A deep-learning approach for reservoir evaluation for shale gas wells with complex fracture networks

Hongyang Chu, Peng Dong, W. John Lee

Abstract view|0|times       PDF download|0|times

Abstract


The complex fracture networks in shale gas reservoirs bring greater challenges and uncertainties to the modeling in reservoir evaluation. As the  emerging potential technology, deep learning can be usefully applied to many aspects of reservoir evaluation. To further conduct the reservoir evaluation in rate transient analysis, this work proposes a data-driven proxy model for accurately evaluating the horizontal wells with complex fracture networks in shales. The production time, variable bottom hole pressure, and the fracture networks properties are used as input variables, while the output variable refers to the production for the forecast time period. The data from boundary element method is used to generate the proxy model for the learning process. The method of shuffled cross-validation is used to increase the model’s accuracy and generalizability. The proxy model is coupled with recently developed deep learning methods such as attention mechanism, skip connection, and cross-validation to address the time series analysis problem for multivariate operating and physical parameters. Results demonstrate that the attention mechanism is robust. The operating parameters analysis shows that the attention mechanism has the ability to analyze variable pressure drop/flowrate data. Sensitivity analysis also indicates that the model takes into account the geometric characteristics of fracture network. The model reliability is proved by a case study from Marcellus shale. The computation time of the trained attention mechanism model is approximately 0.3 s, which equates to 3.8% of the physical model’s 
running time.

Cited as: Chu, H., Dong, P., Lee, W. J. A deep-learning approach for reservoir evaluation for shale gas wells with complex fracture networks. Advances in Geo-Energy Research, 2023, 7(1): 49-65. https://doi.org/10.46690/ager.2023.01.06


Keywords


Deep-Learning, time series analysis, multivariate input, shale gas, reservoir evaluation

Full Text:

PDF

References


Alimohammadi, H., Rahmanifard, H., Chen, N. Multivariate time series modelling approach for production forecasting in nconventional resources. Paper SPE 201571 Presented at SPE Annual Technical Conference and Exhibition, Virtual, 26-29 October, 2020.

Aminian, K., Ameri, S. Predicting production performance of CBM reservoirs. Journal of Natural Gas Science and Engineering, 2009, 1(1-2): 25-30.

Carlson, E. S., Mercer, J. C. Devonian shale gas production: Mechanisms and simple models. Journal of Petroleum Technology, 1991, 43(4): 476-482.

Chao, G., Lee, W. J., Spivey, J. P., et al. Modeling multilayer gas reservoirs including sorption effects. Paper SPE 29173 Presented at SPE Eastern Regional Meeting, Charleston, West Virginia, 8-10 November, 1994.

Cho, H. Integrated optimization on long horizontal well length. Paper SPE 68599 Presented at SPE Hydrocarbon Economics and Evaluation Symposium, Dallas, Texas, 2-3 April, 2001.

Cho, K., Van Merriënboer, B., Gulcehre, C., et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation. Paper Presented at Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, 25-29 October, 2014.

Choi, J., Roberts, D. C., Lee, E. S. Forecasting oil production in North Dakota using the seasonal autoregressive integrated moving average (S-ARIMA). Natural Resources, 2015, 6(1): 16-26.

Cipolla, C. L., Fitzpatrick, T., Williams, M. J., et al. Seismicto-simulation for unconventional reservoir development. Paper SPE 146876 Presented at SPE Reservoir Characterisation and Simulation Conference and Exhibition, Abu Dhabi, UAE, 9-11 October, 2011.

Cipolla, C. L., Lolon, E. P., Erdle, J. C., et al. Reservoir modeling in shale-gas reservoirs. SPE Reservoir Evaluation & Engineering, 2010, 13(4): 638-653.

Clarkson, C. R., Solano, N., Bustin, R. M., et al. Pore structure characterization of North American shale gas reservoirs using USANS/SANS, gas adsorption, and mercury intrusion. Fuel, 2013, 103: 606-616.

Curtis, J. B. Fractured shale-gas systems. AAPG Bulletin, 2002, 86(11): 1921-1938.

Denney, D. Evaluating implications of hydraulic fracturing in shale-gas reservoirs. Journal of Petroleum Technology, 2009, 61(8): 53-54.

Fink, R., Krooss, B. M., Amann-Hildenbrand, A. Stress-dependence of porosity and permeability of the Upper Jurassic Bossier shale: An experimental study. Geological Society, London, Special Publications, 2017, 454(1): 107-130.

Freeman, C. M., Moridis, G., Ilk, D., et al. A numerical study of performance for tight gas and shale gas reservoir systems. Journal of Petroleum Science and Engineering, 2013, 108: 22-39.

Fredd, C. N., McConnell, S. B., Boney, C. L., et al. Experimental study of hydraulic fracture conductivity demonstrates the benefits of using proppants. Paper SPE 60326 Presented at SPE Rocky Mountain Regional/Low-Permeability Reservoirs Symposium and Exhibition, Denver, Colorado, 12-15 March, 2000.

Gale, J. F. W., Laubach, S. E., Olson, J. E., et al. Natural fractures in shale: A review and new observations. AAPG Bulletin, 2014, 98(11): 2165-2216.

Gao, C., Lee,W. J., Spivey, J. P., et al. Modeling multilayer gas reservoirs including sorption effects. Paper SPE 29173 Presented at SPE Eastern Regional Meeting, Charleston, West Virginia, 8-10 November, 1994.

Ghahfarokhi, P. K., Carr, T., Bhattacharya, S., et al. A fiberoptic assisted multilayer perceptron reservoir production modeling: A machine learning approach in prediction of gas production from the marcellus shale. Paper URTEC 2902641 Presented at SPE/AAPG/SEG Unconventional Resources Technology Conference, Houston, Texas, 23-25 July, 2018.

Hamdi, H., Clarkson, C. R., Esmail, A., et al. Huff-npuff (HNP) pilot design in shale reservoirs using dualporosity, dual-permeability compositional simulations. European Association of Geoscientists & Engineers, 2020, 2020: 1-30.

Hübner, R., Steinhauser, M., Lehle, C. A dual-stage two-phase model of selective attention. Psychological Review, 2010, 117(3): 759-784.

Jia, X., Zhang, F. Applying data-driven method to production decline analysis and forecasting. Paper SPE 181616 Presented at SPE Annual Technical Conference and Exhibition, Dubai, UAE, 26-28 September, 2016.

Khan, H., Louis, C. An artificial intelligence neural networks driven approach to forecast production in unconventional reservoirs-comparative analysis with decline curve. Paper IPTC 21350 Presented at International Petroleum Technology Conference, Virtual, 23 March-1 April, 2021.

Kingma, D. P., Ba, J. Adam: A method for stochastic optimization. Paper Presented at 3rd International Conference on Learning Representations, San Diego, 7-9 May, 2015.

Kucuk, F., Sawyer, W. K. Transient flow in naturally fractured reservoirs and its application to Devonian gas shales. Paper SPE 9397 Presented at SPE Annual Technical Conference and Exhibition, Dallas, Texas, 21-24 September, 1980.

Kwak, S. G., Kim, J. H. Central limit theorem: The cornerstone of modern statistics. Korean Journal of Anesthesiology, 2017, 70(2): 144-156.

Lee, J., Sidle, R. Gas-reserves estimation in resource plays. SPE Economics & Management, 2010, 2(2): 86-91.

Liu, J., Ma, S., Shen, W., et al. Image feature recognition and gas permeability prediction of Gaomiaozi bentonite based on digital images and machine learning. Advances in Geo-Energy Research, 2022, 6(4): 314-323.

Luo, S., Ding, C., Cheng, H., et al. Estimated ultimate recovery prediction of fractured horizontal wells in tight oil reservoirs based on deep neural networks. Advances in Geo-Energy Research, 2022, 6(2): 111-122.

Mao, X., Shen, C., Yang, Y. B. Image restoration using very deep convolutional encoder-decoder networks with symmetric skip connections. Advances in Neural Information Processing Systems, 2016, 29: 2802-2810.

Matsumoto, M., Nishimura, T. Mersenne twister: A 623- dimensionally equidistributed uniform pseudo-random number generator. ACM Transactions on Modeling and Computer Simulation, 1998, 8(1): 3-30.

Neal, D. B., Mian, M. A. Early-time tight gas production forecasting technique improves reserves and reservoir description. SPE Formation Evaluation, 1989, 4(1): 25-32.

Ning, Y., Kazemi, H., Tahmasebi, P. A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Computers & Geosciences, 2022, 164: 105126.

Nobakht, M., Ambrose, R., Clarkson, C. R., et al. Effect of completion heterogeneity in a horizontal well with multiple fractures on the long-term forecast in shale-gas reservoirs. Journal of Canadian Petroleum Technology, 2013, 52(6): 417-425.

Ozkan, E., Raghavan, R., Apaydin, O. G. Modeling of fluid transfer from shale matrix to fracture network. Paper SPE 134830 Presented at SPE Annual Technical Conference and Exhibition, Florence, Italy, 19-22 September, 2010.

Pedrosa, O. A. Pressure transient response in stress-sensitive formations. Paper SPE 15115 Presented at SPE California Regional Meeting, Oakland, California, 2-4 April, 1986.

Qin, Y., Song, D., Chen, H., et al. A dual-stage attention-based recurrent neural network for time series prediction. Paper Presented at Proceedings of the 26th International Joint Conference on Artificial Intelligence, 19 August, 2017.

Stehfest, H. Algorithm 368: Numerical inversion of Laplace transforms [D5]. Communications of the ACM, 1970, 13(1): 47-54.

Suhag, A., Ranjith, R., Aminzadeh, F. Comparison of shale oil production forecasting using empirical methods and artificial neural networks. Paper SPE 187112 Presented at SPE Annual Technical Conference and Exhibition, San Antonio, Texas, 9-11 October, 2017.

Sun, H., Chawathe, A., Hoteit, H., et al. Understanding shale gas flow behavior using numerical simulation. SPE Journal, 2015, 20(1): 142-154.

Thompson, J. M., M’Angha, V. O., Anderson, D. M. Advancements in shale gas production forecasting-A marcellus case study. Paper SPE 144436 Presented at North American Unconventional Gas Conference and Exhibition, The Woodlands, Texas, 14-16 June, 2011.

Tong, T., Li, G., Liu, X., et al. Image super-resolution using dense skip connections. Paper Presented at 2017 IEEE International Conference on Computer Vision, Venice, Italy, 22-29 October, 2017.

Van Everdingen, A. F., Hurst, W. The application of the Laplace transformation to flow problems in reservoirs. Journal of Petroleum Technology, 1949, 1(12): 305-324.

Vicente, R., Sarica, C., Ertekin, T. Horizontal well design optimization: A study of the parameters affecting the productivity and flux distribution of a horizontal well. Paper SPE 84194 Presented at SPE Annual Technical Conference and Exhibition, Denver, Colorado, 5-8 October, 2003.

Wang, H. T. Performance of multiple fractured horizontal wells in shale gas reservoirs with consideration of multiple mechanisms. Journal of Hydrology, 2014, 510: 299-312.

Warpinski, N. R., Mayerhofer, M. J., Vincent, M. C., et al. Stimulating unconventional reservoirs: Maximizing network growth while optimizing fracture conductivity. Journal of Canadian Petroleum Technology, 2009, 48(10): 39-51.

Wu, C., Wang, S., Yuan, J., et al. A prediction model of specific productivity index using least square support vector machine method. Advances in Geo-Energy Research, 2020, 4(4): 460-467.

Yao, J., Li, Z., Liu, L., et al. Optimization of fracturing parameters by modified variable-length particle-swarm optimization in shale-gas reservoir. SPE Journal, 2021, 26(2): 1032-1049.

Yin, F., Xue, X., Zhang, C., et al. Multifidelity genetic transfer: an efficient framework for production optimization. SPE Journal, 2021, 26(4): 1614-1635.

Zhao, K., Du, P. A new production prediction model for multistage fractured horizontal well in tight oil reservoirs. Advances in Geo-Energy Research, 2020, 4(2): 152-161.

Zhao, J., Sun, M., Pan, Z., et al. Effects of pore connectivity and water saturation on matrix permeability of deep gas shale. Advances in Geo-Energy Research, 2022, 6(1): 54-68.

Zhang, L., Wang, S., Zhang, K., et al. Cooperative artificial bee colony algorithm with multiple populations for interval multiobjective optimization problems. IEEE Transactions on Fuzzy Systems, 2019, 27(5): 1052-1065.

Zhong, Z., Sun, A. Y., Ren, B., et al. A deep-learning-based approach for reservoir production forecast under uncertainty. SPE Journal, 2021, 26(3): 1314-1340.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2022 The Author(s)

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Copyright ©2018. All Rights Reserved