Complex lithology prediction using mean impact value, particle swarm optimization, and probabilistic neural network techniques

Gu, Yufeng; Zhang, Zhongmin; Zhang, Demin; Zhu, Yixuan; Bao, Zhidong; Zhang, Daoyong

doi:10.1007/s11600-020-00504-2

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Artykuł - szczegóły

Tytuł artykułu

Complex lithology prediction using mean impact value, particle swarm optimization, and probabilistic neural network techniques

Autorzy

Gu Yufeng , Zhang Zhongmin , Zhang Demin , Zhu Yixuan , Bao Zhidong , Zhang Daoyong

Wybrane pełne teksty z tego czasopisma

https://www.springer.com/journal/11600

Identyfikatory

DOI

10.1007/s11600-020-00504-2

Warianty tytułu

Języki publikacji

Abstrakty

Lithology prediction is a fundamental problem because the outcome of lithology prediction is the critical underlying data for some basic geological work, e.g., establishing stratigraphic framework or analyzing distribution of sedimentary facies. As the geological formation generally consists of many diferent lithologies, the lithology prediction is always viewed as a tough work by geologists. Probabilistic neural network (PNN) shows high efciency when solving pattern recognition problem since learning data do not need to do any pre-training of learning data and calculation results are universally reliable, and then, this model could be considered as an efective solution. However, there are two factors that seriously limit the PNN’s performance: One is existence of the interference variables of learning samples, and the other is selection of the window length of probability density distribution. In view of adverse impact of those two factors, two techniques, mean impact value (MIV) and particle swarm optimization (PSO), are introduced to improve the PNN’s calculation capability. Thus, a new prediction method referred as MIV–PSO–PNN is proposed in this paper. The proposed method is validated by three well-designed experiments, and the corresponding experiment data are recorded by two cored wells of the LULA oilfeld. For the three experiments, prediction accuracies of the results provided by the proposed method are 81.67%, 73.34% and 88.34%, respectively, all of which are higher than those provided by other comparative approaches including backpropagation (BP), PNN, and MIV-PNN. The experiment results strongly demonstrate that the proposed method is capable to predict complex lithology.

Słowa kluczowe

backpropagation probabilistic neural network particle swarm optimization lacustrine carbonate formation complex lithology prediction mean impact value

propagacja wsteczna probabilistyczna sieć neuronowa optymalizacja roju cząstek

Wydawca

Instytut Geofizyki PAN
Springer

Czasopismo

Acta Geophysica

Rocznik

2020

Tom

Vol. 68, no. 6

Strony

1727--1752

Opis fizyczny

Bibliogr. 75 poz.

Twórcy

autor

Gu Yufeng

aaaaa3388@126.com

Strategic Research Center of Oil and Gas Resources, Ministry of Natural Resources, Beijing, China

autor

Zhang Zhongmin

Sinopec Exploration & Production Research Institute, Beijing, China

autor

Zhang Demin

Sinopec Exploration & Production Research Institute, Beijing, China

autor

Zhu Yixuan

Sinopec Exploration & Production Research Institute, Beijing, China

autor

Bao Zhidong

College of Geosciences, China University of Petroleum (Beijing), Beijing, China

autor

Zhang Daoyong

Strategic Research Center of Oil and Gas Resources, Ministry of Natural Resources, Beijing, China

Bibliografia

1. Ahila R, Sadasivam V, Manimala K (2012) Particle swarm optimization-based feature selection and parameter optimization for power system disturbances classification. Appl Artif Intell 26(9):832–861
2. Akhmanov GG, Silva IP, Erba E, Cita MB (2003) Sedimentary succession and evolution of the Mediterranean Ridge western sector as derived from lithology of mud breccia clasts. Mar Geol 195(1–4):277–299
3. Alves TM, Fetter M, Lima C, Cartwright JA, Cosgrove J, Gangá A (2017) An incomplete correlation between pre-salt topography, top reservoir erosion, and salt deformation in deep-water Santos Basin (SE Brazil). Mar Pet Geol 79:300–320
4. Andrew AM (2001) Backpropagation. Kybernetes 30(9–10):85–104
5. Andrioni M, Lima JAM, Guerra LA, Ribeiro EO, Nunes LMP, Ceccopieri W (2012) Ocean eddies’ influence on Lula field, Santos Basin, Brazil. In: ASME 2012, international conference on ocean, offshore and arctic engineering
6. Barrow J (2009) Lithology identification and prediction through amplitude variation with offset analysis in an area of the Malay basin, gulf of Thailand/Jerreh barrow. J Braz Chem Soc 20:57–63
7. Bogdanov YA, Gorbunova ZN, Serova VV (1998) Lithology and mineralogy of bottom sediments from the Bear island area, Norwegian sea. Oceanology 38(4):542–547
8. Bosch D, Ledo J, Queralt P (2013) Fuzzy logic determination of lithologies from well log data: application to the KTB project data set (Germany). Surv Geophys 34(4):413–439
9. Boyd A, Souza A, Carneiro G, Machado V, Trevizan W, Coutinho B, Netto P, Polinski R, Bertolini A (2015) Pre-salt carbonate evaluation for Santos Basin, offshore Brazil. Petrophysics 56(6):577–591
10. Broomhead DS, Lowe D (1988) Radial basis functions, multi-variable functional interpolation and adaptive networks. Adv Neural Inf Process Syst 4148:728–734
11. Chen CH, Chu CT (2009) High performance iris recognition based on 1-D circular feature extraction and PSO-PNN classifier. Expert Syst Appl 36(7):10351–10356
12. Chen N, Sun F, Ding L, Wang H (2009) An adaptive PNN-DS approach to classification using multi-sensor information fusion. Neural Comput Appl 18(5):455–467
13. Chetelat B, Liu CQ, Wang Q, Zhang G (2013) Assessing the influence of lithology on weathering indices of Changjiang river sediments. Chem Geol 359(6):108–115
14. Chi MV, Wong PK, Wong KI (2014) Simultaneous-fault detection based on qualitative symptom descriptions for automotive engine diagnosis. Appl Soft Comput 22(5):238–248
15. Cobbold PR, Meisling KE, Mount VS (2001) Reactivation of an obliquely rifted margin, Campos and Santos Basins, southeastern Brazil. AAPG Bull 85(11):1925–1944
16. D’Afonseca L, Lecerf D, Souza A, Sanchez F, Prigent H, Vidal T (2013) Multi-azimuth imaging for deep-water pre-salt reservoirs in Santos Basin, Brazil. In: EAGE conference and exhibition incorporating SPE EUROPEC
17. de Almeida JA (2010) Stochastic simulation methods for characterization of lithoclasses in carbonate reservoirs. Earth Sci Rev 101(3–4):250–270
18. Dev VA, Eden MR (2019) Formation lithology classification using scalable gradient boosted decision trees. Comput Chem Eng 128:392–404
19. Djafarov IS, Khafizov SF, Syngaevsky PE (2004) NMR application in reservoirs with complex lithology: a case study. Petrophysics 45(2):119–129
20. Duarte CSL, Viana AR (2007) Santos drift system: stratigraphic organization and implications for late Cenozoic palaeocirculation in the Santos Basin, SW Atlantic Ocean. Miner Pediatr 276(1):171–198
21. Eberhart R, Shi Y (2001) Particle swarm optimization: developments, applications and resources. In: Proceedings of 2001 IEEE congress on evolutionary computation, vol 1, pp 81–86
22. Freire EB, Lykawka R, Gabaglia GPR, Rodrigues EB, Terra GJS (2011) Searching for potential Analogues for the pre-salt Santos Basin, Brazil: high-resolution stratigraphic studies of microbialite-bearing successions from Salta Basin, Argentina. In: AAPG international conference and exhibition
23. Goldszmidt R, Moises M (1997) Bayesian network classifiers. Machine Learning 29(2–3):131–163
24. 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
25. Guo Y, Ma H, Ba J, Yu H, Long C (2015) Impact of data distribution on fluid sensitivity analysis: a quantitative investigation. J Appl Geophys 119:1–15
26. Huc AY (2004) Petroleum in the south Atlantic. Oil Gas Sci Technol 59(59):243–253
27. Inaba T, Suzuki N, Hirai A, Sekiguchi K, Watanabe T (2001) Source rock lithology prediction based on oil diacholestane abundance in the siliceous-clastic Akita sedimentary basin, Japan. Organ Geochem 32(7):877–890
28. Jacobson LA (1988) Macroscopic thermal neutron capture cross section measurements. IEEE Trans Nucl Sci 35(1):817–821
29. Jacobson LA, Wyatt DF (1993) Elemental yields and complex lithology analysis from the pulsed spectral gamma log. SPWLA Annu Log Symp 37(1):50–61
30. Jain AK, Dubes RC (1988) Algorithms for clustering data. Technometrics 32(2):227–229
31. Kakouei A, Masihi M, Sola BS, Biniaz E (2014) Lithological facies identification in Iranian largest gas field: a comparative study of neural network methods. J Geol Soc India 84(3):326–334
32. Kennedy J, Eberhart R (1995) Particle swarm optimization. In: Proceedings of IEEE international conference on neural networks, vol 4, pp 1942–1948
33. Kominz MA, Patterson K, Odette D (2011) Lithology dependence of porosity in slope and deep marine sediments. J Sediment Res 81(9–10):730–742
34. Kou Y, Shi YM, Boren LI, Qin XS (2010) The complex lithology rock-electricity features of volcanic rocks in Kelameili gas field. Acta Petrol Sin 26(1):291–301
35. Lentini MR, Fraser SI, Sumner HS, Davies RJ (2010) Geodynamics of the central south Atlantic conjugate margins: implications for hydrocarbon potential. Petrol Geosci 16(3):217–229
36. Ma YZ (2011) Lithofacies clustering using principal component analysis and neural network: applications to wireline logs. Math Geosci 43(4):401–419
37. Malik RF, Rahman TA, Hashim SZM, Ngah R (2007) New particle swarm optimizer with sigmoid increasing inertia weight. Int J Comput Sci Secur 1(2):43–52
38. Michelon D, Marques E, Figueiredo J, Ferraz H, Barros P (2013) Santonian-Campanian channelized systems of the Santos Basin, Brazil: stratigraphic framework and reservoir potential. In: GCSSEPM proceedings, pp 381–396
39. Mirzaei-Paiaman A, Saboorian-Jooybari H (2016) A method based on spontaneous imbibition for characterization of pore structure: application in pre-SCAL sample selection and rock typing. J Nat Gas Sci Eng 35(A):814–825
40. Mirzaei-Paiaman A, Salavati S (2012) The application of artificial neural networks for the prediction of oil production flow rate. Energy Sources A Recov Util Environ Eff 34(19):1834–1843
41. Mirzaei-Paiaman A, Saboorian-Jooybari H, Pourafshary P (2015) Improved method to identify hydraulic flow units for reservoir characterization. Energy Technol 3(7):726–733
42. Mirzaei-Paiaman A, Ostadhassan M, Rezaee R, Saboorian-Jooybari H, Chen Z (2018) A new approach in petrophysical rock typing. J Petrol Sci Eng 166:445–464
43. Mirzaei-Paiaman A, Sabbagh F, Ostadhassan M, Shafiei A, Rezaee R, Saboorian-Jooybari H (2019a) A further verification of FZI* and PSRTI: newly developed petrophysical rock typing indices. J Petrol Sci Eng 175:693–705
44. Mirzaei-Paiaman A, Saboorian-Jooybari H, Chen Z, Ostadhassan M (2019b) New technique of true effective mobility (TEM-Function) in dynamic rock typing: reduction of uncertainties in relative permeability data for reservoir simulation. J Petrol Sci Eng 179:210–227
45. Murata N, Yoshizawa S, Amari SI (1994) Network information criterion-determining the number of hidden units for an artificial neural network model. IEEE Trans Neural Netw 5(6):865–872
46. Nakano C, Pinto AC, Marcusso J, Minami K (2010) Pre-salt Santos Basin extended well test and production pilot in the Tupi area-the planning phase. J Petrol Technol 62(2):66–68
47. Paola JD, Schowengerdt RA (1993) A review and analysis of backpropagation neural networks for classification of remotely-sensed multi-spectral imagery. Int J Remote Sens 16(16):3033–3058
48. Parzen E (1962) On estimation of a probability density function and mode. Ann Math Stat 33(3):1065–1076
49. Pediwal J, Mahor A, Khatri N (2012) Exponential decreasing inertia weight particle swarm optimization in economic load dispatch. Int J Eng Innov Res 1(5):380–384
50. Porter CR, Pickett GR, Whitman WW (1969) A method of determining rock characteristics for computation of log data: the litho-porosity cross plot. Log Anal 6:16–24
51. Qi M, Fu Z, Chen F (2016) Research on a feature selection method based on median impact value for modeling in thermal power plants. Appl Therm Eng 94:472–477
52. Riedmiller M (1994) Advanced supervised learning in multi-layer perceptrons-from backpropagation to adaptive learning algorithms. Comput Stand Interfaces 16(3):265–278
53. Roberts HH, Sydow J, Bouma AH (1993) Seismic stratigraphy, sedimentology, and reservoir potential of a late Pleistocene shelf-edge delta. AAPG Bull 77(9):1598–1599
54. Rosenfeld, J.H., Hood, J.F., 2006. Play potential in the deepwater Santos Basin, Brazil. Offshore, 66(9)
55. Sahoo S, Jha MK (2016) Pattern recognition in lithology classification: modeling using neural networks, self-organizing maps and genetic algorithms. Hydrogeol J 25(2):311–330
56. Shaw L, Bagha S (2012) Online EMG signal analysis for diagnosis of neuromuscular diseases by using PCA and PNN. Int J Eng Sci Technol 4(10):4453–4459
57. Shi Y, Eberhart R (1998) A modified particle swarm optimizer. In: Proceedings of 1998 IEEE international conference on evolutionary computation, pp 69–73
58. Shi Y, Eberhart R (1999) Empirical study of particle swarm optimization. In: Proceedings of 1999 IEEE congress on evolutionary computation, pp 1945–1950
59. Smyth GK, Speed T (2003) Normalization of cDNA microarray data. Methods 31(4):265–273
60. Specht DF (1990) Probabilistic neural networks. Neural Netw 3(1):109–118
61. Stanton N, Ponte-Neto C, Bijani R, Masini E, Fontes S, Flexor JM (2014) A geophysical view of the southeastern Brazilian margin at Santos Basin: insights into rifting evolution. J S Am Earth Sci 55(2):141–154
62. Sun J, Li Q, Chen M, Ren L, Huang G, Li C, Zhang Z (2019) Optimization of models for a rapid identification of lithology while drilling: a win-win strategy based on machine learning. J Petrol Sci Eng 176:321–341
63. Thompson DL, Stilwell JD, Hall M (2015) Lacustrine carbonate reservoirs from early cretaceous rift lakes of western Gondwana: pre-salt coquinas of brazil and west Africa. Gondwana Res 28(1):26–51
64. Trelea IC (2003) The particle swarm optimization algorithm: convergence analysis and parameter selection. Inf Process Lett 85(6):317–325
65. Wang X, Wu C, Guo Y, Meng Q, Zhang Y, Tao Y (2013) Accumulation feature of Lula oilfield and its exploratory implication for pre-salt reservoirs in Santos Basin, Brazil. China Pet Explor 18(3):61–69
66. Wertheim PH (2008) Pre-salt discoveries continue in Brazil. Offshore 68(7)
67. Wertheim PH (2009) Tupi extended well test sheds light on Brazil’s subsalt bonanza. Offshore 69(7)
68. Wong MLD, Nandi AK (2004) Automatic digital modulation recognition using artificial neural network and genetic algorithm. Signal Process 84(2):351–365
69. Wu C (2015) Petroleum geology characteristics and exploration targets of pre-salt formations in Santos Basin, Brazil. Petrol Geol Exp 37(1):1–5
70. Xie Y, Zhu C, Zhou W, Li Z, Liu X, Tu M (2018) Evaluation of machine learning methods for formation lithology identification: a comparison of tuning processes and model performances. J Petrol Sci Eng 160:182–193
71. Yong-Yan LU, Wang WG (2011) Variable selection of financial distress prediction-the SVM method based on mean impact value. Syst Eng 29(8):73–78
72. Zhang S (2008) Application of probabilistic neural network technique to lithology inversion of heterogeneous stratum. Acta Petrol Sin 29(4):549–552
73. Zhang DX, Chen YT, Meng J (2018) Synthetic well logs generation via recurrent neural networks. Pet Explor Dev 45(4):629–639
74. Zhu LQ, Zhang C, Zhang CM, Wei Y, Zhou XQ, Cheng Y, Huang YY, Zhang L (2018) Prediction of total organic carbon content in shale reservoir based on a new integrated hybrid neural network and conventional well logging curves. J Geophys Eng 15:1050–1061
75. Zhu LQ, Zhang C, Zhang CM, Zhang ZS, Zhou XQ, Liu WN, Zhu BY (2020) A new and reliable dual model- and data-driven TOC prediction concept: a TOC logging evaluation method using multiple overlapping methods integrated with semi-supervised deep learning. J Petrol Sci Eng 188:106944

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-6225f23f-5bca-4699-a62b-986f65763fe4