Auto recognition of carbonate microfacies based on an improved back propagation neural network

Abstract

Though traditional methods could recognize some facies, e.g. lagoon facies, backshoal facies and foreshoal facies, they couldn’t recognize reef facies and shoal facies well. To solve this problem, back propagation neural network (BP-ANN) and an improved BP-ANN with better stability and suitability, optimized by a particle swarm optimizer (PSO) algorithm (PSO-BP-ANN) were proposed to solve the microfacies’ auto discrimination of M formation from the R oil field in Iraq. Fourteen wells with complete core, borehole and log data were chosen as the standard wells and 120 microfacies samples were inferred from these 14 wells. Besides, the average value of gamma, neutron and density logs as well as the sum of squares of deviations of gamma were extracted as key parameters to build log facies (facies from log measurements)—microfacies transforming model. The total 120 log facies samples were divided into 12 kinds of log facies and 6 kinds of microfacies, e.g. lagoon bioclasts micrite limestone microfacies, shoal bioclasts grainstone microfacies, backshoal bioclasts packstone microfacies, foreshoal bioclasts micrite limestone microfacies, shallow continental micrite limestone microfacies and reef limestone microfacies. Furthermore, 68 samples of these 120 log facies samples were chosen as training samples and another 52 samples were gotten as testing samples to test the predicting ability of the discrimination template. Compared with conventional methods, like Bayes stepwise discrimination, both the BP-ANN and PSO-BP-ANN can integrate more log details with a correct rate higher than 85%. Furthermore, PSO-BP-ANN has more simple structure, smaller amount of weight and threshold and less iteration time.

Keywords

carbonate microfacies / quantitative recognition / bayes stepwise discrimination / backward propagation / neural network / particle swarm optimizer

References

[1] BhattA, HelleH B. Determination of facies from well logs using modular neural networks [J]. Petroleum Geoscience, 2002, 8: 217-228

[2] HalboutyM TGiant oil and gas fields of the 1990s: An introduction [C], 2003TulsaAAPG1-13

[3] AqrawiA A M, ThehniG A, SherwaniG H, KareemB M A. Mid-Cretaceous rudist-bearing carbonates of the M Formation: An important reservoir sequence in the Mesopotamian basin, Iraq [J]. Journal of Petroleum Geology, 1998, 21(1): 57-82

[4] HaykinSNeural networks: A comprehensive foundation [M], 1999LondonPrentice Hall20-25

[5] WolffM, Pelissier-CombescureJFACIOLOG: Automatic electrofacies determination [C], 19826-9

[6] SerraOFundamentals of well-log interpretation: Developments in petroleum science [M], 1986New YorkElsevier354-356

[7] DelfinerP, PeyretO, SerraO. Automatic determination of lithology from well logs [J]. SPE Formation Evaluation, 1987, 2: 303-310

[8] BushJ M, FortneyW G, BerryL N. Determination of lithology from well logs by statistical analysis [J]. SPE Formation Evaluation, 1987, 2: 412-418

[9] DudaR O, HartP EPattern classification and scene analysis [M], 1973OxfordJohn Wiley & Sons482

[10] GrimmE C. CONISS: A FORTRAN 77 program for stratigraphically constrained cluster analysis by the method of incremental sum of squares [J]. Computers & Geoscience, 1987, 13: 13-35

[11] FangJ H, ChenH C, ShultzA W, ShultzA W, MahmoundW. Computer-aided well correlation [J]. AAPG Bulletin, 1992, 76: 307-317

[12] GillD, ShamronyA, FligelmanH. Numerical zonation of log suites and log facies recognition by multivariate clustering [J]. AAPG Bulletin, 1993, 77: 1781-1791

[13] WerbosP JBeyond regression: New tools for prediction and analysis in the behavioral sciences [D], 1975Cambridge, MAHarvard University

[14] LiY, TianY-t, ChenY-tMulti-pattern recognition of sEMG based on improved BP neural network algorithm [C], 20102867-2872

[15] ChenH-r, WangS-l, GaoZ-y, HuY-qArtificial neural network approach for quantifying climate change and human activities impacts on shallow groundwater level-A case study of wuqiao in north China plain [C], 2010

[16] IraniR, NasimiR. An evolving neural network using an ant colony algorithm for a permeability estimation of the reservoir [J]. Petroleum Science and Technology, 2012, 30(4): 375-384

[17] LiZ, LiR-w, ShangZ-h, WangH-y, ChenX-l, MoC-lApplication of BP neural network to sale forecast for H company [C], 2012304-307

[18] DezfoolianM A. Body wave velocities estimation from wireline log data utilizing an artificial neural network for a carbonate reservoir, South Iran [J]. Petroleum Science and Technology, 2013, 31(1): 32-43

[19] RenC, AnN, WangJ-z, LiL, HuB, ShangD. Optimal parameters selection for BP neural network based on particle swarm optimization: A case study of wind speed forecasting [J]. Knowledge Based Systems, 2014, 56: 226-239

[20] SamliR, SivriN, SevgenS, KiremitciV Z. Applying artificial neural networks for the estimation of chlorophyll-a concentrations along the Istanbul Coast [J]. Polish Journal of Environmental Studies, 2014, 23(4): 1281-1287

[21] RogersS J, FangJ H, KarrC L, StanleyD A. Determination of lithology from well logs using a neural network [J]. AAPG Bulletin, 1992, 76: 731-739

[22] WongP M, JianF X, TaggartI J. A critical comparison of neural networks and discriminant analysis in lithofacies, porosity and permeability predictions [J]. Journal of Petroleum Geology, 1995, 18: 191-206

[23] SaggafM M, NebrijaE L. Estimation of lithologies and depositional facies from wire-line logs [J]. AAPG Bulletin, 2000, 84: 1633-1646

[24] KohonenTSelf-organization and associate memory [M], 1989BerlinSpringer-Verlag4-7

[25] HaganM T, DemuthH B, BealeMNeural network design [M], 1996BostonPWS Publishing Co.346-370

[26] WhiteHArtificial Neural Networks: Approximation and learning theory [M], 1992OxfordBasil Blackwell235-270

[27] GoldbergD EGenetic Algorithms in Search, Optimization, and Machine Learning [M], 1989New JerseyAddison-Wesley125-137

[28] FogelL JEvolutionary programming in perspective: the top-down view, in Computational Intelligence: Imitating [M], 1994Piscataway, NJIEEE Press240-267

[29] RechenbergIEvolution strategy, in Computational Intelligence: Imitating Life [M], 1994Piscataway, NJIEEE Press126-178

[30] KozaJ RGenetic Programming: On the programming of computers by means of natural selection [M], 1992Cambridge, MAMIT Press221-256

[31] KennedyJ, EberhartR CParticle swarm optimization [C], 19951942-1948

[32] EberhartR C, DobbinsR W, SimpsonP KComputational Intelligence PC Tools [M], 1996BostonAcademic Press147-201

[33] EberhartR C, KennedyJA new optimizer using particle swarm theory [C], 1995Piscataway, NJIEEE Service Center39-43

[34] KennedyJThe particle swarm: social adaptation of knowledge [C], 1997303-308

[35] ShiY, EberhartR CA modified particle swarm optimizer [C], 199869-73

[36] ClercM, KennedyJ. The particle swarm-Explosion, stability, and convergence in a multidimensional complex space [J]. IEEE Transactions on Evolutionary Computation, 2002, 6: 58-73

[37] EberhartR C, ShiYComparing inertia weights and constriction factors in particle swarm optimization [C], 200084-88

[38] CarlisleA, DozierGAn off-the-shelf PSO [C], 20011-6

[39] POLI R. Analysis of the publications on the applications of particle swarm optimization [J]. Journal of Artificial Evolution and Applications, 2008(2008): 68–175.

[40] ShawR, SrivastavaS. Particle swarm optimization: A new tool to invert geophysical data [J]. Geophysics, 2007, 72: 75-83

[41] Fernández-MartínezJ L, García-GonzaloE, Fernández-ÁlvarezJ P, Menéndez-PérezC O, KuzmaH AParticle swarm optimization (PSO): A simple and powerful algorithm family for geophysical inversion [C], 2008, 27: 3568-3571

[42] NaudetV, FernÁNdez-MartÍNezJ L, GarcÍA-GonzaloE, FernÁNdez-ÁLvarezJ PEstimation of water table from self-potential data using particle swarm optimization (PSO) [C], 2008, 27: 1203-1207

[43] FernÁNdez-MartÍNezJ L, GarcÍA-GonzaloE. The PSO family: Deduction, stochastic analysis and comparison [J]. Swarm Intelligence, 2009, 3: 245-273

[44] FernÁNdez-MartÍNezJ L, GarcÍA-GonzaloE, FernÁNdez-ÁLvarezJ P, KuzmaH A, MenÉNdez-PÉRezC O. PSO: A powerful algorithm to solve geophysical inverse problems: Application to a 1D-DC resistivity case [J]. Journal of Applied Geophysics, 2010, 71: 13-25

[45] FernÁNdez-MartÍNezJ L, GarcÍA-GonzaloE, NaudetV. Particle swarm optimization applied to solving and appraisal the streaming potential inverse problem [J]. Geophysics, 2010, 75: 3-15

[46] FernÁNdez-MartÍNezJ L, GarcÍA-GonzaloE, FernÁNdez-MuÑIzZ, MariethozG, MukerjiT. Posterior sampling using particle swarm optimizers and model reduction techniques [J]. International Journal of Applied Evolutionary Computation, 2010, 71(1): 27-48

[47] SaraswatP, SenM KSimultaneous stochastic inversion of prestack seismic data using hybrid evolutionary algorithm [C], 2010, 29: 2850-2854

[48] OnwunaluJ E, DurlofskyL J. Application of a particle swarm optimization algorithm for determining optimum well location and type [J]. Computational Geosciences, 2010, 14: 183-198

[49] SerraO, DelfinerP, LevertJ CLithology determination from well logs: Case studies [C], 198517-20

[50] WangY-x, TianC-b, GaoJ-x, ZhangX-f, LiuJ-q, TianZ-p, SongX-m, Liub. A quantitative explanation of carbonate microfacies based on conventional logging data: a case study of the Mishrif Formation in north Rumaila oil field of Iraq [J]. Acta Petrolei Sinica, 2013, 34(1): 1088-1099

[51] PoultonM MComputational neural networks for geophysical data processing [M], 2001AmsterdamPergamon Publishers187-215