Using Machine Learning to Predict Production at a Peace River Thermal EOR Site
- Eileen Martin (Stanford University) | Peter Wills (Shell International E&P, Inc.) | Detlef Hohl (Shell International E&P, Inc.) | Jorge L. Lopez (Shell International E&P, Inc.)
- Document ID
- Society of Petroleum Engineers
- SPE Reservoir Simulation Conference, 20-22 February, Montgomery, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2017. Society of Petroleum Engineers
- 5 Reservoir Desciption & Dynamics, 5.6.9 Production Forecasting, 5.4.6 Thermal Methods, 5.6 Formation Evaluation & Management, 7.6.6 Artificial Intelligence, 5.4 Improved and Enhanced Recovery
- production prediction, thermal enhanced oil recovery, oil sands, reservoir management, machine learning
- 9 in the last 30 days
- 436 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
When many daily measurements of a thermal EOR field are taken throughout production, it is not cost effective to manually interpret trends to update reservoir models, so we developed an automated data-driven approach for production prediction using machine learning techniques. This is a two-step scheme that first predicts auxilary field measurements from directly-controlled field settings, then uses these predicted field measurements to predict production. The full two-step prediction process needs further refinement, but the second step alone shows promise for aiding in automated interpretation of data. Time shifts from daily seismic surveys improved production predictions.
|File Size||1 MB||Number of Pages||8|
Barker, T., and Xue, Y. 2015. Continuous seismic reservoir monitoring at Peace River: quantification of reservoir changes. 85th Annual International Meeting, SEG, Expanded Abstracts, http://dx.doi.org/10.1190/segam2015-5868353.1.
Cao, Q., Banerjee, R., Gupta, S.. 2016. Data Driven Production Forecasting Using Machine Learning, presented at the SPE Argentina Exploration and Production of Unconventional Resources Symposium, Buenos Aires, Argenitna, 1-3 June. SPE-180984-MS. http://dx.doi.org/10.2118/180984-MS.
La Follett, J.R., Wills, P., Lopez, J.L.. 2015. Continuous seismic reservoir monitoring at Peace River: Initial results and interpretation. 85th Annual International Meeting, SEG, Expanded Abstracts, http://dx.doi.org/10.1190/segam2015-5883275.1.
Lopez, J.L., Wills, P., La Follett, J.R.. 2015. Real-Time Seismic Surveillance of Thermal EOR at Peace River, presented at the SPE Canada Heavy Oil Technical Conference, Calgary, Canada, 9-11 June. SPE-174459-MS. http://dx.doi.org/10.2118/174459-MS.
Przybysz-Jarnut, J.K., Wills, P.B., Araujo, M.G.. 2016. Combining Frequent 4D Seismic and Mechanistic Reservoir Modeling to Improve the Effectiveness of Steam Injection Operations, presented at the SPE Annual Technical Conference and Exhibition, Dubai, UAE, 26-28 September. SPE-181421-MS. http://dx.doi.org/10.2118/181421-MS.
Suo, X., Tibshirani, R. 2014. An ordered lasso and sparse time-lagged regression. arXiv preprint: 1405.6447. http://arxiv.org/abs/1405.6447.
Subrahmanya, N., Xu, P., El-Bakry, A.. 2014. Advanced Machine Learning Methods for Production Data Pattern Recognition, presented at the SPE Intelligent Energy Conference and Exhibition, Utrecht, The Netherlands, 1-3 April. SPE-167839-MS. http://dx.doi.org/10.2118/167839-MS.
Tolosi, L., and Lengauer, T. 2011, Classification with correlated features: unreliability of feature ranking and solutions. Bioinformatics 27(14), 1986&-&-1994. http://dx.doi.org/10.1093/bioinformatics/btr300.
Tibshirani, R. 1996. Regression shrinkage and selection via the Lasso. Journal of the Royal Statistical Society B 58(1), 267&-&-288. http://dx.doi.org/10.1111/j.1467-9868.2011.00771.x.