Application of Multiboost-KELM algorithm to alleviate the collinearity of log curves for evaluating the abundance of organic matter in marine mud shale reservoirs: a case study in Sichuan Basin, China

Zhu, L.; Zhang, C.; Zhang, C.; Zhou, X.; Wang, J.; Wang, X.

doi:10.1007/s11600-018-0180-8

Artykuł - szczegóły

Tytuł artykułu

Application of Multiboost-KELM algorithm to alleviate the collinearity of log curves for evaluating the abundance of organic matter in marine mud shale reservoirs: a case study in Sichuan Basin, China

Autorzy

Zhu L. , Zhang C. , Zhang C. , Zhou X. , Wang J. , Wang X.

Wybrane pełne teksty z tego czasopisma

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

Identyfikatory

DOI

10.1007/s11600-018-0180-8

Warianty tytułu

Języki publikacji

Abstrakty

The total organic carbon (TOC) content reflects the abundance of organic matter in marine mud shale reservoirs and reveals the hydrocarbon potential of the reservoir. Traditional TOC calculation methods based on statistical and machine learning have limited effect in improving the computational accuracy of marine mud shale reservoirs. In this study, the collinearity between log curves of marine mud shale reservoirs was revealed for the first time, which was found to be adverse to the improvement of TOC calculation accuracy. To this end, a new TOC prediction method was proposed based on Multiboost-Kernel extreme learning machine (Multiboost-KELM) bridging geostatistics and machine learning technique. The proposed method not only has good data mining ability, generalization ability and sound adaptivity to small samples, but also has the ability to improve the computational accuracy by reducing the effect of collinearity between logging curves. In prediction of two mud shale reservoirs of Sichuan basin with proposed model, the results showed that the predicted value of TOC was in good consistence with the measured value. The root-mean-square error of TOC predicting results was reduced from 0.415 (back-propagation neural networks) to 0.203 and 1.117 (back-propagation neural networks) to 0.357, respectively; the relative error value decreased by up to 8.9%. The Multiboost-KELM algorithm proposed in this paper can effectively improve the prediction accuracy of TOC in marine mud shale reservoir.

Słowa kluczowe

total organic carbon collinearity abundance organic matter Multiboost-KELM marine mud shale

całkowity węgiel organiczny kolinearność Multiboost-KELM obfitość materia organiczna

Wydawca

Instytut Geofizyki PAN
Springer

Czasopismo

Acta Geophysica

Rocznik

2018

Tom

Vol. 66, no. 5

Strony

983--1000

Opis fizyczny

Bibliogr. 53 poz.

Twórcy

autor

Zhu L.

Key Laboratory of Exploration Technologies for Oil and Gas Resources Yangtze University Wuhan People’s Republic of China
Hubei Cooperative Innovation Center of Unconventional Oil and Gas Wuhan People’s Republic of China

autor

Zhang C.

yzlogging@163.com

Key Laboratory of Exploration Technologies for Oil and Gas Resources Yangtze University Wuhan People’s Republic of China
Hubei Cooperative Innovation Center of Unconventional Oil and Gas Wuhan People’s Republic of China

autor

Zhang C.

Key Laboratory of Exploration Technologies for Oil and Gas Resources Yangtze University Wuhan People’s Republic of China
Hubei Cooperative Innovation Center of Unconventional Oil and Gas Wuhan People’s Republic of China

autor

Zhou X.

Key Laboratory of Exploration Technologies for Oil and Gas Resources Yangtze University Wuhan People’s Republic of China
Hubei Cooperative Innovation Center of Unconventional Oil and Gas Wuhan People’s Republic of China

autor

Wang J.

Key Laboratory of Exploration Technologies for Oil and Gas Resources Yangtze University Wuhan People’s Republic of China
Hubei Cooperative Innovation Center of Unconventional Oil and Gas Wuhan People’s Republic of China

autor

Wang X.

Key Laboratory of Exploration Technologies for Oil and Gas Resources Yangtze University Wuhan People’s Republic of China
Hubei Cooperative Innovation Center of Unconventional Oil and Gas Wuhan People’s Republic of China

Bibliografia

1. Anifowose FA, Labadin J, Abdulraheem A (2015) Ensemble model of non-linear feature selection-based extreme learning machine for improved natural gas reservoir characterization. J Nat Gas Sci Eng 26:1561–1572
2. Benbouzid D, Casagrande N (2012) Multiboost: a multi-purpose boosting package. J Mach Learn Res 13(1):549–553
3. Billings SA, Voon WSF (1985) A prediction-error and stepwise-regression estimation algorithm for non-linear systems. Int J Control 44(3):803–822
4. Breiman L (1996) Bagging predictors. Mach Learn 24(2):123–140
5. Chen YY, Wang ZB, Wang ZB (2017) Novel variable selection method based on uninformative variable elimination and ridge extreme learning machine: CO gas concentration retrieval trial. Spectrosc Spectr Anal 37(1):299–305
6. Craney TA, Surles JG (2002) Model-dependent variance inflation factor cutoff values. Qual Eng 14(3):391–403
7. Dong DZ, Zou CN, Yang H, Wang YM, Li XJ, Chen GS, Wang SQ, Lü ZG, Huang YB (2012) Progress and prospects of mud shale exploration and development in china. Shiyou Xuebao 33(s1):107–114
8. Du JM, Zhang XL, Zheng X, Zhang ZJ, Zhong GR, Guo L (2016) The applicability of well logs prediction models of organic carbon content in source rocks of the tight oil: a case of the source rocks of lower section of N1 formation in Qaidm Basin. Xibei Daxue Xuebao, Ziran Kexueban 46(2):239–245
9. Efron B, Gong G (1983) A leisurely look at the bootstrap, the jackknife, and cross-validation. Am Stat 37(1):36–48
10. Farrar DE, Glauber RR (1967) Multicollinearity in regression analysis: the problem revisited. Rev Econ Stat 49(1):92–107
11. Ge XM, Fan YR, Cao YC, Li JT, Cai JC, Liu JY, Wei SD (2016) Investigation of organic related pores in unconventional reservoir and its quantitative evaluation. Energy Fuels 30(6):4699–4709
12. Hashem S (1996) Effect of collinearity on combing neural networks. Connect Sci 4(3):315–336
13. He C, Su A, Zhang MZ, Wu YD, Ji LM (2016) Optimal selection and application of prediction means for organic carbon content of source rocks based on logging data in Yanchang Formation, Ordos Basin. Nat Gas Geosci 27(4):754–764
14. Hoerl AE, Kennard RW (1970) Ridge regression: applications to nonorthogonal problems. Technometrics 12(1):69–82
15. Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1):489–501
16. Huang GB, Zhou H, Ding X, Zhang R (2012) Extreme learning machine for regression and multiclass classification. IEEE Trans Syst Man Cybern B Cybern 42(2):513–529
17. Imasuen OI, Mordi C, Imarhiagbe OJ (2016) Organic richness and organic matter quality studies of source rocks in Imiegba and environs, Benin Flank, South-Western Anambra Basin, Nigeria. Scientia Afr 35(1):41–53
18. Jacobi DJ, Gladkikh M, Lecompte B, Hursan G, Mendez F, Longo J et al (2008) Integrated petrophysical evaluation of mud shale reservoirs. Soc Pet Eng SPE114925G
19. Jarvie DM, Hill RJ, Ruble TE, Pollastro RM (2007) Unconventional shale-gas systems: the mississippian barnett shale of north-central texas as one model for thermogenic shale-gas assessment. AAPG Bull 91(4):475–499
20. Jiang Y, Song Y, Lin QI, Lei C, Tao Y, Hui G, Chen L, Tao YZ, Gan H, Wu PJ, Ye ZY (2016) Fine lithofacies of china’s marine shale and its logging prediction:a case study of the lower silurian longmaxi marine shale in weiyuan area, southern sichuan basin, china. Earth Sci Front 23(1):107–118
21. Kadkhodaie-Ilkhchi A, Rahimpour-Bonab H, Rezaee M (2009) A committee machine with intelligent systems for estimation of total organic carbon content from petrophysical data: an example from kangan and dalan reservoirs in south pars gas field, Iran. Comput Geosci 35(3):459–474
22. Lee DS, Herman JD, Elsworth D, Kim HT, Lee HS (2011) A critical evaluation of unconventional gas recovery from the marcellus shale, northeastern united states. Ksce J Civ Eng 15(4):679
23. Lou JG, Jiang YL, Shen Q, Jiang JH (2013) Evaluating the prediction performance of different kernal functions in kernel based software reliability models. Chin J Comput 36(36):1303–1311
24. Lu J, Li J, Wu QZ, Jin WJ, Hao SB (2016) A study and an application on logging evaluation method of toc in shale oil and gas reservoir. Sci Technol Eng 16(6):143–147
25. Ma L, Kevin T, PatrickJ D, Loic C, Ali G, PeterD L (2017) Multi-scale 3D characterisation of porosity and organic matter in shales with variable TOC content and thermal maturity: examples from the Lublin and Baltic Basins, Poland and Lithuania. Int J Coal Geol 180(7):100–112
26. Mahmoud AAA, Elkatatny S, Mahmoud M, Omar M, Abdulraheem A, Ali A (2017) Determination of the total organic carbon (TOC) based on conventional well logs using artificial neural network. Int J Coal Geol 179:72–80
27. Meinhold G, Howard JP, Strogen D, Kaye MD, Abutarruma Y, Elgadry M, Thusu B, Whitham AG (2013) Hydrocarbon source rock potential and elemental composition of lower silurian subsurface shales of the eastern Murzuq Basin, Southern Libya. Mar Pet Geol 48:224–246
28. Ouadfeul SA, Aliouane L (2015) Total organic carbon prediction in mud shale reservoirs from well logs data using the multilayer perceptron neural network with Levenberg Marquardt training algorithm: application to Barnett shale. Arab J Sci Eng 40(11):3345–3349
29. Passey QR, Moretti FJ, Kulla JB, Creaney S, Stroud JD (1990) Practical model for organic richness from porosity and resistivity logs. AAPG Bull 74(12):1777–1794
30. Qian Z, Dong YH, Liu SM, Elsworth D, Zhao YX (2017) Shale pore characterization using NMR cryoporometry with octamethylcyclotetrasiloxane as the probe liquid. Energy Fuels 31(7):6951–6959
31. Rätsch G, Onoda T, Müller KR (2001) Soft margins for adaBoost. Mach Learn 42(3):287–320
32. Reed D, Mcgee D, Yano K, Hankin J (1985) Diet, blood pressure and multicollinearity. Nutr Prev Cardiovasc Dis 7(3 Pt 1):405
33. Schmoker JW, Hester TC (1983) Organic carbon in Bakken formation, United States portion of Williston Basin. Am Assoc Pet Geol Bull (United States) 67(12):2165–2174
34. Shi X, Wang J, Liu G, Yang L, Ge X, Jiang S (2016) Application of extreme learning machine neural networks in total organic carbon content prediction in organic shale with wire line logs. J Nat Gas Sci Eng 33:687–702
35. Supernaw IR, Arnold DM, Link AJ (1978) Method for in situ evaluation of the source rock potential of earth formations. US, US4071755
36. Tabatabaei SME, Kadkhodaie-Ilkhchi A, Hosseini Z, Moghaddam AA (2015) A hybrid stochastic-gradient optimization to estimating total organic carbon from petrophysical data: a case study from the Ahwaz oilfield, SW Iran. J Pet Sci Eng 127(1):35–43
37. Tan M, Liu Q, Zhang S (2013) A dynamic adaptive radial basis function approach for total organic carbon content prediction in organic shale. Geophysics 78(6):D445–D459
38. Tan M, Song X, Yang X, Wu Q (2015) Support-vector-regression machine technology for total organic carbon content prediction from wireline logs in organic shale: acomparative study. J Nat Gas Sci Eng 26(1):792–802
39. Tibshirani R (2011) Regression shrinkage and selection via the lasso: a retrospective. J R Stat Soc 73(3):1–28
40. Wang GT, Li P, Su CL (2011) Soft sensor modeling method of extreme learning machine ridge regression. J Hefei Univ Technol 34(8):1150–1154
41. Wang P, Ji YL, Pan RF, Wang ZZ, Wu Y (2013) A comprehensive evaluation methodology of shale brittleness: a case study from the Lower Silurian Longmaxi Fm in Block W, Sichuan Basin. Nat Gas Ind 33(12):48–53
42. Wang X, Yao J, Jiang ZY, Zhang Q, Zhang Z, Duan LY, Jia XX (2017) A new method of fast distance transform 3D image based on “neighborhood between voxels in space” theory. Sci China Press c62(15):c1662–c1669
43. Wheeler D, Tiefelsdorf M (2005) Multicollinearity and correlation among local regression coefficients in geographically weighted regression. J Geogr Syst 7(2):161–187
44. Xu S, Zhu Y (2010) Well logs response and prediction model of organic carbon content in source rock—a case study from the source rock of wenchang formation in the pearl mouth basin. Pet Geol Exp 32(3):289–290
45. Yan JP, Cai JG, Zhao MH, Zheng DS (2009) Advances in the study of source rock evaluation by geophysical logging and its significance in resource assessment. Prog Geophys 24(1):270–279
46. Yang YF, Wang CC, Yao J, Hu RR, Sun H, Zhao JL (2015) A new method for microscopic pore structure analysis in shale matrix. Earth Sci 41(6):1067–1073
47. Yu HY, Rezaee R, Wang ZL, Han TC, Zhang YH, Arif M, Johnson L (2017) A new method for toc estimation in tight mud shale reservoirs. Int J Coal Geol 179:269–277
48. Yuan C, Zhou CC, Song HU, Cheng XZ, Dou Y (2014) Summary on well logging evaluation method of total organic carbon content in formation. Prog Geophys 29(6):2831–2837
49. Zhang SC, Liang DG, Zhang DJ (2002) Evaluation criteria for paleozoic effective hydrocarbon source rocks. Pet Explor Dev 29(2):8–12
50. Zhao P, Mao Z, Huang Z, Zhang C (2016) A new method for estimating total organic carbon content from well logs. AAPG Bull 100(8):1311–1327
51. Zhao P, Ma H, Rasouli V, Liu W, Cai J, Huang Z (2017) An improved model for estimating the TOC in shale formations. Mar Pet Geol 83:174–183
52. Zhu LQ, Zhang C, Wei Y, Guo C, Zhou XQ, Chen YL (2017) The method for TOC content evaluation in shale resrevoirs based on improved rain forest fuzzy neural network model. Geol J China Univ 22(4):716–723
53. 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 Geo Eng 15(3):1050–1061

Typ dokumentu

Bibliografia

Identyfikator YADDA

bwmeta1.element.baztech-fcd425ce-3bdd-43c2-a35c-75bc2b320124