Advertisement

Permeability prediction for carbonate reservoir using a data-driven model comprising deep learning network, particle swarm optimization, and support vector regression: a case study of the LULA oilfield

  • Yufeng Gu
  • Zhidong BaoEmail author
  • Xinmin Song
  • Mingyang Wei
  • Dongsheng Zang
  • Bo Niu
  • Kai Lu
Original Paper
  • 19 Downloads

Abstract

Permeability is universally considered as an important parameter since its data is critical for some basic geological work, such as constructing a pore-throat system of reservoir, evaluating flowing capability of formation, etc. Accordingly, how to predict permeability becomes a primary research in the realm of geoscience. Lots of physical models specifically used for permeability prediction have been created in recent decades, but calculation parameters involved in the models must be determined through core experiments. In order to reduce reliance on the usage of the data generated by core experiments, statistical prediction methods for permeability are developed. Support vector regression (SVR) is one of the optimal prediction approaches that can perfectly reveal the nonlinear relationship between permeability and other geological parameters, while its performance is severely limited by qualities of input data and calculation parameters. Colinear issue regarding variables of input data and bad initialization of calculation parameters can cause failure of fitting equation establishment. Thus, in view of those demerits, two techniques, deep learning and particle swarm optimization (PSO), are introduced to enhance the calculation capability of SVR. Then, a hybrid data-driven model which consists of deep learning network, PSO, and SVR is proposed. Data for method validation is recorded by three wells of the LULA oilfield. Two experiments are designed by the validation data. Experiment results prove that the proposed method has the capability to produce more accurate predicted results than those provided by single SVR and PSO-SVR. Consequently, the new hybrid data-driven model is effective in predicting permeability under processing real data.

Keywords

Permeability prediction Continuous restricted Boltzmann machine Particle swarm optimization Support vector regression 

References

  1. Adam J, Ge Z, Sanchez M (2012) Salt-structural styles and kinematic evolution of the Jequitinhonha deepwater fold belt, central Brazil passive margin. Mar Pet Geol 37:101–120.  https://doi.org/10.1016/j.marpetgeo.2012.04.010 CrossRefGoogle Scholar
  2. Ahmadi MA (2011) Prediction of asphaltene precipitation using artificial neural network optimized by imperialist competitive algorithm. J Pet Explor Prod Technol 1(2-4):99–106.  https://doi.org/10.1007/s13202-011-0013-7 CrossRefGoogle Scholar
  3. Ahmadi MA (2012) Neural network based unified particle swarm optimization for prediction of asphaltene precipitation. Fluid Phase Equilib 314:46–51.  https://doi.org/10.1016/j.fluid.2011.10.016 CrossRefGoogle Scholar
  4. Ahmadi MA (2015a) Connectionist approach estimates gas-oil relative permeability in petroleum reservoirs: application to reservoir simulation. Fuel 140:429–439.  https://doi.org/10.1016/j.fuel.2014.09.058 CrossRefGoogle Scholar
  5. Ahmadi MA (2015b) Developing a robust surrogate model of chemical flooding based on the artificial neural network for enhanced oil recovery implications. Math Probl Eng 2015:706897.  https://doi.org/10.1155/2015/706897 CrossRefGoogle Scholar
  6. Ahmadi MA (2016) Toward reliable model for prediction drilling fluid density at wellbore conditions: a LSSVM model. Neurocomputing 211:143–149.  https://doi.org/10.1016/j.neucom.2016.01.106 CrossRefGoogle Scholar
  7. Ahmadi MA, Ahmadi A (2016) Applying a sophisticated approach to predict CO2 solubility in brines: application to CO2 sequestration. Int J Low Carbon Technol 11(3):325–332.  https://doi.org/10.1093/ijlct/ctu034 CrossRefGoogle Scholar
  8. Ahmadi MA, Bahadori A (2015a) A LSSVM approach for determining well placement and conning phenomena in horizontal wells. Fuel 153:276–283.  https://doi.org/10.1016/j.fuel.2015.02.094 CrossRefGoogle Scholar
  9. Ahmadi MA, Bahadori A (2015b) Prediction performance of natural gas dehydration units for water removal efficiency using a least-square support vector machine. Int J Ambient Energy:1–9.  https://doi.org/10.1080/01430750.2015.1004105 CrossRefGoogle Scholar
  10. Ahmadi MA, Ebadi M (2014) Evolving smart approach for determination dew point pressure through condensate gas reservoirs. Fuel 117:1074–1084.  https://doi.org/10.1016/j.fuel.2013.10.010 CrossRefGoogle Scholar
  11. Ahmadi MA, Golshadi M (2012) Neural network based swarm concept for prediction asphaltene precipitation due to natural depletion. J Pet Sci Eng 98-99(6):40–49.  https://doi.org/10.1016/j.petrol.2012.08.011 CrossRefGoogle Scholar
  12. Ahmadi MA, Mahmoudi B (2016) Development of robust model to estimate gas-oil interfacial tension using least square support vector machine: experimental and modeling study. J Supercrit Fluids 107:122–128.  https://doi.org/10.1016/j.supflu.2015.08.012 CrossRefGoogle Scholar
  13. Ahmadi MA, Shadizadeh SR (2012) New approach for prediction of asphaltene precipitation due to natural depletion by using evolutionary algorithm concept. Fuel 102:716–723.  https://doi.org/10.1016/j.fuel.2012.05.050 CrossRefGoogle Scholar
  14. Ahmadi MA, Ahmadi MR, Hosseini SM, Ebadi M (2014a) Connectionist model predicts the porosity and permeability of petroleum reservoirs by means of petro-physical logs: application of artificial intelligence. J Pet Sci Eng 123:183–200.  https://doi.org/10.1016/j.petrol.2014.08.026 CrossRefGoogle Scholar
  15. Ahmadi MA, Ebadi M, Hosseini SM (2014b) Prediction breakthrough time of water coning in the fractured reservoirs by implementing low parameter support vector machine approach. Fuel 117:579–589.  https://doi.org/10.1016/j.fuel.2013.09.071 CrossRefGoogle Scholar
  16. Ahmadi MA, Ebadi M, Marghmaleki PS, Fouladi MM (2014c) Evolving predictive model to determine condensate-to-gas ratio in retrograded condensate gas reservoirs. Fuel 124:241–257.  https://doi.org/10.1016/j.fuel.2014.01.073 CrossRefGoogle Scholar
  17. Ahmadi MA, Ebadi M, Yazdanpanah A (2014d) Robust intelligent tool for estimating dew point pressure in retrograded condensate gas reservoirs: application of particle swarm optimization. J Pet Sci Eng 123:7–19.  https://doi.org/10.1016/j.petrol.2014.05.023 CrossRefGoogle Scholar
  18. Ahmadi MA, Masoumi M, Askarinezhad R (2014e) Evolving connectionist model to monitor the efficiency of an in Situ combustion process: application to heavy oil recovery. Energy Technol 2(9-10):811–818.  https://doi.org/10.1002/ente.201402043 CrossRefGoogle Scholar
  19. Ahmadi MA, Soleimani R, Lee M, Kashiwao T, Bahadori A (2015a) g. Determination of oil well production performance using artificial neural network (ANN) linked to the particle swarm optimization (PSO) tool. Petroleum 1(2):118–132.  https://doi.org/10.1016/j.petlm.2015.06.004 CrossRefGoogle Scholar
  20. Ahmadi MA, Bahadori A, Shadizadeh SR (2015b) A rigorous model to predict the amount of dissolved calcium carbonate concentration throughout oil field brines: side effect of pressure and temperature. Fuel 139:154–159.  https://doi.org/10.1016/j.fuel.2014.08.044 CrossRefGoogle Scholar
  21. Ahmadi MA, Ebadi M, Samadi A, Siuki MZ (2015c) Phase equilibrium modeling of clathrate hydrates of carbon dioxide +1,4-dioxine using intelligent approaches. J Dispers Sci Technol 36(2):236–244.  https://doi.org/10.1080/01932691.2014.904792 CrossRefGoogle Scholar
  22. Ahmadi MA, Hasanvand MZ, Bahadori A (2015d) A least-squares support vector machine approach to predict temperature drop accompanying a given pressure drop for the natural gas production and processing systems. Int J Ambient Energy:1–8.  https://doi.org/10.1080/01430750.2015.1055515 CrossRefGoogle Scholar
  23. Ahmadi MA, Lee M, Bahadori A (2015e) Prediction of a solid desiccant dehydrator performance using least squares support vector machines algorithm. J Taiwan Inst Chem Eng 50:115–122.  https://doi.org/10.1016/j.jtice.2014.12.004 CrossRefGoogle Scholar
  24. Ahmadi MA, Pouladi B, Javvi Y, Alfkhani S, Soleimani R (2015f) Connectionist technique estimates H2S solubility in ionic liquids through a low parameter approach. J Supercrit Fluids 97:81–87.  https://doi.org/10.1016/j.supflu.2014.11.009 CrossRefGoogle Scholar
  25. Ahmadi MA, Masoumi M, Askarinezhad R (2015g) Evolving smart model to predict the combustion front velocity for in situ combustion. Energy Technol 3(2):128–135.  https://doi.org/10.1002/ente.201402104 CrossRefGoogle Scholar
  26. Akande KO, Owolabi TO, Olatunji SO, Abdulraheem AA (2016) A hybrid particle swarm optimization and support vector regression model for modeling permeability prediction of hydrocarbon reservoir. J Pet Sci Eng 150:43–53.  https://doi.org/10.1016/j.petrol.2016.11.033 CrossRefGoogle Scholar
  27. Andrew M, Bijeljic B, Blunt MJ (2015) Pore-by-pore capillary pressure measurements using X-ray microtomography at reservoir conditions: curvature, snap-off, and remobilization of residual CO2. Water Resour Res 50(11):8760–8774.  https://doi.org/10.1002/2014WR015970 CrossRefGoogle Scholar
  28. Anifowose F, Adeniye S, Abdulraheem A (2014) Recent advances in the application of computational intelligence techniques in oil and gas reservoir characterization: a comparative study. J Exp Theor Artif Intell 26(4):551–570.  https://doi.org/10.1080/0952813X.2014.924577 CrossRefGoogle Scholar
  29. Arpat GB, Gümrah F, Yeten B (1998) The neighborhood approach to prediction of permeability from wireline logs and limited core plug analysis data using backpropagation artificial neural networks. J Pet Sci Eng 20(1-2):1–8.  https://doi.org/10.1016/S0920-4105(98)00034-5 CrossRefGoogle Scholar
  30. Aslanian D, Moulin M, Olivet JL, Unternehr P, Matias L, Bache F (2009) Brazilian and African passive margins of the central segment of the south Atlantic Ocean: kinematic constraints. Tectonophysics 468(1):98–112.  https://doi.org/10.1016/j.tecto.2008.12.016 CrossRefGoogle Scholar
  31. Awad M, Khanna R (2007) Support vector regression. Neural Inf Process Lett Rev 11(10):203–224.  https://doi.org/10.1007/978-1-4302-5990-9_4 CrossRefGoogle Scholar
  32. Baziar S, Tadayoni M, Nabi-Bidhendi M, Khalili M (2014) Prediction of permeability in a tight gas reservoir by using three soft computing approaches: a comparative study. Journal of Natural Gas Science & Engineering 21:718–724.  https://doi.org/10.1016/j.jngse.2014.09.037 CrossRefGoogle Scholar
  33. Bengio Y, Delalleau O (2014) Justifying and generalizing contrastive divergence. Neural Comput 21(6):1601–1621.  https://doi.org/10.1162/neco.2008.11-07-647 CrossRefGoogle Scholar
  34. Bengio Y, Lamblin P, Popovici D, Larochelle H (2006) Greedy layer-wise training of deep networks. Adv Neural Inf Proces Syst 19:153–160 http://dblp.uni-trier.de/db/conf/nips/nips2006.html#BengioLPL06 Google Scholar
  35. Billings SA, Voon WSF (1986) A prediction-error and stepwise-regression estimation algorithm for non-linear systems. Int J Control 44(3):803–822.  https://doi.org/10.1080/00207178608933633 CrossRefGoogle Scholar
  36. Brown CE (1993) Use of principal-component, correlation, and stepwise multiple-regression analyses to investigate selected physical and hydraulic properties of carbonate-rock aquifers. J Hydrol 147(1-4):169–195.  https://doi.org/10.1016/0022-1694(93)90080-S CrossRefGoogle Scholar
  37. Chen Y, Lu L, Li X (2014) Application of continuous restricted Boltzmann machine to identify multivariate geochemical anomaly. J Geochem Explor 140(4):56–63.  https://doi.org/10.1016/j.gexplo.2014.02.013 CrossRefGoogle Scholar
  38. Chilingar GV (1964) Relationship between porosity, permeability, and grain-size distribution of sands and sandstones. Dev Sedimentol 1:71–75.  https://doi.org/10.1016/S0070-4571(08)70469-2 CrossRefGoogle Scholar
  39. Daigle H, Dugan B (2009) Extending NMR data for permeability estimation in fine-grained sediments. Mar Pet Geol 26(8):1419–1427.  https://doi.org/10.1016/j.marpetgeo.2009.02.008 CrossRefGoogle Scholar
  40. Denney D (2009) Worldwide deepwater petroleum exploration and development prospectivity: comparative analysis of efforts and outcomes. J Pet Technol 62(6):44–46.  https://doi.org/10.2118/0610-0044-JPT CrossRefGoogle Scholar
  41. Djuric N, Lan L, Vucetic S, Wang Z (2013) BudgetedSVM: a toolbox for scalable SVM approximations. J Mach Learn Res 14(1):3813–3817.  https://doi.org/10.1142/S0218194013500484 CrossRefGoogle Scholar
  42. Duchi J, Hazan E, Singer Y (2011) Adaptive subgradient methods for online learning and stochastic optimization. J Mach Learn Res 12:2121–2159 http://dblp.uni-trier.de/db/journals/jmlr/jmlr12.html#DuchiHS11 Google Scholar
  43. Fischer A, Igel C (2014) Training restricted Boltzmann machines: an introduction. Pattern Recogn 47(1):25–39.  https://doi.org/10.1016/j.patcog.2013.05.025 CrossRefGoogle Scholar
  44. Gholami R, Shahraki AR, Paghaleh MJ (2012) Prediction of hydrocarbon reservoirs permeability using support vector machine. Math Probl Eng 2012:139–149.  https://doi.org/10.1155/2012/670723 CrossRefGoogle Scholar
  45. Gu Y, Bao Z, Lin Y, Qin Z, Lu J, Wang H (2017) The porosity and permeability prediction methods for carbonate reservoirs with extremely limited logging data: stepwise regression vs. N-way analysis of variance. J Nat Gas Sci Eng 42:99–119.  https://doi.org/10.1016/j.jngse.2017.03.010 CrossRefGoogle Scholar
  46. Guerra MCM, Underhill JR (2012) Role of halokinesis in controlling structural styles and sediment dispersal in the Santos Basin, offshore Brazil. Geol Soc Lond Spec Publ 363:175–206.  https://doi.org/10.1144/SP363.9 CrossRefGoogle Scholar
  47. Helmy T, Fatai A (2010) Hybrid computational intelligence models for porosity and permeability prediction of petroleum reservoirs. Int J Comput Intell Appl 9(4):313–337.  https://doi.org/10.1142/S1469026810002902 CrossRefGoogle Scholar
  48. Hinton GE, Osindero S, Teh Y (2006a) A fast learning algorithm for deep belief nets. Neural Comput 18:1527–1554.  https://doi.org/10.1162/neco.2006.18.7.1527 CrossRefGoogle Scholar
  49. Hinton GE, Osindero S, Welling M, Teh Y (2006b) Unsupervised discovery of non-linear structure using contrastive backpropagation. Cogn Sci 30:725–731.  https://doi.org/10.1207/s15516709cog0000_76 CrossRefGoogle Scholar
  50. Huc AY (2004) Petroleum in the south Atlantic. Oil Gas Sci Technol 59:243–253.  https://doi.org/10.2516/ogst:2004017 CrossRefGoogle Scholar
  51. Kennedy J, Eberhart RC (1995) Particle swarm optimization. Proceedings of IEEE International Conference on Neural Networks.  https://doi.org/10.1109/ICNN.1995.488968 CrossRefGoogle Scholar
  52. Larochelle H, Bengio Y, Louradour J, Lamblin P (2009) Exploring strategies for training deep neural networks. J Mach Learn Res 1(10):1–40.  https://doi.org/10.1145/1577069.1577070 CrossRefGoogle Scholar
  53. Liu T, Ma Z, Wang J, Lv H (2005) Integrating MDT, NMR log, and conventional logs for one-well evaluation. J Pet Sci Eng 46(1-2):73–80.  https://doi.org/10.1016/j.petrol.2004.09.001 CrossRefGoogle Scholar
  54. Ons B, Mohammed B (2018) Efficient FPGA-based architecture of an automatic wheeze detector using a combination of MFCC and SVM algorithms. J Syst Archit 88:54–64.  https://doi.org/10.1016/j.sysarc.2018.05.010 CrossRefGoogle Scholar
  55. Park C, Ki M, Namkung J, Paik J (2006) Multimodal priority verification of face and speech using momentum back-propagation neural network. Lect Notes Comput Sci:140–149.  https://doi.org/10.1007/11760023_22 CrossRefGoogle Scholar
  56. Platt JC (1998) Sequential minimal optimization: a fast algorithm for training support vector machines. Adv Kernel Methods 208:212–223 http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.43.4376 Google Scholar
  57. Shadizadeh SR, Saffarzadeh S (2012) Reservoir rock permeability prediction using support vector regression in an Iranian oil field. J Geophys Eng 9(3):336–344.  https://doi.org/10.1088/1742-2132/9/3/336 CrossRefGoogle Scholar
  58. Sheri AM, Rafique A, Pedrycz W, Jeon M (2015) Contrastive divergence for memristor-based restricted Boltzmann machine. Eng Appl Artif Intell 37:336–342.  https://doi.org/10.1016/j.engappai.2014.09.013 CrossRefGoogle Scholar
  59. Shi Y, Eberhart RC (1998) Parameter selection in particle swarm optimization. In: International Conference on Evolutionary Programming, 1447, pp 591–600.  https://doi.org/10.1007/BFb0040810 CrossRefGoogle Scholar
  60. Thompson DL, Stilwell JD, Hall M (2015) Lacustrine carbonate reservoirs from early Cretaceous rift lakes of western Gondwana: pre-salt coquina of Brazil and west Africa. Gondwana Res 28:26–51.  https://doi.org/10.1016/j.gr.2014.12.005 CrossRefGoogle Scholar
  61. Timur A (1968) An investigation of permeability, porosity, and residual water saturation relationship for sandstone reservoirs. Log Anal 9(4):8–17Google Scholar
  62. Walsh, J.B., 1981. Effect of pore pressure and confining pressure on fracture permeability. Int J Rock Mech Min Sci Geomech Abstr, 18(5), 429-435.  https://doi.org/10.1016/0148-9062(81)90006-1.CrossRefGoogle Scholar
  63. Wyllie MRJ, Rose WD (1950) Some theoretical considerations related to the quantitative evaluation of the physical characteristics of reservoir rock from electrical log data. J Pet Technol 2(4):105–118.  https://doi.org/10.2118/950105-G CrossRefGoogle Scholar

Copyright information

© Saudi Society for Geosciences 2019

Authors and Affiliations

  • Yufeng Gu
    • 1
    • 2
    • 3
  • Zhidong Bao
    • 1
    Email author
  • Xinmin Song
    • 2
  • Mingyang Wei
    • 1
  • Dongsheng Zang
    • 1
  • Bo Niu
    • 1
  • Kai Lu
    • 1
  1. 1.College of GeosciencesChina University of PetroleumBeijingChina
  2. 2.PetroChina Research Institute of Petroleum Exploration and DevelopmentBeijingChina
  3. 3.State Key Laboratory of Petroleum ResourcesChina University of PetroleumBeijingChina

Personalised recommendations