Production Analysis and Forecasting for Unconventional Reservoirs Using Laplacian Echo-State Networks
- Yuewei Pan (Texas A&M University) | Peng Zhou (Texas A&M University) | Lichi Deng (Texas A&M University) | John Lee (Texas A&M University)
- Document ID
- Society of Petroleum Engineers
- SPE Western Regional Meeting, 23-26 April, San Jose, California, USA
- Publication Date
- Document Type
- Conference Paper
- 2019. Society of Petroleum Engineers
- Production Forecasting, Deconvolution, Production Analysis, Laplacian Echo-State Networks, Data Analytics
- 3 in the last 30 days
- 166 since 2007
- Show more detail
- View rights & permissions
|SPE Member Price:||USD 5.00|
|SPE Non-Member Price:||USD 28.00|
Production data analysis for low permeability shale reservoirs is crucial in characterizing flow regimes and reservoir properties, and the forecasting of production is essential for portfolio and reservoir management. However, traditional methods have failed due to incorrect physics or complicated convolution from the well control history. In this research, we provide a physics-assisted analytics workflow using Laplacian Eigenmaps Coupled Echo-State Network (LEESN) to facilitate and accelerate the analysis of noisy historical production data.
Pressure-rate deconvolution is an ill-posed, complex time-series problem when using the traditional Echo-State Network when the number of training sets is less than the number of neurons. To solve this problem, we apply LEESN to first deconvolve noisy variable-pressure variable-rate histories into smooth constant-pressure rate responses. The physics-based training features and training algorithm provide additional benefits in addition to the analytic approach by honoring transient flow physics. After training, constant-pressure rate responses can be predicted and used for reservoir characterization, as well as production and EUR forecasting through long-term rate predictions to the economic limit.
The proposed workflow was first applied to a synthetic case where the production data were obtained through simulation. The short-term flow rate history was obtained by specifying highly variable controlling pressures. We also added artificial white Gaussian noise to approximate measured signals collected in the field and input this information into LEESN for deconvolution. The constant-pressure rate response was generated after training to determine flow regimes and properties such as permeability using a traditional transient testing specialized plot. All outcomes from the analytics approach were validated by comparison to the input data from the synthetic simulation model. Advantages of the analytics approach were maintained with moderate variation of noisy pressure-rate signals. For production forecasting, both the trained analytics model and simulator were used to predict for an extended time period, and the results indicated good agreement between the response predictions. We performed further sensitivity analysis on important parameters such as the training scale as well as with or without noise in training data. The comparison between the model predictions and simulation data showed significantly increased accuracy in reserves booking and production estimates. Results were further validated from field case studies with actual production data using hindcasting.
This study shows that the LEESN approach is a powerful alternative to interpret pressure-rate-time information from production data. Deconvolved pressure-rate data greatly enhances traditional rate-transient analysis used to characterize reservoirs and enables engineers to predict future production even with noisy, highly-variable production histories. The robustness of the proposed analytics methodology is strengthened by coupling the training features with transient flow physics, and provides a unique approach for production analysis and forecasting for unconventional reservoirs.
|File Size||3 MB||Number of Pages||28|
Antonelo, E.,Camponogara, E., and Foss, B. 2017. Echo State Networks for Data-Driven Downhole Pressure Estimation in Gas-Lift Oil Wells. Neural Networks, 106–117. doi:10.1016/j.neunet.2016.09.009.
Arps, J. J. 1945, Analysis of Decline Curves, Transactions of the AIME, 160, 228. SPE-945228-G, doi:10.2118/945228-G.
Belkin, M. and Niyogi, P. 2003. Laplacian Eigenmaps for Dimensionality Reduction and Data Representation. Neural Computation., 15, 1373–1396. doi: 10.1162/089976603321780317.
Dambre, J.,Verstraeten, D.,Schrauwen, B., and Massar, S. 2012. Information processing capacity of dynamical systems. Scientific Reports., 2, 512. doi:10.1038/srep00514.
Deng, L.,Davani, E.,Darabi, H.,. 2018. Rapid and Comprehensive Artificial Lift Systems Performance Analysis Through Data Analytics, Diagnostics and Solution Evaluation. Paper presented at the SPE Middle East Artificial Lift Conference and Exhibition, Manama, Bahrain, 28-29 November. SPE-192460-MS. Society of Petroleum Engineers. doi: 10.2118/192460-MS
Deng, L. and King, M.J. 2015. Capillary Corrections to Buckley-Leverett Flow. Paper presented at the SPE Annual Technical Conference and Exhibition, Houston, Texas, 28-30 September. SPE-175150-MS. Society of Petroleum Engineers. doi: 10.2118/175150-MS
Deng, L. and King, M.J. 2018. Theoretical Investigation of Water Blocking in Unconventional Reservoirs Due to Spontaneous Imbibition and Water Adsorption. Paper presented at the Unconventional Resources Technology Conference, Houston, Texas, 23-25 July. URTEC-2875353-MS. doi: 10.15530/URTEC-2018-2875353.
Deng, L.,Olalotiti-Lawal, F.,Davani, E.,. 2019. Hypervolume-Based Multiobjective Optimization for Gas Lift Systems. Paper presented at the SPE Oklahoma City Oil and Gas Symposium, Oklahome City, Oklahoma, 9-10 April. SPE-195208-MS. Society of Petroleum Engineers. doi: 10.2118/195208-MS
Han, M. and Xu, M. 2018. Laplacian Echo State Network for Multivariate Time Series Prediction. IEEE Transactions on Neural Networks and Learning Systems., 29, 238–244. doi:10.1109/TNNLS.2016.2574963.
Hermans, M. and Schrauwen, B. 2012. Recurrent Kernel Machines: Computing with In-finite Echo State Networks. Neural Computation., 24, 104–33. doi:10.1162/NECO_a_00200.
Jaeger, H. and Haas, H. 2004: Harnessing nonlinearity: Prediction chaotic systems and saving energy in wireless communication. Science, 304, 78–80. doi:10.1126/science.1091277.
Jaeger, H.,Lukoševicius, M.,Popovici, D., and Siewert, U. 2007. Optimization and applications of echo state networks with leaky- integrator neurons. Neural Networks. 20, 335–252. doi:10.1016/j.neunet.2007.04.016
Kuchuk, F.,Hollaender, F.,Gok, I., and Onur, M. 2005. Decline Curves from Deconvolution of Pressure and Flow-Rate Measurements for Production Optimization and Prediction. Proceedings of SPE Annual Technical Conference and Exhibition, 9-12 October, Dallas, Texas, USA. SPE-96002-MS, doi:10.2118/96002-MS.
Levitan, M. 2003. Practical Application of Pressure-Rate Deconvolution to Analysis of Real Well Tests. Proceedings of SPE Annual Technical Conference and Exhibition, 5-8 October, Denver, Colorado, USA. SPE-84290-MS, doi:10.2118/84290-MS.
Liu, G. and Ehlig-Economides, C. 2018. Practical Considerations for Diagnostic Fracture Injection Test (DFIT) Analysis. Journal of Petroleum Science and Engineering 171: 1133–1140. doi: 10.1016/j.petrol.2018.08.035
Liu, Y., and Horne, R. 2013. Interpreting Pressure and Flow-Rate Data From Permanent Downhole Gauges by Use of Data-Mining Approaches. SPE Journal, 18, 69–82. SPE-147298-PA. doi:10.2118/147298-PA.
Maass, W.,Natschläger, T. and Markram, H. 2002. Real-Time Computing Without Stable States: A New Framework for Neural Computation Based on Perturbations. Neural Computation. 14, 2531–2560. doi:10.1162/089976602760407955.
Pathak, J.,Hunt, B.,Girvan, M.,Lu, Z. and Ott, E. 2018. Model-Free Prediction of Large Spatiotemporally Chaotic Systems from Data: A Reservoir Computing Approach. Physical Review Letters. 120, 024102. doi:10.1103/PhysRevLett.120.024102.
Scardapane, S. and Wang, D. 2017. Randomness in neural networks: an overview. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery. 7, doi:10.1002/widm.1200.
Sun, Q. and Ertekin, T. 2015. The Development of Artificial-neural-network-based Universal Proxies to Study Steam Assisted Gravity Drainage(SAGD) and Cyclic Staem Stimulation (CSS) Processes. SPE Western Regional Meeting, 27-30 April, Garden Grove, California, USA. SPE-174074-MS, doi:10.2118/174074-MS.
Sun, Q. and Ertekin, T. 2017. Structuring an artificial intelligence based decision making tool for cyclic steam stimulation processes. Journal of Petroleum Science and Engineering, 154, 564–575. doi:10.1016/j.petrol.2016.10.042.
Tang, H.,Killough, J.E.,Heidari, Z. and Sun, Z., 2017. A new technique to characterize fracture density by use of neutron porosity logs enhanced by electrically transported contrast agents. SPE Journal, 22(04), pp.1–034. SPE-181509-PA. doi:10.2118/181509-PA.
Tang, H.,Sun, Z.,He, Y.,Chai, Z.,Hasan, A.R. and Killough, J., 2019. Investigating the pressure characteristics and production performance of liquid-loaded horizontal wells in unconventional gas reservoirs. Journal of Petroleum Science and Engineering. 176, 456–465. doi:10.1016/j.petrol.2019.01.072
von Schroeter, T.,Hollaender, F., and Gringarten, A. 2001. Deconvolution of Well Test Data as A Nonlinear Total Least Squares Problem. SPE Annual Technical Conference and Exhibition. 30 September – 3 October, New Orleans, Louisiana, USA. SPE-71574-MS, doi:10.2118/71574-MS.
von Schroeter, T.,Hollaender, F. and Gringarten, A. 2004. Deconvolution of Well-Test Data as a Nonlinear Total Least-Squares Problem. SPE Journal, 9,375–390. SPE-77688-PA, doi:10.2118/77688-PA.
Tian, C. and Horne, R. 2015. Applying Machine Learning Techniques to Interpret Flow Rate, Pressure and Temperature Data From Permanent Downhole Gauges. SPE Western Regional Meeting, 27-30 April, Garden Grove, California, USA. SPE-174034-MS, doi:10.2118/174034-MS.
Valko, P. and Lee, W. 2010. A Better Way To Forecast Production From Unconventional Gas Wells. SPE Annual Technical Conference and Exhibition, 19-22 September, Florence, Italy. SPE-134231-MS, doi:10.2118/134231-MS.
Zhang, F.,Saputra, I.,Niu, G.,Adel, I.,Xu, L. and Schecter, D. 2018. Upscaling Laboratory Result of Surfactant-Assisted Spontaneous Imbibition to the Field Scale through Scaling Group Analysis, Numerical Simulation, and Discrete Fracture Network Model. SPE Improved Oil Recovery Conference, Tulsa, Oklahoma, USA. Tulsa, Oklahoma, USA. SPE-190155-MS, doi:10.2118/190155-MS.
Zhang, F.,Saputra, I.,Parsegov, S.,Adel, I. and Schecter, D. 2019. Experimental and Numerical Studies of EOR for the Wolfcamp Formation by Surfactant Enriched Completion Fluids and Multi-Cycle Surfactant Injection. SPE Hydraulic Fracturing Technology Conference. Woodlands, TX, USA. SPE-194325-MS, doi:10.2118/194325-MS.
Zhang, S. and Zhu, D. 2017. Inversion of Downhole Temperature Measurements in Multistage Fracture Stimulation in Horizontal Wells. Paper presented at the SPE Annual Technical Conference and Exhibition, San Antonio, Texas, 9-11 October. SPE-187322-MS. Society of Petroleum Engineers. doi:10.2118/187322-MS