Multi-physical and Data-driven Modelling for Subsurface Energy Geotechnics

The long-term goal underlying the proposed Discovery program is to address the issues around geological uncertainty and computational inefficiency in multi-physical and data-driven decision making in energy geotechnics. The application areas include extraction of energy from hydrocarbons and geothermal sources, as well as storage of CO2 and hydrogen. This long-term goal will be achieved by developing a cloud-based modelling platform that integrates smart mechanical earth modelling, upscaling, multi-scale coupled THMC simulation, and data-driven decision making for subsurface energy developments.

For the first 5 years of my Discovery program, I will lay the foundation of the proposed cloud-based modelling platform and focus on the following three short-term objectives:

(1)   establishing a smart, dynamic 3D mechanical earth model (MEM) that can automatically update changes in pore pressure and in-situ stress with new feeds of geological data;

(2)   developing a coupled THMC upscaling technique; and

(3)   developing multi-fidelity and multi-temporal proxy models based on coupled THMC simulations of CO2 storage for optimization and uncertainty quantification.

Publications:

1. Qiao, S., BenSaleh, W., & Zhang, B. (2025, March). Coupled Flow-Geomechanics Surrogate Model with Flexible Boundary Conditions for Geological CO2 Storage Using Fourier Neural Operator Based Gated Recurrent Network. In SPE Reservoir Simulation Conference (pp. 223871-MS).

2. Ou, X., Qiao, S., & Zhang, B. (2024, November). Smart Coupled Flow-Geomechanical Upscaling Technique for Oil Sands. Smart Coupled Flow-Geomechanical Upscaling Technique for Oil Sands. In ARMA/DGS/SEG International Geomechanics Symposium (pp. ARMA-IGS).

3. Yin, X. H., & Zhang, B. (2024, June). Investigation of failure mode and permeability evolution of Inclined Heterolithic Strata using coupled Discrete Element Method-Computational Fluid Dynamics model. In ARMA US Rock Mechanics/Geomechanics Symposium (p. D021S004R003).

4. Ma, Z., Ou, X., & Zhang, B. (2024). Development of a convolutional neural network based geomechanical upscaling technique for heterogeneous geological reservoir. Journal of Rock Mechanics and Geotechnical Engineering, 16(6), 2111-2125.

5. Zhang, B., Deisman, N., Chalaturnyk, R., & Boisvert, J. (2024). Numerical upscaling of anisotropic failure criteria in heterogeneous reservoirs. Engineering Geology, 331, 107455.

6. Zhang, B., Chalaturnyk, R., & Boisvert, J. (2023). Sequentially coupled thermal-hydraulic-mechanical simulation for geomechanical assessments of caprock integrity in SAGD. Canadian Geotechnical Journal, 61(6), 1242-1265.

7. Zhang, B., Ma, Z., Zheng, D., Chalaturnyk, R. J., & Boisvert, J. (2023). Upscaling shear strength of heterogeneous oil sands with interbedded shales using artificial neural network. SPE Journal, 28(02), 737-753.

8. Zhang, B., Chalaturnyk, R., & Boisvert, J. (2021). A numerical characterization workflow for assessing the strength and failure modes of heterogeneous oil sands. Canadian Geotechnical Journal, 58(6), 763-781.

9. Zhang, B., Deisman, N., Khajeh, M., Chalaturnyk, R., & Boisvert, J. (2020). Numerical local upscaling of elastic geomechanical properties for heterogeneous continua. Petroleum Geoscience, 26(3), 400-416.