[1N4-GS-13] AI application: Machine learning and application (1)

[1N4-GS-13-02] Development of temperature prediction method for supercritical geothermal resources using neural networks

〇Yosuke Kobayashi¹, Kazuya Ishitsuka², Toru Mogi³, Koichi Suzuki⁴, Norihiro Watanabe⁵, Yusuke Yamaya⁵, Kyosuke Okamoto⁵, Hiroshi Asanuma⁵, Tatsuya Kaziwara⁶, Ken Sugimoto⁶, Ryoichi Saito⁶, Koji Nagano¹ (1. Muroran Institute of Technology, 2. Kyoto University, 3. Tokyo Institute of Technology, 4. Hokkaido University, 5. National Institute of Advanced Industrial Science and Technology, 6. Geothermal Engineering Co., Ltd.)

Keywords:supercritical geothermal resources, temperature prediction , neural networks

We propose an subsurface temperature structure prediction model using a neural network with the aim of predicting a distribution of a supercritical geothermal resources. In our proposed model, three-dimensional coordinates, specific resistance by magnetotelluric, D95, gravity anomaly value, and mineral isograds were calculated from measurement data as input features. This model training procedure was applied to the Kakkonda geothermal field, Japan. As a result of evaluation using actual measurement data, the RMSE was shown 39.3 ℃ when optimized input features.