Carbon dioxide capture and sequestration has attracted widespread interest worldwide due to greenhouse effect. Geological uncertainties affect final decisions of the injection work. Optimizing injection work under geological parameters can maximize the carbon dioxide injection efficiency and minimize the difference between the carbon dioxide storage target and actual injection volume. This work introduces an optimization workflow for decisions. It is composed of three steps. At first, generating samples as the initial data sets by using Latin Hypercube Sampling method. Secondly, a data-driven model is deployed to simulate the fluid movement in the reservoir using the samples generated in step 1. The surrogate model is optimized by tuning hyper parameters in neural networks and applying K-fold validation, which can mitigate the limitations of high-fidelity simulations. After optimization, the surrogate model is validated using full reservoir simulation. At last, with the help of genetic algorithm, both the critical pressure area and CO2 plume area reduce largely, and CO2 injection volume increases by 115*103 m3. This optimization can largely enhance CO2 sequestration efficiency. It introduces an efficient workflow to provide a reference to the decision-making process of CO2 injection location.

Shunzheng Jia. An Integrated Machining Learning-Based Workflow for CO2 Sequestration Optimization under Geological Uncertainty. International Journal of Engineering Technology and Construction (2023), Vol. 4, Issue 2: 28-37. https://doi.org/10.38007/IJETC.2023.040204.

[1] Korelskiy, Evgeny, et al. "Geomechanical modelling application to support reservoir selection for carbon dioxide utilization and storage." SPE Russian Petroleum Technology Conference. SPE, 2021.

[2] Coffin, Richard, et al. "The Importance of Secondary Traps and Sinks in Offshore CO2 Sequestration." Offshore Technology Conference. OTC, 2023.

[3] Hu, Ke, Xinglan Bai, and Zhaode Zhang. "Prediction model of pipeline scour depth based on BP neural network optimized by genetic algorithm." ISOPE International Ocean and Polar Engineering Conference. ISOPE, 2020.

[4] Saptharishi, Priyadharshini, and Manisha Makwana. "Technical and Geological review of Carbon dioxide Geo Sequestration along with analysis and study of various Monitoring Techniques." International Petroleum Technology Conference. IPTC, 2011.

[5] Park, Se-Hun, Suk-Jae Kwon, and Wee-Yeong Oh. "Economic evaluation of CO2 ocean sequestration in Korea." ISOPE Ocean Mining and Gas Hydrates Symposium. ISOPE, 2007.

[6] Xuan, Zhao, and Shunli He. "Potential and early opportunity-analysis on CO2 geo-sequestration in China." SPE EUROPEC/EAGE Annual Conference and Exhibition. OnePetro, 2010.

[7] Gumina, Jamie M., Clifford Whitcomb, and Alejandro S. Hernandez. "Latin Hypercube Sampling Strategies Applied to Set-Based Design." SNAME Maritime Convention. SNAME, 2019.

[8] Carpenter, Chris. "Numerical Simulation of Gas Lift Optimization Uses Genetic Algorithm." Journal of Petroleum Technology 74.03 (2022): 65-67.

[9] Lie, Knut-Andreas. An introduction to reservoir simulation using MATLAB/GNU Octave: User guide for the MATLAB Reservoir Simulation Toolbox (MRST). Cambridge University Press, 2019.

[10] Chollet, Francois. Deep learning with Python. Simon and Schuster, 2021.

[11] Nicot, Jean-Philippe, et al. "Pressure perturbations from geologic carbon sequestration: Area-of-review boundaries and borehole leakage driving forces." Energy procedia 1.1 (2009): 47-54.