Ren Y, Gong R, Feng Z, et al. Valuable Data Extraction for Resistivity Imaging Logging Interpretation. Tsinghua Science and Technology, 2020, 25(2): 281-293. https://doi.org/10.26599/TST.2019.9010020
Imaging logging has become a popular means of well logging because it can visually represent the lithologic and structural characteristics of strata. The manual interpretation of imaging logging is affected by the limitations of the naked eye and experiential factors. As a result, manual interpretation accuracy is low. Therefore, it is highly useful to develop effective automatic imaging logging interpretation by machine learning. Resistivity imaging logging is the most widely used technology for imaging logging. In this paper, we propose an automatic extraction procedure for the geological features in resistivity imaging logging images. This procedure is based on machine learning and achieves good results in practical applications. Acknowledging that the existence of valueless data significantly affects the recognition effect, we propose three strategies for the identification of valueless data based on binary classification. We compare the effect of the three strategies both on an experimental dataset and in a production environment, and find that the merging method is the best performing of the three strategies. It effectively identifies the valueless data in the well logging images, thus significantly improving the automatic recognition effect of geological features in resistivity logging images.
Institute of Computer Application Technology, PetroChina Research Institute of Petroleum Exploration and Development (RIPED), Beijing100083, China.
Department of Well Logging & Remote Sensing Technology of RIPED, Beijing100083, China.
Abstract
Imaging logging has become a popular means of well logging because it can visually represent the lithologic and structural characteristics of strata. The manual interpretation of imaging logging is affected by the limitations of the naked eye and experiential factors. As a result, manual interpretation accuracy is low. Therefore, it is highly useful to develop effective automatic imaging logging interpretation by machine learning. Resistivity imaging logging is the most widely used technology for imaging logging. In this paper, we propose an automatic extraction procedure for the geological features in resistivity imaging logging images. This procedure is based on machine learning and achieves good results in practical applications. Acknowledging that the existence of valueless data significantly affects the recognition effect, we propose three strategies for the identification of valueless data based on binary classification. We compare the effect of the three strategies both on an experimental dataset and in a production environment, and find that the merging method is the best performing of the three strategies. It effectively identifies the valueless data in the well logging images, thus significantly improving the automatic recognition effect of geological features in resistivity logging images.
H. Li and H. Wang, Investigation of eccentricity effects and depth of investigation of azimuthal resistivity LWD tools using 3D finite difference method, Journal of Petroleum Science and Engineering, vol. 143, no. 9, pp. 211–225, 2016.
H. Wang and M. C. Fehler, The wavefield of acoustic logging in a cased hole with a single casing — part II: A dipole tool, Geophysical Journal International, vol. 212, no. 2, pp. 1412–1428, 2018.
H. Wang and M. C. Fehler, The wavefield of acoustic logging in a cased-hole with a single casing — part I: A monopole tool, Geophysical Journal International, vol. 212, no. 1, pp. 612–626, 2018.
H. Wang, T. Guo, and X. F. Shang, Understanding acoustic methods for cement bond logging, The Journal of the Acoustical Society of America, vol. 139, no. 5, pp. 2407–2416, 2016.
S. D. Russell, M. Akbar, B. Vissapragada, and G. M. Walkden, Rock types and permeability prediction from dipmeter and image logs; Shuaiba Reservoir (Aptian), Abu Dhabi, AAPG Bulletin, vol. 86, no. 10, pp. 1709–1732, 2002.
ChitaleD. V., Borehole imaging in reservoir characterization: Implementation of a standard interpretation workflow for the clastic and carbonate reservoirs, in Proc. 2005 IEEE Int. Conf. the 46th Annual Symposium of the SPWLA, New Orleans, LA, USA, 2005, pp. 1–43.
[7]
O. Faivre and G. Catala, Dip estimation from azimuthal Laterolog tools, in Proc. 1995 IEEE Int. Conf. SPWLA 36th Annual Logging Symposium, Paris, France, 1995, pp. 1–10.
[8]
J. Prilliman, C. Bean, M. Hashem, T. Bratton, M. A. Fredette, and J. R. Lovell, A comparison of wireline and LWD resistivity images in the Gulf of Mexico, in Proc. 1997 IEEE Int. Conf. 38th SPWLA Annual Logging Symposium, Houston, TX, USA, 1997, pp. 1–11.
[9]
NurmiR., ChararaM., WaterhouseM., and ParkR., Heterogeneities in carbonate reservoirs: Detection and analysis using borehole electrical imagery (in geological applications of wireline logs), Geological Society Special Publications, vol. 48, no. 1, pp. 95–111, 1990.10.1144/GSL.SP.1990.048.01.09
D. Moos, P. Peska, T. Finkbeiner, and M. Zoback, Comprehensive wellbore stability analysis utilizing quantitative risk assessment, Journal of Petroleum Science and Engineering, vol. 38, nos. 3&4, pp. 97–109, 2003.
P. A. Pezard and S. M. Luthi, Borehole electrical images in the basement of the cajon pass scientific drillhole, California; fracture identification and tectonic implications, Geophysical Research Letters, vol. 15, no. 9, pp. 1017–1020, 1988.
H. Q. Gao, H. F. Wang, Z. Feng, M. X. Fu, C. N. Ma, H. X. Pan, B. S. Xu, and N. Li, A novel texture extraction method for the sedimentary structures’ classification of petroleum imaging logging, in Proc. 2016 IEEE Int. Conf. on Pattern Recognition, Chengdu, China, 2016, pp. 161–172.
H. Chai, N. Li, X. L. Liu, D. L. Li, C. Z. Wang, D. C. Wu, and C. Xiao, Automatic discrimination of sedimentary facies and lithologies in reef-bank reservoirs using borehole image logs, Applied Geophysics, vol. 6, no. 1, pp. 17–29, 2009.
H. F. Wang, Y. T. Wang, and H. Chai, State-of-the-art on texture-based well logging image classification, (in Chinese), Journal of Computer Research and Development, vol. 50, no. 6, pp. 1335–1348, 2013.
Y. Q. Yang, W. P. Cui, and X. Zhang, A new method to detect formation occurrence from image recognition of electric imaging logging, (in Chinese), Petroleum Geophysics, vol. 56, no. 2, pp. 302–308, 2017.
S. Z. Ke, Full 3-D numerical modeling of borehole electric image logging and the evaluation model of fracture, Science in China Series D: Earth Sciences, vol. 51, pp. 170–173, 2008.
C. Barton, D. Moos, and K. Tezuka, Geomechanical wellbore imaging: Implications for reservoir fracture permeability, AAPG Bulletin, vol. 93, no. 11, pp. 1551–1569, 2009.
B. M. Newberry, L. M. Grace, and D. O. Stief, Analysis of carbonate dual porosity systems from borehole electrical images, in Proc. 1996 IEEE Int. Conf. on Permian Basin Oil and Gas Recovery Conference, Midland, TX, USA, 1996, pp. 1–7.
T. Li, S. H. Zhu, and M. Ogihara, Using discriminant analysis for multi-class classification: An experimental investigation, Knowledge and Information Systems, vol. 10, no. 4, pp. 453–472, 2006.
K. S. Goh, E. Y. Chang, and B. Li, Using one-class and two-class SVMs for multiclass image annotation, Journals & Magazines, vol. 17, no. 10, pp. 1333–1346, 2005.
T. G. Dietterich and G. Bakiri, Solving multiclass learning problems via error-correcting output codes, Journal of Artificial Intelligence Research, vol. 2, no. 1, pp. 263–286, 1995.
E. B. Kong and T. G. Dietterich, Error-correcting output coding corrects bias and variance, in Proc. 1995 IEEE Int. Conf. on the 12th Machine Learning, Tahoe City, CA, USA, 1995, pp. 313–321.
M. M. Breunig, H. P. Kriegel, R. T. Ng, and J. Sander, OPTICS-OF: Identifying local outliers, in Proc. 1999 IEEE Int. Conf. on the Third European Conference on Principles of Data Mining and Knowledge Discovery, Prague, Czech Republic, 1999, pp. 262–270.
M. M. Breunig, H. P. Kriegel, T. N. Raymond, and J. Sander, LOF: Identifying density-based local outliers, in Proc. 2000 IEEE ACM SIGMOD International Conference on Management of Data, Dallas, TX, USA, 2000, pp. 93–104.
C. Li and W. H. Wong, Model-based analysis of oligonucleotide arrays: Expression index computation and outlier detection, PNAS, vol. 98, no. 1, pp. 31–36, 2001.
J. Hardin and D. M. Rocke, Outlier detection in the multiple cluster setting using the minimum covariance determinant estimator, Computational Statistics and Data Analysis, vol. 44, no. 4, pp. 625–638, 2004.
G. Shi, Superiorities of support vector machine in fracture prediction and gassiness evaluation, Journal of Petroleum Exploration and Development, vol. 35, no. 5, pp. 588–594, 2008.
L. Bruzzone and D. F. Prieto, A technique for the selection of kernel-function parameters in RBF neural networks for classification of remote-sensing images, Geoscience and Remote Sensing, vol. 37, no. 2, pp. 1179–1184, 1999.
V. Cherkassky and Y. Q. Ma, Practical selection of SVM parameters and noise estimation for SVM regression, Neural Networks, vol. 17, no. 1, pp. 113–126, 2004.
J. E. Wang and J. Z. Qiao, Parameter selection of SVR based on improved k-fold cross validation, Applied Mechanics and Materials, vol. 462, no. 463, pp. 182–186, 2013.
T. S. Joaquin, H. E. Carlos, and F. R. Mercedes, Improving adaptive boosting with k-cross-fold validation, in Proc. 2006 IEEE Int. Conf. on Intelligent Computing, Kunming, China, 2006, pp. 397–402.
P. Lameski, E. Zdravevski, R. Mingov, and A. Kulakov, SVM parameter tuning with grid search and its impact on reduction of model over-fitting, in Proc. 2015 IEEE Int. Conf. on Rough Sets, Fuzzy Sets, Data Mining, and Granular Computing, Tianjin, China, 2015, pp. 464–474.
C. Liu, S. Q. Yin, M. Zhang, Y. Zeng, and J. Y. Liu, An improved grid search algorithm for parameters optimization on SVM, Applied Mechanics and Materials, vols. 644–650, pp. 2216–2219, 2014.
R. Liu, E. Liu, J. Yang, M. Li, and F. Wang, Optimizing the hyper-parameters for SVM by combining evolution strategies with a grid search, in Proc. 2006 IEEE Int. Conf. on Intelligent Computing, Kunming, China, 20016, pp. 712–721.
J. F. Kruiger, P. E. Rauber, R. M. Martins, A. Kerren, S. Kobourow, and A. C. Telea, Graph layout by t-SNE, Computer Graphics Forum, vol. 36, no. 3, pp. 283–294, 2017.
A. Gisbrecht, A. Schulz, and B. Hammer, Parametric nonlinear dimensionality reduction using kernel t-SNE, Neurocomputing, vol. 147, no. 5, pp. 71–82, 2015.
Z. Yang, C. W. Wang, and E. Oja, Multiplicative updates for t-SNE, in Proc. 2010 IEEE Int. Conf. on Machine Learning for Signal Processing, Kittila, Finland, 2010, pp. 19–23.
[44]
M. A. Li, X. Y. Luo, and J. F. Yang, Extracting the nonlinear features of motor imagery EEG using parametric t-SNE, Neurocomputing, vol. 218, no. 19, pp. 371–381, 2016.
The articles published in this open access journal are distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/).
Open Access
Issue
Published:
02 September 2019
),
Download citation
FEEDBACK 
TOP