Layer | Fill | Outline |
---|
Map layers
Theme | Visible | Selectable | Appearance | Zoom Range (now: 0) |
---|
Fill | Stroke |
---|---|
Collaborating Authors
Results
An Integrated Application of Cluster Analysis and Artificial Neural Networks for SAGD Recovery Performance Prediction in Heterogeneous Reservoirs
Amirian, Ehsan (University of Alberta) | Leung, Juliana Y. (University of Alberta) | Zanon, Stefan D. (Nexen Energy ULC) | Dzurman, Peter J. (Nexen Energy ULC)
Abstract Evaluation of steam-assisted gravity drainage (SAGD) performance that involves detailed compositional simulations is usually deterministic, cumbersome, expensive (manpower and time consuming), and not quite suitable for practical decision making and forecasting, particularly when dealing with high-dimensional data space consisting of large number of operational and geological parameters. Data-driven modeling techniques, which entail comprehensive data analysis and implementation of machine learning methods for system forecast, provide an attractive alternative. In this paper, artificial neural network (ANN) is employed to predict SAGD production in heterogeneous reservoirs, an important application that is lacking in existing literature. Numerical flow simulations are performed to construct a training data set consists of various attributes describing characteristics associated with reservoir heterogeneities and other relevant operating parameters. Empirical Arps decline parameters are tested successfully for parameterization of cumulative production profile and considered as outputs of the ANN models. Sensitivity studies on network configurations are also investigated. Principal components analysis (PCA) is performed to reduce the dimensionality of the input vector, improve prediction quality, and limit over-fitting. In a case study, reservoirs with distinct heterogeneity distributions are fed to the model. It is shown that robustness and accuracy of the prediction capability are greatly enhanced when cluster analysis are performed to identify internal data structures and groupings prior to ANN modeling. Both deterministic and fuzzy-based clustering techniques are compared, and separate ANN model is constructed for each cluster. The model is then verified using a testing data set (cases that have not been used during the training stage). The proposed approach can be integrated directly into most existing reservoir management routines. In addition, incorporating techniques for dimensionality reduction and clustering with ANN demonstrates the viability of this approach for analyzing large field data set. Given that quantitative ranking of operating areas, robust forecasting, and optimization of heavy oil recovery processes are major challenges faced by the industry, the proposed research highlights the significant potential of applying effective data-driven modeling approaches in analyzing other solvent-additive steam injection projects.
- Europe (1.00)
- Asia (1.00)
- North America > United States > Texas (0.93)
- South America (0.93)
- Geology > Petroleum Play Type > Unconventional Play > Heavy Oil Play (1.00)
- Geology > Rock Type > Sedimentary Rock (0.93)
- South America > Venezuela > North Atlantic Ocean > Eastern Venezuela Basin (0.99)
- South America > Venezuela > Eastern Venezuela Basin > Furrial Field (0.99)
- North America > United States > Texas > Fort Worth Basin > Barnett Shale Formation (0.99)
- North America > United States > Alaska > North Slope Basin > Kuparuk River Field (0.99)
- Information Technology > Artificial Intelligence > Representation & Reasoning > Uncertainty > Fuzzy Logic (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Statistical Learning > Clustering (1.00)
- Information Technology > Artificial Intelligence > Machine Learning > Neural Networks (1.00)
Abstract Particle-size distribution (PSD) is a list of values that defines the relative amount of particles present according to the size in a sample. The PSD of the McMurray Formation sediments characterizes rock granulometry and is a fundamental indicator of sediment's nature. The size distribution of the component solid particles in the McMurray Formation sediments relates to their porosity, volume of water and bitumen contained within the pore space, and to depositional environment, including lithological association, stratigraphy, aerial distribution, and associated physical processes. Particle size distribution is known to be a significant factor for evaluating bitumen recovery from an oil sands mine. This is because presence of fines (evaluated by PSD analysis) affects the hot water separation process, processing plant recovery prediction and provides grade control. Presence of more fines translates into lower recovery from commercial oil sands processing. In this paper we investigate whether the particle size distribution should be also considered a critical parameter for evaluation and estimation of permeability of an oil sands reservoir. We show using the data from the Cenovus Energy's Telephone Lake lease that there is a strong relationship between permeability and particle size distribution data. We also show that the information provided by the PSDs for permeability prediction is more significant than the one inferred from a simple porosity-permeability relationship. Subsequently, we comment on permeability modeling using particle size distribution data and list the techniques available for cleaning and modeling of multivariate PSDs. We document a methodology for accurate modeling of PSDs and provide a workflow for incorporating these data in improved understanding and modeling of permeability and its distribution.
- North America > United States (1.00)
- North America > Canada > Alberta (0.96)
- Europe (0.69)
- Research Report > Experimental Study (0.46)
- Overview (0.46)
- Geology > Sedimentary Geology > Depositional Environment (1.00)
- Geology > Petroleum Play Type > Unconventional Play > Heavy Oil Play (1.00)
- Geology > Geological Subdiscipline (1.00)
- (2 more...)
- North America > United States > New Mexico > Albuquerque Basin (0.99)
- North America > Canada > Alberta > Western Canada Sedimentary Basin > Alberta Basin > Telephone Lake Project (0.99)
- North America > Canada > Alberta > Western Canada Sedimentary Basin > Alberta Basin > Clearwater Formation (0.99)
- (2 more...)