Reservoir production capacity prediction of Zananor field based on LSTM neural network

• Autorzy: Liu JiYuan , Wang Fei , Zhang ChengEn , Zhang Yong , Li Tao

Identyfikatory

DOI

11600-024-01388-2

• Języki publikacji: EN

Abstrakty

EN

This paper aims to explore the application of artificial intelligence in the petroleum industry, with a specific focus on oil well production forecasting. The study utilizes the Zananor field as a case study, systematically organizing raw data, categorizing different well instances and production stages in detail, and normalizing the data. An individual long short-term memory (LSTM) neural network model is constructed with monthly oil production data as input to predict the monthly oil production of the experimental oilfield. Furthermore, a multivariate LSTM neural network model is introduced, incorporating different production data as input sets to enhance the accuracy of monthly oil production predictions. A comparative analysis is conducted with particle swarm optimization optimized recurrent neural network results. Finally, gray relational analysis and principal component analysis methods are compared in feature selection. Experimental results demonstrate that the LSTM model is more suitable for the study area, and the multivariate model outperforms the univariate model in terms of prediction accuracy, especially for monthly oil production. Additionally, gray relational analysis exhibits higher accuracy and greater applicability in feature selection compared to principal component analysis. These research findings provide valuable guidance for production forecasting and operational optimization in the petroleum industry.

Słowa kluczowe

EN

artificial intelligence; output prediction; long-term memory networks; short-term memory networks; parameter optimization; master factor selection

PL

sztuczna inteligencja; prognozowanie wyników; sieci pamięci długotrwałej; sieci pamięci krótkotrwałej; optymalizacja parametrów

• Wydawca: Instytut Geofizyki PAN ; Springer
• Czasopismo: Acta Geophysica
• Rocznik: 2025
• Tom: Vol. 73, no. 1
• Strony: 295--310
• Opis fizyczny: Bibliogr. 32 poz.

Twórcy

autor

Liu JiYuan

• College of Geological Engineering and Geomatics, Chang’an University, Xi’ an 710054, China

autor

Wang Fei

• College of Geological Engineering and Geomatics, Chang’an University, Xi’ an 710054, China

• https://orcid.org/0000-0001-7847-6234

autor

Zhang ChengEn

• China Petroleum Logging Co Ltd, Qinghai Branch, Lenghu 736202, Qinghai, China

autor

Zhang Yong

• China Petroleum & Chemical Corporation, Qinghai Oilfield New Energy Division, Lenghu 736202, Qinghai, China

autor

Li Tao

• China Petroleum & Chemical Corporation, Qinghai Oilfield New Energy Division, Lenghu 736202, Qinghai, China

Bibliografia

• 1. Alakeely AA, Horne RN (2021) Application of deep learning methods to estimate multiphase flow rate in producing wells using surface measurements. J Petrol Sci Eng 205:16. https://doi.org/ 10.1016/j.petrol.2021.108936
• 2. Barraza JF, Brauning LG, Perez RB, Morais CB, Martins MR, Droguett EL (2022) Deep learning health state prognostics of physical assets in the Oil and Gas industry. Proc Inst Mech Eng Part O J Risk Reliab 236(4):598-616. https://doi.org/10.1177/ 1748006X20976817
• 3. Chen YX, Li JR, IEEE (2021) Recurrent neural networks algorithms and applications. Paper presented at the 2nd international conference on big data and artificial intelligence and software engineering (ICBASE), Zhuhai, 24-26 Sep 2021
• 4. D’Almeida AL, Bergiante NCR, Ferreira GD, Leta FR, Lima CBD, Lima GBA (2022) Digital transformation: a review on artificial intelligence techniques in drilling and production applications. Int J Adv Manuf Technol 119(9-10):5553-5582. https://doi.org/10.1007/s00170-021-08631-w
• 5. Duan YG, Wang H, Wei MQ, Tan LJ, Yue T (2022) Application of ARIMA-RTS optimal smoothing algorithm in gas well production prediction. Petroleum 8(2):270-277. https://doi.org/10. 1016/j.petlm.2021.09.001
• 6. Fan DY, Sun H, Yao J, Zhang K, Yan X, Sun ZX (2021) Well production forecasting based on ARIMA-LSTM model considering manual operations. Energy 220:13. https://doi.org/10.1016/j. energy.2020.119708
• 7. Galkin VI, Koltyrin AN (2020) Investigation of probabilistic models for forecasting the efficiency of proppant hydraulic fracturing technology. J Min Inst 246:650-659
• 8. Guo ZX, Zhao JZ, You ZJ, Li YM, Zhang S, Chen YY (2021) Prediction of coalbed methane production based on deep learning. Energy 230:13. https://doi.org/10.1016/j.energy.2021.120847
• 9. H S, S J (1997) Long short-term memory. Neural Comput 9(8):1735
• 10. He HH (2023) An intelligent algorithm for fast machine translation of long English sentences. J Intell Syst 32(1):9. https://doi.org/10.1515/jisys-2022-0257
• 11. Hospedales T, Antoniou A, Micaelli P, Storkey A (2022) Meta-learning in neural networks: a survey. IEEE Trans Pattern Anal Mach Intell 44(9):5149-5169
• 12. Huang RJ, Wei CJ, Wang BH, Yang J, Xu X, Wu SW, Huang SQ (2022) Well performance prediction based on long short-term memory (LSTM) neural network. J Petrol Sci Eng 208:17. https://doi.org/10.1016/j.petrol.2021.109686
• 13. Ibrahim NM, Alharbi AA, Alzahrani TA, Abdulkarim AM, Alessa IA, Hameed AM, Almuqhim AA (2022) Well performance classification and prediction: deep learning and machine learning long term regression experiments on oil, gas, and water production. Sensors 22(14):22. https://doi.org/10.3390/s22145326
• 14. Karim ME, Foysal M, Das S (2022) Stock price prediction using Bi-LSTM and GRU-based hybrid deep learning approach. Paper presented at the 3rd doctoral symposium on computational intelligence (DoSCI), Inst of Eng and Tech, Lucknow, 05 March 2022
• 15. Katterbauer K, Marsala A (2021) A novel sparsity deploying reinforcement deep learning algorithm for saturation mapping of oil and gas reservoirs. Arab J Sci Eng 46(7):6859-6865. https://doi.org/10.1007/s13369-020-05023-2
• 16. Kumar I, Tripathi BK, Singh A (2023) Attention-based LSTM network-assisted time series forecasting models for petroleum production. Eng Appl Artif Intell 123:15. https://doi.org/10.1016/j.engappai.2023.106440
• 17. Li XC, Ma XF, Xiao FC, Xiao C, Wang F, Zhang SC (2022) A physics-constrained long-term production prediction method for multiple fractured wells using deep learning. J Petrol Sci Eng 217:14. https://doi.org/10.1016/j.petrol.2022.110844
• 18. Liang B, Liu J, You JY, Jia J, Pan Y, Jeong H (2023) Hydrocarbon production dynamics forecasting using machine learning: a state-of-the-art review. Fuel 337:13. https://doi.org/10.1016/j. fuel.2022.127067
• 19. Liu YY, Ma XH, Zhang XW, Guo W, Kang LX, Yu RZ, Sun YP (2021) A deep-learning-based prediction method of the estimated ultimate recovery (EUR) of shale gas wells. Pet Sci 18(5):1450—1464. https://doi.org/10.1016/j.petsci.2021.08.007
• 20. Mahzari P, Emambakhsh M, Temizel C, Jones AP (2022) Oil production forecasting using deep learning for shale oil wells under variable gas-oil and water-oil ratios. Pet Sci Technol 40(4):445- 468. https://doi.org/10.1080/10916466.2021.2001526
• 21. Pan ST, Wu HJ (2023) Performance improvement of speech emotion recognition systems by combining 1D CNN and LSTM with data augmentation. Electronics 12(11):21. https://doi.org/10. 3390/electronics12112436
• 22. Qiang Z, Yasin Q, Golsanami N, Du QZ (2020) Prediction of reservoir quality from log-core and seismic inversion analysis with an artificial neural network: a case study from the sawan gas field. Pak Energ 13(2):19. https://doi.org/10.3390/en13020486
• 23. Sagheer A, Kotb M (2019) Time series forecasting of petroleum production using deep LSTM recurrent networks. Neurocomputing 323:203-213. https://doi.org/10.1016Zj.neucom.2018.09.082
• 24. Sang W, Yuan S, Han H, Liu H, Yu Y (2022) Porosity prediction using semi-supervised learning with biased well log data for improving estimation accuracy and reducing prediction uncertainty. Geophys J Int 232(2):940-957. https://doi.org/10.1093/ gji/ggac371
• 25. Shin J, Kim SM (2022) Temporal prediction of paralytic shellfish toxins in the mussel mytilus galloprovincialis using a LSTM neural network model from environmental data. Toxins 14(1):14. https://doi.org/10.3390/toxins14010051
• 26. Sobczyki EJ, Sokolowski A, Kopacz M, Fijorek K, Denkowska S (2020) The analysis of dependence of the level of operational costs and production outputs upon geological and mining conditions in selected hard coal mines in Poland. Gospodarka Surowcami Mineralnymi-Mineral Resources Management 36(3):75-95
• 27. Song X, Liu Y, Xue L, Wang J, Zhang J, Wang J, Cheng Z (2020) Time-series well performance prediction based on long shortterm memory (LSTM) neural network model. J Pet Sci Eng 186:106682. https://doi.org/10.1016/j.petrol.2019.106682
• 28. Xu XJ, Rui XP, Fan YL, Yu T, Ju YW (2020a) Forecasting of coalbed methane daily production based on T-LSTM neural networks. Symmetry 12(5):15. https://doi.org/10.3390/sym12050861
• 29. Xu XJ, Rui XP, Fan YL, Yu T, Ju YW (2020b) A Multivariate long short-term memory neural network for coalbed methane production forecasting. Symmetry 12(12):15. https://doi.org/10.3390/ sym12122045
• 30. Yuan S, Jiao X, Luo Y, Sang W, Wang S (2021) Double-scale supervised inversion with a data-driven forward model for low-frequency impedance recovery. Geophysics 87(2):R165-R181. https://doi.org/10.1190/geo2020-0421.1
• 31. Zhang K, Zhang JD, Ma XP, Yao CJ, Zhang LM, Yang YF, Zhao H (2021) History matching of naturally fractured reservoirs using a deep sparse autoencoder. SPE J 26(4):1700-1721. https://doi.org/10.2118/205340-PA
• 32. Zhang JH, Zhang QS, Zhang JX (2023) The result greyness problem of the grey relational analysis and its solution. J Intell Fuzzy Syst 44(4):6079-6088

Uwagi

Opracowanie rekordu ze środków MNiSW, umowa nr POPUL/SP/0154/2024/02 w ramach programu "Społeczna odpowiedzialność nauki II" - moduł: Popularyzacja nauki (2025).