A Machine Learning Approach to Optimize Shale Gas Supply Chain Networks
- H. I. Asala (Louisiana State University) | J. Chebeir (Louisiana State University) | W. Zhu (Louisiana State University) | I. Gupta (Louisiana State University) | A. Dahi Taleghani (Louisiana State University) | J. Romagnoli (Louisiana State University)
- Document ID
- Society of Petroleum Engineers
- SPE Annual Technical Conference and Exhibition, 9-11 October, San Antonio, Texas, USA
- Publication Date
- Document Type
- Conference Paper
- 2017. Society of Petroleum Engineers
- 5.8.2 Shale Gas, 6.1.5 Human Resources, Competence and Training, 5.5 Reservoir Simulation, 5.5.8 History Matching, 7 Management and Information, 3.2.4 Produced Water Management, 7.6.7 Neural Networks, 5.8 Unconventional and Complex Reservoirs, 3 Production and Well Operations, 2.4 Hydraulic Fracturing, 4.6 Natural Gas, 1.6 Drilling Operations, 2 Well completion, 7.6 Information Management and Systems, 3.2 Well Operations and Optimization, 5 Reservoir Desciption & Dynamics, 3 Production and Well Operations, 6.1 HSSE & Social Responsibility Management, 5.8.4 Shale Oil, 7.6.6 Artificial Intelligence, 6 Health, Safety, Security, Environment and Social Responsibility
- Recurrent Neural Network, Compositional Modeling, Re-fracturing and Candidate Selection, Mixed Integer Non-Linear Programming, Forecasted Natural Gas Demand
- 7 in the last 30 days
- 411 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 8.50|
|SPE Non-Member Price:||USD 25.00|
The unsteady recovery of oil and gas prices in early 2017 led to an increase in drilling and hydraulic fracturing operations in North America liquid-rich shale plays. The increasing number of producing wells, in addition to re-fractured wells, impose the need for optimizing field development strategies and shale gas supply chain networks that maximize profitability. Moreover, operators must account for undulating natural gas demands both locally and externally in a persistently low oil price environment. In this paper, we adopt supervised machine learning approaches to forecast local natural gas demand as well as guide well re-frac candidature. Both serve as critical inputs for maximizing the net present value of any shale gas field development project. An optimized water management structure is also incorporated in the proposed framework to account for associated produced-water recycling.
Considering a shale gas network in the Marcellus play, supply chain optimization was achieved using a mixed integer non-linear programming formulation. The Strategic Planning model relies on at least 4 major efforts including reservoir simulation, which in turn relies on output from a feed forward Neural Network (NN) algorithm. The trained NN algorithm was deemed suitable for recommending re-frac candidates, necessary decision variables for multiphase reservoir simulation. Finally, NPV optimization relied on a four-layer Long Short-Term Memory (LSTM) recurrent neural network, developed for forecasting local shale gas demand. Both neural network algorithms were scripted using python.
17 non-redundant parameters were mined for 250 wells in the case study. The t-Distributed Stochastic Neighbor Embedding technique was used to visualize related low dimensional manifolds within the high-dimensional data set, and a NN algorithm was used to obtain probabilities of misclassification. The well-pads in the case study superstructure are modeled using compositional reservoir simulation. Each reservoir model is tuned by history matching production and pressure data for designated producing wells. Alternative field development strategies (including re-fracturing) are then simulated for a 10-year planning horizon to generate gas and water rate decline profiles. Using the LSTM developed, local gas demand is forecasted using data sets created from multivariate time-dependent local and global variables affecting shale gas demand. The LSTM algorithm is derived by convolving some features from the raw data set, with fined-tuned weights, with the objective of minimizing a pre-defined demand error function. The results obtained show that application of this integrated approach can give operators a calculated advantage, preventing erroneous feedback of project profitability but allowing early time decision-making that maximizes shale asset NPV.
|File Size||3 MB||Number of Pages||29|
Alireza A. and Sudhendu K., 2016. A Geomechanical Study of Refracturing Based on Microseismic Observations - Case Study of Haynesville and EagleFord Wells, UrTEC, San Antonio, TX, 1-3 Aug. 2016. DOI:10.15530/urtec-2016-2435484
Asala, H. I.,Ahmadi M.,Dahi-Talehgani A., 2016. Why Refracturing Works and Under What Conditions, Paper SPE-181516-MS was prepared for presentation at the SPE Annual Technical Conference and Exhibition held in Dubai, U.A.E, 26-28 September, 2016. DOI: 10.2118/181516-MS
Asala, H.I.,Chebeir, J. C.,Dahi-Taleghani, A., Romagnoli, J. A., 2017. The Application of Compositional Modelling to the Integration of Realistic Re-Stimulation Strategies and Unconventional Shale Gas Supply Chain Optimization. Chemical Engineering Transactions, CET, 2 (57): 979–984. DOI: 10.3303/CET1757164
Barree, R. D.,Miskimins, J. L.,Svatek, K. J., 2017. Reservoir and Completion Considerations for the Refracturing of Horizontal Wells, Paper SPE-184837-MS was prepared for presentation at the SPE Hydraulic Fracturing Technology Conference and Exhibition held in The Woodlands, Texas, 24-26 January, 2017. DOI:10.2118/184837-MS.
DrillingInfo - DI Engineering Explorer, 2016, http://info.drillinginfo.com (downloaded January 2017)
French, S., Rodgerson, J., Feik, C., 2014. Re-fracturing Horizontal Shale Wells: Case History of a Woodford Shale Pilot Project, Paper SPE-168607-MS was prepared for presentation at the SPE Hydraulic Fracturing Technology Conference and Exhibition held in The Woodlands, Texas, 4-6 February, 2014. DOI:10.2118/168607-MS.
Fulford, D., Bowie, B., Berry, M., and Bowen, B., 2015. Machine Learning as a Reliable Technology for Evaluating Time-Rate Performance of Unconventional Wells. Paper SPE-174784-MS was prepared for presentation at the SPE Annual Technical Conference and Exhibition held in Houston, Texas, USA, 28-30 September, 2015. DOI: 10.2118/174784-MS.
King, G. and Valencia, R., 2016. Well Integrity for Fracturing and Re-Fracturing: What is Needed and Why? Paper SPE-179120-MS was presented at the SPE Hydraulic Fracturing Technology Conference, The Woodlands, Texas, USA, 9-11 February. DOI:10.2118/179120-MS.
Lindsay, G. J.,White, D. J.,Miller, G.A.,Baihly, J.D., & Sinosic, B., 2016. Understanding the Applicability and Economic Viability of Refracturing Horizontal Well in Unconventional Plays. Paper SPE-179113 was presented at the SPE Hydraulic Fracturing Technology Conference, The Woodlands, Texas, USA, 9-11 February. DOI:10.2118/179113-MS.
Marongiu-Porcu, M., Lee, D., Shan, D.. 2015. Advanced Modelling of InterWell Fracturing Interference: An EagleFord Shale Oil Study, Paper SPE-174902-MS presented at the SPE Annual Technical Conference and Exhibition, Houston, Texas, USA, 28-30 September. http://dx.doi.org/10.2118/174902-MS.
Mohaghegh, S., Gaskari, R., and Maysami, M., 2017. Shale Analytics: Making Production and Operational Decisions Based on Facts: A Case Study in Marcellus Shale. Paper SPE-184822-MS was presented at the SPE Hydraulic Fracturing Technology Conference, The Woodlands, Texas, USA, 24-26 January. DOI:10.2118/184822-MS
Olah, C. (2015, August 17). Understanding LSTM Networks [Blog post]. Retrieved from http://colah.github.io/posts/2015-08-Understanding-LSTMs/
Xu, B., Li, Y., Yuan, T., Qin, G., Yin, C., Xiao, J., 2016. Numerical Modeling and Candidate Selection of Re-Fracturing with Micro-Seismic Data in Shale Gas Productions, Paper SPE 181874-MS was prepared for presenatation at the SPE Asia Pacific Huydraulic Fracturing Conference held in Beijing, China, 24-26 August 2016. DOI:10.2118/181874-MS.
Yang, C., Xue, X., Huang, J., Datta-Gupta, A., and King, M., 2016. Rapid Refracturing Candidate Selection in Shale Reservoirs Using Drainage Volume and Instantaneous Recovery Ratio. Paper SPE 2459368 presented at SPE Unconventional Resources Conference – San Antonio, Texas, USA 1–3 August. DOI: 10.15530-urtec-2016-2459368.