Application of Long Short-Term Memory Neural Networks in Shale Gas Production Prediction using Production-Related Factors

Dae-Mo Lee; Hyo-Jin Shin; Jong-Se Lim

doi:10.32390/ksmer.2022.59.6.673

All Issue

2022 Vol.59, Issue 6 Preview Page Next Page

Research Paper

Application of Long Short-Term Memory Neural Networks in Shale Gas Production Prediction using Production-Related Factors 셰일가스 생산량 예측 시 생산관련인자를 활용한 장단기기억 신경망 적용 연구

31 December 2022. pp. 673-683

PDF XML

Abstract

Insufficient data in the early stages of production results in uncertainty of predicted values on applying decline curve analysis (DCA) using production data of shale reservoir. Additionally, there are limits in production-related factors, such as hydraulic fracturing or well completion conditions, that cannot be considered. In this study, Long Short-Term Memory (LSTM) neural networks were constructed to predict shale gas production by assuming the production time. It was discovered that prediction models could simulate production decline for new wells by learning the decline behavior of multiple shale wells. Moreover, the error could be reduced by using production-related factors for true vertical depth, gross perforated interval, stage count of hydraulic fracturing, and initial production rate, as additional input was confirmed. It may be possible to predict production based on LSTM at the early stages of shale gas production, where it is challenging to apply DCA, through the results of this study.

Keywords

Shale gas

Long Short-Term Memory

Production-related factor

Production prediction

셰일 저류층의 생산량 자료를 활용하여 생산감퇴곡선분석법 적용 시 생산 초기의 충분하지 않은 자료를 사용할 경우 예측 결과에 대한 불확실성이 존재하며, 수압파쇄와 유정완결 조건 등의 생산관련인자를 고려할 수 없다는 한계가 있다. 이 연구에서는 생산시점을 가정하여 셰일가스 생산량을 예측하기 위한 장단기기억 신경망을 구축하였으며, 예측모델이 여러 생산정의 감퇴거동을 학습하여 새로운 생산정에 대한 생산감퇴를 모사할 수 있음을 확인하였다. 또한, 실수직심도, 총천공간격, 수압파쇄 횟수, 초기 생산량에 대한 생산관련인자를 추가 입력자료로 활용함으로써 오차율을 개선할 수 있음을 파악하였다. 이 결과를 통하여 생산감퇴곡선분석법 적용이 어려운 셰일가스 생산 초기에 장단기기억 신경망을 바탕으로 생산량 예측이 가능할 것으로 사료된다.

키워드

셰일가스

장단기기억

생산관련인자

생산량 예측

References

Alabboodi, M.J. and Mohaghegh, S.D., 2016. Conditioning the Estimating Ultimate Recovery of Shale Wells to Reservoir and Completion Parameters, The SPE Eastern Regional meeting, SPE, Canton, Ohio, USA, p.1-21. 10.2118/184064-MS

Alom, M.Z., Taha, T.M., Yakopcic, C., Westberg, S., Sidike, P., Nasrin, M.S., Hasan, M., Van Essen, B.C., Awwal, A.A.S., and Asari, V.K., 2019. A State-of-the-Art Survey on Deep Learning Theory and Architectures, Electronics, 8(3), p.1-66. 10.3390/electronics8030292

Arps, J.J., 1945. Analysis of Decline Curves, Transactions of the AIME, 160(1), p.228-247. 10.2118/945228-G

Biswas, D., 2020. Adapting Shallow and Deep Learning Algorithms to Examine Production Performance - Data Analytics and Forecasting, The SPE/IATMI Asia Pacific Oil & Gas Conference and Exhibition, SPE, Bali, Indonesia, p.1-21. 10.2118/196404-MS

Engelder, T. and Lash, G.G., 2008. Marcellus Shale Play's Vast Resource Potential Creating Stir In Appalachia, American Oil and Gas Reporter, 51(May), Kansas City, Missouri, USA, p.76-87.

Gihm, Y.S., Hwang, I.G., Kim, H.T., Lee, H.S., and Lee, D.S., 2011. Geological Characteristics and Development Strategy of the Marcellus Shale, Journal of the Korean Society for Geosystem Engineering, 48(3), p.371-382.

Gupta, I., Rai, C., Sondergeld, C., and Devegowda, D., 2018. Variable Exponential Decline: Modified Arps To Characterize Unconventional-Shale Production Performance, SPE Reservoir Evaluation and Engineering, 21(4), p.1045-1057. 10.2118/194005-PA

Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory, Neural computation, 9(8), p.1735-1780. 10.1162/neco.1997.9.8.17359377276

Ji, M., Kwon, S., Park, G., Min, B., and Huy, N.X., 2021. Prediction of Water Saturation from Well Log Data using Deep Learning Algorithms, Journal of the Korean Society of Mineral and Energy Resources Engineers, 58(3), p.215-226. 10.32390/ksmer.2021.58.3.215

Kanfar, M. and Wattenbarger, R., 2012. Comparison of Empirical Decline Curve Methods for Shale Wells, The SPE Canadian Unconventional Resources Conference, SPE, Calgary, Alberta, Canada, p.1-12. 10.2118/162648-MS23346116PMC3546477

Kang, P.S., Shin, H.J., and Lim, J.S., 2017. Effect of Shale Reservoir Property and Condition of Hydraulic Fracture on Decline Curve Analysis Factor, Journal of the Korean Society of Mineral and Energy Resources Engineers, 54(3), p.223-232. 10.12972/ksmer.2017.54.3.223

Ki, S., Seo, J., Kwon, O., and Jang, I., 2019. Prediction of Missing Tubing Head Pressure Using Recurrent Neural Network, Journal of the Korean Society of Mineral and Energy Resources Engineers, 56(5), p.416-426. 10.32390/ksmer.2019.56.5.416

Kim, J.S., Shin, H.J., and Lim, J.S., 2014. Probabilistic Decline Curve Analysis for Forecasting Estimated Ultimate Recovery in Shale Gas Play, Journal of the Korean Society of Mineral and Energy Resources Engineers, 51(6), p.808-819. 10.12972/ksmer.2014.51.6.808

Kocoglu, Y., Gorell, S., and McElroy, P., 2021. Application of Bayesian Optimized Deep Bi-LSTM Neural Networks for Production Forecasting of Gas Wells in Unconventional Shale Gas Reservoirs, The SPE/AAPG/SEG Unconventional Resources Technology Conference, URTeC, Houston, Texas, USA, p.1-21. 10.15530/urtec-2021-5418

Lee, K., Lim, J., Yoon, D., and Jung, H., 2019. Prediction of Shale-Gas Production at Duvernay Formation Using Deep-Learning Algorithm, SPE Journal, 24(6), p.2423-2437. 10.2118/195698-PA

Li, X., Ma, X., Xiao, F., Wang, F., and Zhang, S., 2020. Application of Gated Recurrent Unit (GRU) Neural Network for Smart Batch Production Prediction, Energies, 13(22). p.1-22. 10.3390/en13226121

Luo, G., Tian, Y., Bychina, M., and Ehlig-Economides, C., 2019. Production-Strategy Insights Using Machine Learning: Application for Bakken Shale, SPE Reservoir Evaluation and Engineering, 22(3), p.800-816. 10.2118/195681-PA

Luo, S. and Su, H., 2022. Study on the Production Decline Characteristics of Shale Oil: Case Study of Jimusar Field, Frontiers in Energy Research, 10, p.1-13. 10.3389/fenrg.2022.845651

Mosobalaje, O.O., Tiab, D., and Lu, J., 2014. Theories of Arps' Decline Curve Exponent and Loss Ratio, for Saturated Reservoirs, The Abu Dhabi International Petroleum Exhibition and Conference, SPE, Abu Dhabi, UAE, p.1-16. 10.2118/172128-MS

Oh, H., Ki, S., Park, C., and Jang, I., 2021. Analysis of Uncertainty Trend for Estimated Ultimate Recovery Prediction of Shale Gas with Various Production Periods based on Machine Learning, Journal of the Korean Society of Mineral and Energy Resources Engineers, 58(5), p.475-490. 10.32390/ksmer.2021.58.5.475

Olah, C., 2022.07.05., http://colah.github.io/posts/2015-08-Understanding-LSTMs/

Paryani, M., Ahmadi, M., Awoleke, O., and Hanks, C., 2016. Using Improved Decline Curve Models for Production Forecasts in Unconventional Reservoirs, The SPE Eastern Regional Meeting, SPE, Canton, Ohio, p.1-15. 10.2118/184070-MS

Rezaee, R., 2015. Fundamentals of Gas Shale Reservoirs, John Wiley & Sons, New York, USA, p.283-300. 10.1002/9781119039228

Shin, H.J., Lim, J.S., and Jang, I.S., 2021. Probabilistic Prediction of Multi-Wells Production Based on Production Characteristics Analysis Using Key Factors in Shale Formations, Energies, 14(17), p.1-30. 10.3390/en14175226

Song, X., Liu, Y., Xue, L., Wang, J., Zhang, J., Wang, J., Jiang, L., and Cheng, Z., 2020. Time-series well performance prediction based on Long Short-Term Memory (LSTM) neural network model, Journal of Petroleum Science and Engineering, 186, p.1-11. 10.1016/j.petrol.2019.106682

Tan, L., Zuo, L., and Wang, B., 2018. Methods of Decline Curve Analysis for Shale Gas Reservoirs, Energies, 11(3), p.1-18. 10.3390/en11030552

U.S. Energy Information Administration(EIA), 2022.06.07., https://www.eia.gov/todayinenergy/detail.php?id=52198

Wang, S., Chen, Z., and Chen, S., 2019. Applicability of deep neural networks on production forecasting in Bakken shale reservoirs, Journal of Petroleum Science and Engineering, 179, p.112-125. 10.1016/j.petrol.2019.04.016

Yao, B., Chen, J., Li, C., Yang, F., Sun, G., and Lu, Y., 2021. Prediction of Wax Deposits for Crude Pipelines Using Time-Dependent Data Mining, SPE Journal, 26(4), p.1980-2001. 10.2118/205374-PA

Zhan, C., Sankaran, S., LeMoine, V., Graybill, J., and Mey, D.O.S., 2019. Application of Machine Learning for Production Forecasting for Unconventional Resources, The SPE/AAPG/ SEG Unconventional Resources Technology Conference,URTeC, Colorado, USA, p.1-9. 10.15530/urtec-2019-47

Information

Publisher :The Korean Society of Mineral and Energy Resources Engineers
Publisher(Ko) :한국자원공학회
Journal Title :Journal of the Korean Society of Mineral and Energy Resources Engineers
Journal Title(Ko) :한국자원공학회지
Volume : 59
No :6
Pages :673-683
Received Date : 2022-10-14
Revised Date : 2022-12-05
Accepted Date : 2022-12-27
DOI :https://doi.org/10.32390/ksmer.2022.59.6.673

Journal of the Korean Society of Mineral and Energy Resources Engineers ISSN:2288-0291(Print) 2288-2790(Online) 한국자원공학회지

All Issue