| Title | Data-driven EUR modeling and optimization in the liquid-rich Duvernay Formation, Western Canada Sedimentary Basin, Canada |
| |
| Author | Kong, B ; Chen,
Z |
| Source | Journal of Petroleum Science & Engineering vol. 213, 110352, 2022 p. 1-15, https://doi.org/10.1016/j.petrol.2022.110352 |
| Image |  |
| Year | 2022 |
| Alt Series | Natural Resources Canada, Contribution Series 20210470 |
| Publisher | Elsevier |
| Document | serial |
| Lang. | English |
| Media | paper; digital; on-line |
| File format | pdf; html |
| Province | Alberta |
| NTS | 83F/09; 83F/10; 83F/11; 83F/12; 83F/13; 83F/14; 83F/15; 83F/16; 83K |
| Area | Fox Creek |
| Lat/Long WENS | -118.0000 -116.0000 55.0000 53.5000 |
| Subjects | fossil fuels; Economics and Industry; Science and Technology; Nature and Environment; petroleum resources; hydrocarbon recovery; oil; gas; reservoirs; resource estimation; modelling; Duvernay Formation;
Western Canada Sedimentary Basin; Methodology; machine learning; Artificial intelligence |
| Illustrations | flow charts; models; geoscientific sketch maps; diagrams; tables; bar graphs; plots; time series |
| Program | Geoscience for New Energy Supply (GNES) Shale-hosted petroleum resource assessment |
| Released | 2022 03 09 |
| Abstract | Estimated Ultimate Recovery (EUR) is one of the focuses of the feasibility assessment for oil and gas development projects. EUR is the utmost recoverable oil and gas volume under the current assumption
of technology and economics. Many factors including geology, drilling, completion, operation, and commodity prices influence EUR, which makes the prediction a difficult task. Reservoir numerical simulation and production decline curve analysis (DCA)
are two broadly accepted method to calculate EUR. However, the former requires substantial data and resources, while the latter is lack of causative mechanism to associate the fundamentals to productivity. This study proposes a machine learning (ML)
procedure in EUR modeling, by which EUR is linked to fundamental variables from available data and the variation in EUR can be explained by various factors so that the results can be applied to optimize future projects. In the proposed procedure, the
EUR was estimated using a probabilistic dual flow regime model and Markov Chain Monte Carlo (MCMC) simulation. The resulting EUR in each well was then modeled using a two-level stacked ensemble ML approach, while Shapley value was used to explain
feature sensitivity in the trained model. In the last, the EUR is optimized by adjusting the most sensitive factors in the trained model. The trained ML model achieved high accuracy on EUR prediction, and the Shapley value analysis showed that
completion length, condensate gas ratio and fracturing fluid volume are among the most important features to EUR. The EUR optimization result showed that there is large room for improvement by adjusting the key features. This proposed approach
provides a new perspective to find associations between the fundamental factors and the well EUR which improves the understanding of oil and gas production in unconventional reservoirs. |
| Summary | (Plain Language Summary, not published)
EUR is the utmost recoverable oil and gas volume under the assumption of current technology and economics. Many factors including geologic, drilling,
completion, operation, and commodity prices influence EUR, making precise prediction difficult. Reservoir computer simulation and production decline curve analysis (DCA) are two widely accepted methods to calculate EUR. However, the former requires
substantial data and resources, while the latter is lack of causative mechanism to associate the fundamentals to productivity. This study proposes a machine learning procedure in EUR modeling, by which EUR is linked to fundamental variables from
available data and the variation in EUR can be explained by various factors so that the results can be used to guide future completion and production practice to optimize resource extraction and reduce environmental footprints. In the proposed
procedure, the EUR was estimated using a probabilistic dual flow regime model and Markov Chain Monte Carlo (MCMC) simulation. The resulting EUR in each well was then modeled using a two-level stacked ensemble ML approach, while Shapley value from the
game theory was used to explain feature sensitivity in the trained model. In the last, the EUR is optimized by adjusting the most sensitive factors in the trained model. This proposed approach provides a new perspective to find associations between
the fundamental factors and the well EUR, providing practical guidance for improving resource recovery and reducing associated environmental impacts. |
| GEOSCAN ID | 329327 |
|
|