TY - JOUR

T1 - Bayesian and Neural Network Approaches to Estimate Deep Temperature Distribution for Assessing a Supercritical Geothermal System

T2 - Evaluation Using a Numerical Model

AU - Ishitsuka, Kazuya

AU - Kobayashi, Yosuke

AU - Watanabe, Norihiro

AU - Yamaya, Yusuke

AU - Bjarkason, Elvar

AU - Suzuki, Anna

AU - Mogi, Toru

AU - Asanuma, Hiroshi

AU - Kajiwara, Tatsuya

AU - Sugimoto, Takeshi

AU - Saito, Ryoichi

N1 - Funding Information:
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).
Publisher Copyright:
© 2021, International Association for Mathematical Geosciences.

PY - 2021/10

Y1 - 2021/10

N2 - 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.

AB - 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.

KW - Bayesian estimation

KW - Data-driven discovery

KW - Kakkonda geothermal field

KW - Neural networks

KW - Supercritical geothermal system

KW - Temperature estimation

UR - http://www.scopus.com/inward/record.url?scp=85108330334&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85108330334&partnerID=8YFLogxK

U2 - 10.1007/s11053-021-09874-w

DO - 10.1007/s11053-021-09874-w

M3 - Article

AN - SCOPUS:85108330334

VL - 30

SP - 3289

EP - 3314

JO - Nonrenewable Resources

JF - Nonrenewable Resources

SN - 1520-7439

IS - 5

ER -