018). https://doi.org/10.1016/j.marpetgeo.2018.11.001

  40. Hastie, T., Tibshirani, R., Friedman, J.: The elements of statistical learning, vol. 1. Springer series in statistics, New York (2001)

    Book  Google Scholar 

  41. Shawe-Taylor, D., Shawe-Taylor, J., Cristianini, N.: Kernel methods for pattern analysis. Cambridge University Press. (2004)

  42. Smola, A.J., Schölkopf, B.: A tutorial on support vector regression. Stat. Comput. 14, 199–222 (2004). https://doi.org/10.1023/B:STCO.0000035301.49549.88

    Article  Google Scholar 

  43. Robbins, H., Monro, S.: A stochastic approximation method. Ann. Math. Stat. 22, 400–407 (1951)

    Article  Google Scholar 

  44. Breiman, L., Friedman, J., Stone, C.J., Olshen, R.A.: Classification and regression trees. Taylor & Francis. (1984)

  45. Breiman, L.: Random Forests. Machine Learning. 45, 5–32 (2001). https://doi.org/10.1023/A:1010933404324

  46. Schapire, R.E., Freund, Y.: Boosting: foundations and algorithms. MIT Press. (2012)

  47. Friedman, J.H.: Greedy function approximation: a gradient boosting machine. Ann. Stat. 29, 1189–1232 (2001)

    Article  Google Scholar 

  48. Dudani, S.A.: The distance-weighted k-nearest-neighbor rule. IEEE Trans. Syst. Man Cybern. SMC-6, 325–327 (1976). https://doi.org/10.1109/TSMC.1976.5408784

    Article  Google Scholar 

  49. Pal, S.K., Mitra, S.: Multilayer perceptron, fuzzy sets, and classification. IEEE Trans. Neural Netw. 3, 683–697 (1992). https://doi.org/10.1109/72.159058

    Article  Google Scholar 

  50. Friedman, J.H.: Multivariate adaptive regression splines. Ann. Statist. 19, 1–67 (1991). https://doi.org/10.1214/aos/1176347963

    Article  Google Scholar 

  51. Hastie, T.J., Tibshirani, R.J.: Generalized additive models. CRC Press. (1990)

  52. Bhowmick, D.; Shankar, U.; Maiti, S. Revisiting supervised learning in the context of predicting gas hydrate saturation. European Association of Geoscientists & Engineers, 1–5 (2016)

  53. Boswell, R., Hunter, R., Collett, T.S., Digert, S., Hancock, S.H., Weeks, M., Team, M.E.S.: Investigation of gas hydrate-bearing sandstone reservoirs at the “Mount Elbert” stratigraphic test well. Milne Point, Alaska (2008). https://doi.org/10.14288/1.0041029

    Book  Google Scholar 

  54. Inks, T.L., Agena, W.F.: Successful gas hydrate prospecting using 3D seismic - a case study for the Mt. Elbert prospect, Milne Point, North Slope Alaska. 27, 473–477 (2008). https://doi.org/10.1190/1.3054848

    Article  Google Scholar 

  55. Good, R., Fletcher, H.J.: Reporting explained variance. J. Res. Sci. Teach. 18, 1–7 (1981). https://doi.org/10.1002/tea.3660180102

    Article  Google Scholar 

  56. Abu-Mostafa, Y.S., Magdon-Ismail, M., Lin, H.-T.: Learning from data: a short course; AMLBook.com. (2012)

    Google Scholar 

  57. Gavves, E., Mensink, T., Tommasi, T., Snoek, C.G.M., Tuytelaars, T.: Active transfer learning with zero-shot priors: reusing past datasets for future tasks. arXiv:1510.01544 [cs] 2015

  58. Shankar, U., Gupta, D.K., Bhowmick, D., Sain, K.: Gas hydrate and free gas saturations using rock physics modelling at site NGHP-01-05 and 07 in the Krishna–Godavari Basin, eastern Indian margin. J. Petrol. Sci. Eng. 106, 62–70 (2013). https://doi.org/10.1016/j.petrol.2013.04.004

    Article  Google Scholar 

  59. Myshakin, E.M., Ajayi, T., Anderson, B.J., Seol, Y., Boswell, R.: Numerical simulations of depressurization-induced gas production from gas hydrates using 3-D heterogeneous models of L-pad, Prudhoe Bay unit, North Slope Alaska. J. Nat. Gas Sci. Eng. 35, 1336–1352 (2016). https://doi.org/10.1016/j.jngse.2016.09.070

    Article  Google Scholar 

  60. Myshakin, E.M., Seol, Y., Lin, J.-S., Uchida, S., Collett, T.S., Boswell, R.: Numerical simulations of depressurization-induced gas production from an interbedded turbidite gas hydrate-bearing sedimentary section in the offshore India: site NGHP-02-16 (area-B). Mar. Pet. Geol. 108, 619–638 (2018). https://doi.org/10.1016/j.marpetgeo.2018.10.047

    Article  Google Scholar 

  61. Yuan, Y., Xu, T., Xia, Y., Xin, X.: Evaluation of gas productivity from layered heterogeneity methane hydrate reservoirs by depressurisation. Offshore Technology Conference. (2018)

  62. Cook, A.E., Waite, W.F.: Archie’s saturation exponent for natural gas hydrate in coarse-grained reservoirs. J. Geophys. Res. Solid Earth. 2069–2089, 123–2089 (2018). https://doi.org/10.1002/2017JB015138

    Article  Google Scholar 

  63. Myshakin, E.M., Anderson, B.J., Rose, K., Boswell, R.: Simulations of variable bottomhole pressure regimes to improve production from the double-unit Mount Elbert, Milne point unit, north slope Alaska hydrate deposit. Energy Fuel. 25, 1077–1091 (2011). https://doi.org/10.1021/ef101407b

    Article  Google Scholar 

Download references

Acknowledgments

This research was performed in support of the National Energy Technology Laboratory’s ongoing research on numerical simulations support for reservoir characterization and production performance prediction of gas hydrate reservoirs. This research was supported in part by an appointment to the National Energy Technology Laboratory Research Participation Program, sponsored by the US Department of Energy and administered by the Oak Ridge Institute for Science and Education. Research performed by Leidos Research Support Team (LRST) staff was conducted under the RSS contract 89243318CFE000003. Thanks to Ray Boswell (US DOE) and Tim S. Collett (USGS) for their comments that were helpful in improving the manuscript.

Code availability

The code for this study was written in Python using scikit-learn and Tensorflow as the machine learning packages.

Funding

This research was supported in part by an appointment to the National Energy Technology Laboratory Research Participation Program, sponsored by the US Department of Energy and administered by the Oak Ridge Institute for Science and Education. This work was funded by the Department of Energy, National Energy Technology Laboratory, an agency of the US Government, through a support contract with LRST.

Author information

Authors and Affiliations

Authors

Contributions

HS conceived the research idea, designed the workflow, and wrote the code. H.S., E.M.M., and Y.S. analyzed the results. H.S. wrote the manuscript, E.M.M. and Y.S. edited it. All authors have reviewed and approved the final version of the manuscript.

Corresponding authors

Correspondence to Harpreet Singh or Yongkoo Seol.

Ethics declarations

Conflict of interest

The authors declare there is no competing interest.

Disclaimer

Neither the United States Government nor any agency thereof, nor any of their employees, nor LRTS, nor any of their employees, makes any warranty, expressed or implied, or assumes any legal liability or responsibility for the accuracy, completeness, or usefulness of any information, apparatus, product, or process disclosed, or represents that its use would not infringe privately owned rights. Reference herein to any specific commercial product, process, or service by trade name, trademark, manufacturer, or otherwise, does not necessarily constitute or imply its endorsement, recommendation, or favoring by the United States Government or any agency thereof. The views and opinions of authors expressed herein do not necessarily state or reflect those of the United States Government or any agency thereof.

Additional information

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Electronic supplementary material

ESM1

(DOCX 2333 kb)

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Singh, H., Seol, Y. & Myshakin, E.M. Prediction of gas hydrate saturation using machine learning and optimal set of well-logs. Comput Geosci 25, 267–283 (2021). https://doi.org/10.1007/s10596-020-10004-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10596-020-10004-3

Keywords

Navigation