Skip to main content

Advertisement

SpringerLink
Log in

Bayesian and Neural Network Approaches to Estimate Deep Temperature Distribution for Assessing a Supercritical Geothermal System: Evaluation Using a Numerical Model

  • Original Paper
  • Published:
Natural Resources Research Aims and scope Submit manuscript

Abstract

The temperature distribution at depth is a key variable when assessing the potential of a supercritical geothermal resource as well as a conventional geothermal resource. Data-driven estimation by a machine-learning approach is a promising way to estimate temperature distributions at depth in geothermal fields. In this study, we developed two methodologies—one based on Bayesian estimation and the other on neural networks—to estimate temperature distributions in geothermal fields. These methodologies can be used to supplement existing temperature logs, by estimating temperature distributions in unexplored regions of the subsurface, based on electrical resistivity data, observed geological/mineralogical boundaries, and microseismic observations. We evaluated the accuracy and characteristics of these methodologies using a numerical model of the Kakkonda geothermal field, Japan, where a temperature above 500 °C was observed below a depth of about 3.7 km. When using geological and geophysical knowledge as prior information for the machine learning methods, the results demonstrate that the approaches can provide subsurface temperature estimates that are consistent with the temperature distribution given by the numerical model. Using a numerical model as a benchmark helps to understand the characteristics of the machine learning approaches and may help to identify ways of improving these methods.

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

Figure 1
Figure 2
Figure 3
Figure 4
Figure 5
Figure 6
Figure 7
Figure 8
Figure 9
Figure 10
Figure 11

Similar content being viewed by others

Data Availability

The datasets generated during the current study are available from the authors on reasonable request. The numerical model used in this study is provided from the Tohoku Sustainable & Renewable Energy Co. Inc. (TOUSEC), but restrictions apply to their availability, which were used under license for the current study and are therefore not publicly available.

Code Availability

The program codes used in this study are available from the authors on reasonable request.

References

  • Abadi, M., Barham, P., Chen, J., Chen, Z., Davis A., Dean, J., et al. (2016). TensorFlow: A system for large-scale machine learning. In Proceedings in 12th USENIX symposium on operating systems design and implementation, 978-1931971-33-1, pp. 265–283.

  • Akiba, T., Sano, S., Yanase, T., Ohta, T., & Koyama, M. (2019). Optuna: A next-generation hyperparameter optimization framework.

  • Bannard, J. E. (1975). Effect of density on the electrical conductance of aqueous sodium chloride solutions. Journal of Applied Electrochemistry, 5, 43–53.

    Article  Google Scholar 

  • Carpenter, B., Gelman, A., Hoffman, M. D., Lee, D., Goodrich, B., Brubaker, M., et al. (2017). Stan: A probabilistic programming language. Journal of Statistical Software. https://doi.org/10.18637/jss.v076.i01.

  • Cumming, W. (2016). Geophysics and resource conceptual models in geothermal exploration and development. In R. DiPippo (Ed.), Geothermal power generation (pp. 33–76). Woodhead Publishing.

    Google Scholar 

  • Elders, W. A., Friðleifsson, G. Ó., & Pálsson, B. (2014). Iceland deep drilling project: The first well, IDDP-1, drilled into magma. Geothermics, 49, 1. https://doi.org/10.1016/j.geothermics.2013.08.012

    Article  Google Scholar 

  • Fabbri, P. (2001). Probabilistic assessment of temperature in the Euganean geothermal area (Veneto region, NE Italy). Mathematical Geology, 33(6), 745–760.

    Article  Google Scholar 

  • Fournier, R. O. (1991). The transition from hydrostatic to greater than hydrostatic fluid pressure in presently active continental hydrothermal systems in crystalline rock. Geophysical Research Letters, 18(5), 955–958.

    Article  Google Scholar 

  • Frioleifsson, G. Ó., Elders, W. A., Zierenberg, R. A., Stefánsson, A., Fowler, A. P. G., Weisenberger, T. B., et al. (2017). The Iceland Deep Drilling Project 4.5 km deep well, IDDP-2, in the seawater-recharged Reykjanes geothermal field in SW Iceland has successfully reached its supercritical target. Scientific Drilling.

  • Gelman, A. (2013). Bayesian data analysis, 3rd edn. Chapman and Hall/CRC.

  • Glorot, X., Bordes, A., & Bengio, Y. (2011). Deep sparse rectifier neural networks. In Proceedings of the 14th international conference on artificial intelligence and statistics, pp. 315–323.

  • Glover, P. W. J., Hole, M. J., & Pous, J. (2000). A modified Archie’s law for two conducting phases. Earth and Planetary Science Letters, 180, 369–383.

    Article  Google Scholar 

  • Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning (adaptive computation and machine learning). The MIT Press.

    Google Scholar 

  • Heinrich, C. A. (2005). The physical and chemical evolution of low-salinity magmatic fluids at the porphyry to epithermal transition: A thermodynamic study. Mineralium Deposita, 39, 864–889.

    Article  Google Scholar 

  • Hinton, G. (2012). Neural networks for machine learnings. Coursera, video lectures.

  • Hoffman, M. D., & Gelman, A. (2014). The No-U-Turn sampler: Adaptively setting path lengths in Hamiltonian Monte Carlo. Journal of Machine Learning Research, 15, 1593–1623.

    Google Scholar 

  • Hokstad, K., & Tänavsuu-Milkeviciene, K. (2017). Temperature prediction by multigeophysical inversion: Application to the IDDP-2 well at Reykjanes, Iceland. GRC Transactions, 41, 1141–1152.

    Google Scholar 

  • Ikeuchi, K., Doi, N., Sakagawa, Y., Kamenosono, H., & Uchida, T. (1998). High temperature measurements in well WD-1a and the thermal structure of the Kakkonda geothermal system, Japan. Geothermics, 27, 591–607.

    Article  Google Scholar 

  • Ishitsuka, K., Mogi, T., Sugano, K., Yamaya, Y., Uchida, T., & Kajiwara, T. (2018). Resistivity-based temperature estimation of the Kakkonda geothermal field, Japan, using a neural network and neural kriging. IEEE Geoscience and Remote Sensing Letters, 15(8), 1154–1158.

    Article  Google Scholar 

  • Jordani, A., & Revil, A. (2009). Stochastic joint inversion of temperature and self-potential data. Geophysical Journal International, 179, 640–654.

    Article  Google Scholar 

  • Kato, O., Doi, N., Sakagawa, Y., & Uchida, T. (1998). Fracture systematics in and around well WD-1, Kakkonda geothermal field, Japan. Geothermics, 27, 609–629.

    Article  Google Scholar 

  • Kingma, D., & Ba, J. (2014). A method for stochastic optimization.

  • Kummerow, J., & Raab, S. (2015). Temperature dependence of electrical resistivity—Part I: Experimental investigations of hydrothermal fluids. Energy Procedia, 76, 240–246.

    Article  Google Scholar 

  • Moek, I. S. (2014). Catalog of geothermal play types based on geologic controls. Renewable and Sustainable Energy Reviews, 37, 867–882.

    Article  Google Scholar 

  • Neal, R. (2011). MCMC using Hamiltonian dynamics. In: S. Brooks, A. Gelman, G. Jones, &X.-L. Meng (Eds.), Handbook of Markov chain Monte Carlo. Chapman and Hall/CRC Press, pp. 113–162.

  • O’Sullivan, M. J., & O’Sullivan, J. P. (2016). Reservoir modeling and simulation for geothermal resource characterization and evaluation. In R. DiPippo (Ed.), Geothermal power generation (pp. 165–199). Woodhead Publishing.

    Google Scholar 

  • Ogawa, Y., Ichiki, M., Kanda, W., Mishina, M., & Asamori, K. (2014). Three-dimensional magnetotelluric imaging of crustal fluids and seismicity around Naruko volcano NE Japan. Earth, Planets and Space, 66, 158. https://doi.org/10.1186/s40623-014-0158-y

    Article  Google Scholar 

  • Okamoto, K., Asanuma, H., Ishibashi, T., Yamaya, Y., Saishu, H., Yanagisawa, N., et al. (2019). Geological and engineering features of developing ultra-high-temperature geothermal systems in the world. Geothermics, 82, 267–281.

    Article  Google Scholar 

  • Olhoeft, G. R. (1981). Electrical properties of granite with implications for the lower crust. Journal of Geophysical Research, 86(B2), 931–936.

    Article  Google Scholar 

  • Reinsh, T., Dobson, P., Asanuma, H., Huenges, E., Poletto, F., & Sanjuan, B. (2017). Utilizing supercritical geothermal systems: A review of past ventures and ongoing research activities. Geothermal Energy, 5, 16. https://doi.org/10.1186/s40517-017-0075-y

    Article  Google Scholar 

  • Rumelhart, D., & McClelland, J. (1988). Parallel distributed processing. MIT Press.

    Google Scholar 

  • Saishu, H., Okamoto, A., & Tsuchiya, N. (2014). The significance of silica precipitation on the formation of the permeable-impermeable boundary within earth’s crust. Terra Nova, 26(4), 253–259.

    Article  Google Scholar 

  • Sakagawa, Y., Aoyama, K., Ikeuchi, K., Takahashi, M., Kato, O., & Doi, N. (2000). Natural state simulation of the Kakkonda geothermal field, Japan. Proceedings World Geothermal Congress, 2000, 2839–2844.

    Google Scholar 

  • Sakuma, H., & Ichiki, M. (2016). Electrical conductivity of NaCl-H2O fluid in the crust. Journal of Geophysical Research, 121, 577–594.

    Google Scholar 

  • Sen, M. K., & Stoffa, P. L. (1995). Global optimization method in geophysical inversion. Cambridge Univ. Press.

    Google Scholar 

  • Sepúlveda, F., Rosenberg, M. D., Rowland, J. V., & Simmons, S. F. (2012). Kriging predictions of drill-hole stratigraphy and temperature data from the Wairakei geothermal field, New Zealand: Implications for conceptual modeling. Geothermics, 42, 13–31.

    Article  Google Scholar 

  • Spichak, V., Geiermann, J., Zakharova, O., Calcagno, P., Genter, A., & Schill, E. (2015). Estimating deep temperatures in the Soultz-sous-For e ts geothermal area (France): From magnetotelluric data. Near Surface Geophysics, 13, 397–408.

    Article  Google Scholar 

  • Spichak, V. V., & Zakharova, O. K. (2012). The subsurface temperature assessment by means of an indirect electromagnetic geothermometer. Geophyics, 77(4), WB179–WB190.

  • Spichak, V. V., Zakharova, O. K., & Goidina, A. G. (2013). A new conceptual model of the Icelandic crust in the Hengill geothermal area based on the indirect electromagnetic geothermometry. Journal of Volcanology and Geothermal Research, 257, 99–112.

    Article  Google Scholar 

  • Srivastava, N., Hinton, G., Krizhevsky, A., Sutkever, I., & Salakhutdinov, R. (2014). Dropout: a simple way to prevent neural networks from overfitting. Journal of Machine Learning Research, 15, 1929–1958.

    Google Scholar 

  • Teng, Y., & Koike, K. (2007). Three-dimensional imaging of a geothermal system using temperature and geological models derived from a well-log dataset. Geothermics, 36, 518–538.

    Article  Google Scholar 

  • Tsuchiya, N., & Hirano, N. (2007). Chemical reaction diversity of geofluids revealed by hydrothermal experiments under sub- and supercritical states. Island Arc, 16(1), 6–15. https://doi.org/10.1111/j.1440-1738.2007.00554.x

    Article  Google Scholar 

  • Vogt, C., Klitzsch, N., & Rath, V. (2014). On self-potential data for estimating permeability in enhanced geothermal systems. Geothermics, 51, 201–213.

    Article  Google Scholar 

  • Waff, H. S. (1974). Theoretical consideration of electrical conductivity in a partially molten mantle and implications for geothermometry. Journal of Geophysical Research, 79, 4003–4010.

    Article  Google Scholar 

  • Watanabe, N., Numakura, T., Sakaguchi, K., Saishu, H., Okamoto, A., Ingebritsen, S. E., & Tsuchiya, N. (2017). Potentially exploitable supercritical geothermal resources in the ductile crust. Nature Geoscience, 10(2), 140–144.

    Article  Google Scholar 

  • Yamaya, Y., Uchida, T., Ogawa, Y., & Mogi, T. (2017). Organization of resistivity exploration data for development of deep geothermal systems-reprocessing magnetotelluric data from the Kakkonda geothermal field, northeast Japan. In Proceedings in 39th NZ Geothermal Workshop, Vol. 61.

  • Yasukawa, K., Mogi, T., Widarto, D., & Ehara, S. (2003). Numerical modeling of a hydrothermal system around Waita volcano, Kyushu, Japan, based on resistivity and self-potential survey results. Geothermics, 32, 21–46.

    Article  Google Scholar 

Download references

Acknowledgments

This research was funded by the New Energy and Industrial Technology Development Organization (NEDO), Japan, through the research project “Technology for estimation of deep geothermal structures and drilling bit life using artificial intelligence.” K.I. was also funded partly by the Japan Society for the Promotion of Science (JSPS) KAKENHI (Grant No. 20K15219). The authors also acknowledge the support by the Tohoku Sustainable & Renewable Energy Co. Inc. (TOUSEC).

Author information

Authors and Affiliations

  1. Department of Urban Management, Kyoto University, Nishikyo-ku, Kyoto, Japan

    Kazuya Ishitsuka

  2. Department of Sciences and Informatics, Muroran Institute of Technology, Muroran, Hokkaido, Japan

    Yosuke Kobayashi

  3. Fukishima Renewable Energy Institute, National Institute of Advanced Industrial Science and Technology, Koriyama, Fukushima, Japan

    Norihiro Watanabe, Yusuke Yamaya & Hiroshi Asanuma

  4. Institute of Fluid Science, Tohoku University, Aoba-ku, Sendai, Japan

    Elvar Bjarkason & Anna Suzuki

  5. Volcanic Fluid Research Center, Tokyo Institute of Technology, Meguro-ku, Tokyo, Japan

    Toru Mogi

  6. Geothermal Engineering Co., Ltd, Takizawa, Iwate, Japan

    Tatsuya Kajiwara, Takeshi Sugimoto & Ryoichi Saito

Authors
  1. Kazuya Ishitsuka
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Yosuke Kobayashi
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Norihiro Watanabe
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yusuke Yamaya
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Elvar Bjarkason
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Anna Suzuki
    View author publications

    You can also search for this author in PubMed Google Scholar

  7. Toru Mogi
    View author publications

    You can also search for this author in PubMed Google Scholar

  8. Hiroshi Asanuma
    View author publications

    You can also search for this author in PubMed Google Scholar

  9. Tatsuya Kajiwara
    View author publications

    You can also search for this author in PubMed Google Scholar

  10. Takeshi Sugimoto
    View author publications

    You can also search for this author in PubMed Google Scholar

  11. Ryoichi Saito
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Kazuya Ishitsuka.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Ishitsuka, K., Kobayashi, Y., Watanabe, N. et al. Bayesian and Neural Network Approaches to Estimate Deep Temperature Distribution for Assessing a Supercritical Geothermal System: Evaluation Using a Numerical Model. Nat Resour Res 30, 3289–3314 (2021). https://doi.org/10.1007/s11053-021-09874-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11053-021-09874-w

Keywords

Search

Navigation