Machine Learning Applied to Optimize Duvernay Well Performance
- Braden Bowie (Apache Corporation)
- Document ID
- Society of Petroleum Engineers
- SPE Canada Unconventional Resources Conference, 13-14 March, Calgary, Alberta, Canada
- Publication Date
- Document Type
- Conference Paper
- 2018. Society of Petroleum Engineers
- 7.6 Information Management and Systems, 7 Management and Information, 7.6.6 Artificial Intelligence, 2 Well completion, 4.6 Natural Gas, 7.6.7 Neural Networks, 2.4 Hydraulic Fracturing, 6 Health, Safety, Security, Environment and Social Responsibility, 4.6 Natural Gas, 6.1 HSSE & Social Responsibility Management, 6.1.5 Human Resources, Competence and Training, 2.5.2 Fracturing Materials (Fluids, Proppant)
- Duvernay, Machine Learning, Neural Network, Completion Optimization
- 28 in the last 30 days
- 595 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
This paper presents the use of machine learning via a multiple linear regression and a neural network to solve the complex problem of optimizing completions and well designs in the Duvernay shale. Solutions were revealed that could save over a million dollars per well, along with the potential for more than 50% improvement in well performance. This was accomplished through a workflow that rigorously analyzed the relationships between a multitude of well completion variables, generated predictions of future results, and performed optimizations for ideal outcomes. Most importantly, this workflow is not Duvernay specific, and can easily be applied to other basins and formations.
This is a fundamental problem in many industries, in that a responding variable is controlled not just by one predictor variable, but by a number of predictor variables. Inferring the relationship between the responding variable and the predictor variables is then of key importance. Interactions between predictor variables, as well as noise in the data, complicate matters further. This problem can be solved with a multiple linear regression or a neural network, both of which utilizes all predictor variables together. However, care must be taken to obtain a model that is truly predictive and not a result of overfitting the data.
The workflow was applied to 262 Duvernay wells, ranging from dry gas to volatile oil. No wells were excluded for operational or geological reasons, a strength of this methodology. By not excluding any wells, the model could maximize learnings and establish statistical reasons for the variances in well performance observed. The final model achieved very high predictive power, correctly predicting 78% of the variance in well performance on 52 wells the model hadn't been trained on. Conclusions were quite significant, including:
Indicating virtually no benefit from more expensive fracturing procedures, such as using ceramic or resin coasted proppant, or having hybrid fluid systems, offering savings of over a million dollars per well in the Duvernay.
No benefit from placing wells on an azimuth (parallel to the minimum horizontal stress) vs. a North-South orientation (~45° off azimuth). This allows potentially large savings on a land ownership system not aligned to this direction, by allowing simpler pad design in achieving the same aerial coverage of reservoir depletion.
Confirming total fracture tonnage as a key driver of well performance.
Suggesting fracture pump rate is associated with better well performance and should be investigated further.
These conclusions would have been very difficult to derive without expensive strategic testing on numerous wells with rigorous control of the completions and geological inputs. When compared to recent well performance of six operators, the neural network predicted substantial ability to improve well performance by varying parameters under operator control. Potential improvement ranged from 19% to 97%, showing large potential improvement for all operators.
|File Size||3 MB||Number of Pages||24|
Ani, M., Oluyemi, G., Petrovski, A., Rezaei-Gomari, S., 2016. Reservoir Uncertainty Analysis: The Trends from Probability to Algorithms and Machine Learning, Paper SPE-181049-MS Presented at SPE Intelligent Energy International Conference and Exhibition in Aberdeen, United Kingdom, 6-8 September. doi:10.2118/181049-MS
Cunningham, C.F., Cooley, L., Wozniak, G., Pancake, J., 2012. Using Multiple Linear Regression to Model EUR's of Horizontal Marcellus Shale Wells, Paper SPE-161343 Presented at SPE Eastern Regional Meeting in Lexington, Kentucky, USA, 3-5 October. doi:10.2118/161343-MS
Fulford, D.S., Bowie, B., Berry, M.E., Bowen, B., Turk, D.W., 2015. Machine Learning as a Reliable Technology for Evaluating Time-Rate Performance of Unconventional Wells, Paper SPE-174784-MS Presented at SPE Annual Technical Conference and Exhibition in Houston, Texas, USA, 28-30 September. doi:10.2118/174784-MS
Shelley, R.F., Grieser, W.V. 1999. Artifical Neural Netowrk Enhanced Completions Improve Well Economics, Paper SPE 52959 Presented at SPE Hydrocarbon Economics and Evaluation Symposium in Dallas, Texas, USA, 21-23 March. doi:10.2118/52959-MS
Wang, S., Chen, S., 2016. A Comprehensive Evaluation of Well Completion and Production Performance in Bakken Shale Using Data-Driven Approaches, Paper SPE-181803-MS Presented at SPE Asia Pacific Hydraulic Fracturing Conference in Beijing, China, 24-26 August. doi:10.2118/181803-MS
Wust, R.A.J, Cui, A., Nassichuk, B.R., Bustin, M., 2014. Rock Characteristics of Oil-, Condensate- and Dry Gas-Producing Wells of the Unconventional Devonian Duvernay Formation, Canada, Paper IPTC-18081-MS Presented at International Petroleum Technology Conference, Kuala Lumpur, Malaysia, 10-12 December. doi:10.2523/IPTC-18081-MS