THM analysis for an in situ experiment using FLAC3D-TOUGH2 and an artificial neural network

The evaluation of Thermo-Hydro-Mechanical (THM) coupling behavior is important for the development of underground space for various purposes. For a high-level radioactive waste repository excavated in a deep underground rock mass, the accurate prediction of the complex THM behavior is essential for the long-term safety and stability assessment. In order to develop reliable THM analysis techniques effectively, an international cooperation project, Development of Coupled models and their Validation against Experiments (DECOVALEX), was carried out. In DECOVALEX-2015 Task B2, the in situ THM experiment that was conducted at Horonobe Underground Research Laboratory(URL) by Japan Atomic Energy Agency (JAEA), was modeled by the research teams from the participating countries. In this study, a THM coupling technique that combined TOUGH2 and FLAC3D was developed and applied to the THM analysis for the in situ experiment, in which rock, buffer, backfill, sand, and heater were installed. With the assistance of an artificial neural network, the boundary conditions for the experiment could be adequately implemented in the modeling. The thermal, hydraulic, and mechanical results from the modeling were compared with the measurements from the in situ THM experiment. The predicted buffer temperature from the THM modelling was about 10oC higher than measurement near by the overpack. At the other locations far from the overpack, modelling predicted slightly lower temperature than measurement. Even though the magnitude of pressure from the modeling was different from the measurements, the general trends of the variation with time were found to be similar.