- 206 views
- 228 downloads
Application of Data-Driven Techniques to SAGD and Solvent-Aided Methods
-
- Author / Creator
- Hunyinbo, Seyide, O
-
The warm vaporized solvent injection process has been proposed as a more environmentally friendly alternative to steam-based technologies for bitumen recovery. The process typically involves injecting heated solvent vapor into a horizontal injector; the solvent condenses and dissolves into bitumen, while the diluted oleic phase would flow towards a horizontal producer. An optimization process is important because of its potential reduction of solvent loss to the reservoir and energy requirements while maximizing bitumen recovery. Hence, this research proposes a workflow for optimizing the multiple conflicting performance objectives associated with the warm vaporized solvent injection process. Specific considerations phase behavior constraints, multiple realizations of reservoir heterogeneity, and computational efficiency are considered. It is expected that this workflow can be readily integrated into the design and decision-making processes in reservoir management, especially where multiple geostatistical realizations are involved.
Apart from performing automated optimization and quantification of geological uncertainties and requiring lower computational effort compared to reservoir simulation, data-driven models offer better accuracy than semi-analytical or proxy models based on Butler’s equation. Hence, this thesis also presents another workflow for real-time forecasting, uncertainty assessment of SAGD profiles, and optimization of steam allocation using a real SAGD dataset which includes operational data, geological, and well design parameters. The workflow includes the development of a predictive model using the random forest algorithm, and clustering, Bayesian updating, Monte Carlo sampling, and genetic algorithm for the real-time prediction of SAGD injection and production data. This workflow can update predictions in real-time, perform uncertainty quantification of the forecasts, and optimize steam allocation, making it a practical tool for development planning and field-wide optimization. -
- Graduation date
- Fall 2021
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- This thesis is made available by the University of Alberta Libraries with permission of the copyright owner solely for non-commercial purposes. This thesis, or any portion thereof, may not otherwise be copied or reproduced without the written consent of the copyright owner, except to the extent permitted by Canadian copyright law.