Comparative Application of Various Machine Learning Techniques for Lithology Predictions

- Journal title : Journal of Soil and Groundwater Environment
- Volume 21, Issue 3, 2016, pp.21-34
- Publisher : Korean Society of Soil and Groundwater Environment
- DOI : 10.7857/JSGE.2016.21.3.021

Title & Authors

Comparative Application of Various Machine Learning Techniques for Lithology Predictions

Jeong, Jina; Park, Eungyu;

Jeong, Jina; Park, Eungyu;

Abstract

In the present study, we applied various machine learning techniques comparatively for prediction of subsurface structures based on multiple secondary information (i.e., well-logging data). The machine learning techniques employed in this study are Naive Bayes classification (NB), artificial neural network (ANN), support vector machine (SVM) and logistic regression classification (LR). As an alternative model, conventional hidden Markov model (HMM) and modified hidden Markov model (mHMM) are used where additional information of transition probability between primary properties is incorporated in the predictions. In the comparisons, 16 boreholes consisted with four different materials are synthesized, which show directional non-stationarity in upward and downward directions. Futhermore, two types of the secondary information that is statistically related to each material are generated. From the comparative analysis with various case studies, the accuracies of the techniques become degenerated with inclusion of additive errors and small amount of the training data. For HMM predictions, the conventional HMM shows the similar accuracies with the models that does not relies on transition probability. However, the mHMM consistently shows the highest prediction accuracy among the test cases, which can be attributed to the consideration of geological nature in the training of the model.

Keywords

Secondary information;Well-logging;Subsurface prediction;Machine learning;

Language

Korean

References

1.

An, L.H., 2000, Neutral network in lithology determination, Tap Chi Tin Hoc Va Dieu Khien Hoc, 16(2), 59-62.

2.

Bauer, K., Schulze, A., Ryberg, T., Sobolev, S.V., and Weber, M.H., 2003, Classification of lithology from seismic tomography: A case study from the Messum igneous complex, Namibia, J. Geophys. Res., 108(B3), 2152, doi:10.1029/2001JB001073.

3.

Benaouda, D., Wadge, G., Whitmarsh, R.B., Rothwell, R.G., and MacLeod, C., 1999, Inferring the lithology of borehole rocks by applying neural network classifiers to downhole logs: an example from the Ocean Drilling Program, Geohphys. J. Int., 136, 477-491.

4.

Birch, F., 1961, The velocity of compressional waves in rocks to 10 kilobars, part 2, J. Geophys. Res., 66, 2199-2224.

5.

Bishop, C.M., 1995, Neural networks for pattern recognition, Oxford University Press.

6.

Bowling, J.M., Rodriguez, A.B., Harry, D.L., and Zheng, C., 2005, Delineating alluvial aquifer heterogeneity using resistivity and GPR data, 2005, Ground Water, 43(6), 890-903.

7.

Bowling, J.M., Harry, D.L, Rodriguez, A.B., and Zheng, C., 2007, Integrated geophysical and geological investigation of heterogeneous fluvial aquifer in Columbus Mississippi, Journal of Applied Geophysics, 62, 58-73.

8.

Busch, J.M., Fortney, W.G., and Berry, L.M., 1987, Determination of lithology from well logs by statistical analysis, SPE Formation Evaluation, 2, 412-418.

9.

Chang, H.C., Chen, H.C., and Fang, J.H, 1997, Lithology Determination from Well Logs with Fuzzy Associative Memory Neural Network, IEEE Transactions on Geoscience and Remote Sensing, 35(3), 773-780.

10.

11.

Cortes, C. and Vapnik, V., 1995, Support-vector networks, Machine Learning, 20(3), 273, DOI:10.1007/BF00994018.

12.

Delfiner, P., Peyret, O., and Serra, O., 1987, Automatic determination of lithology from well logs, SPE Formation Evaluation, 2, 303-310.

13.

Dunne, R.A. and Campbell, N.A., 1997, On the pairing of the softmax activation and cross-entropy penalty functions and the derivation of the softmax activation function, Proc. 8th Aust. Conf. on Neural Networks, Melb., 181-185.

14.

Eidsvik, J., Mukerji, T., and Switzer, P., 2004, Estimation of geological attributes from a well log: an application of hidden Markov chains, Mathematical Geology, 36(3), 379-397.

15.

Elliott, R.J., Aggoun, L., and Moore, J.B., 1995, Hidden Markov models: estimation and control, Springer, New York.

16.

Fung, C.C., Wong, K.W., Eren, H., and Charlebois, R., 1995, Lithology Classification Using Self-Organising Map, IEEE international Conference, 1.

17.

Gassaway, G.R., Miller, D.R., Bennett, L.E., Brown, R.A., Rapp, M., and Nelson, V., 1989, Amplitude variations with Offset: fundamentals and Case Histories, SEG Continuing Education Course Notes.

18.

Guven, O., Molz, F.J., Melville, J.G., El Didy, S., and Boman, G.K., 1992, Three-dimensional modeling of a two-well tracer test, Ground water, 30(6), 945-957.

19.

Jeong, J., Park, E., Han, W.S., and Kim, K.Y., 2014, A novel data assimilation methodology for predicting lithology based on sequence labeling algorithms, Journal of Geophysical Research: Solid Earth, 119(10), 7503-7520.

20.

Kendall, M.G. and Stuart, A., 1977, The advanced theory of statistics, Vol. 4, 4^{th} ed., MacMillan, New York.

21.

Liu, G., Zheng, C., Gorelick, S.M., 2004, Limits of applicability of the advection-dispersion model in aquifers containing high-conductivity channels, Water Resour. Res., 40, W08308, DOI:10.1029/2003WR002735.

22.

Maiti, S., Tiwari, R.K., and Kumpel, H.-J., 2007, Neural network modelling and classification of lithofacies using well log data: a case study from KTB borehole site, Geophys. J. Int., 169, 733-746.

23.

Murphy, K.P., 2012, Machine learning: a probabilistic perspective, MIT press, 1067p.

24.

Park, E., 2010, A multidimensional generalized coupled Markov chain model for surface and subsurface characterization, Water Resour. Res., 46(11), W11509, doi:10.1029/2009WR008355.

25.

Pickett, G.R., 1963, Acoustic character logs and their application in formation evaluation, J. Petr. Tech., 15, 659-667.

26.

Rimstad, K. and Omre, H., 2013, Approximate posterior distributions for convolutional two-level hidden Markov models, Computational Statistics and Data Analysis, 58, 187-200, doi:10.1016/j.csda.2012.09.001.

27.

Rogers, S.J., Fang, J.H., Karr, C.L., and Stanley, D.A., 1992, Determination of lithology from well logs using a neural network, The American Association of Petroleum Geolgists Bulletin, 76(5), 731-739.

28.

Sandham, W. and Leggett, M., 2003, Geophysical applications of artificial neural networks and fuzzy logic, Springer-science+business Media, Kluwer Acad., Boston, 348 p.

29.

Schon, J.H., 1996, Physical Properties of Rocks: Fundamentals and Principles of Petrophysics, Handbook of Geophys. Explor., Seismic Explor., 18, Pergamon, New York.

30.

Schumann, A., 1997, Neural networks versus statistics: a comparing study of their classification performance on well log data, Proc. Annu. Conf. International Association for Mathematical Geology-IAMG'97, 3rd, Barcelona, Spain, 237-241.

31.

Schumann, A., 2002, Hidden Markov models for lithological well log classification, In Proc. Annu. Conf. International Association for Mathematical Geology-IAMG'2002, 8th, Berlin, Germany, 373-378.

32.

Smirnoff, A., Boisvert, E., and Paradis, S.J., 2008, Support vector machine for 3d modelling from sparse geological information of various origins, Comput. Geosci., 34(2), 127-143.

33.

Sobolev, S.V. and Babeyko, A.Y., 1994, Modeling of mineral composition, density, and elastic wave velocities in anhydrous magmatic rocks, Surv. Geophys., 15, 515-544.

34.

Thompson, A.F.B. and Gelhar, L.W., 1990, Numerical siulation of solute transport in three-dimensional randomly heterogeneous porous media, Water Resour. Res., 26, 2541-2562.

35.

Wollff, M. and Pelissier-Combescure, J., 1982, Faciolog: automatic electrofacies determination, SPWLA Annual Logging Symposium, 6-9.