Reservoir porosity determination from 3D seismic data – Application of two machine learning techniques
Alimoradi, A., Moradzadeh, A. and Bakhtiari, M.R., 2012. Reservoir porosity determination from 3D seismic data - application of two machine learning techniques. Journal of Seismic Exploration, 21: 323-345. This paper proposes a method for solving 3D seismic data inversion problems for prediction of porosity in hydrocarbon reservoirs. An actual carbonate oil field in the south-western part of Iran was selected for this study. Taking real geological conditions into account, different synthetic models of reservoir were constructed for a range of viable porosity values. Seismic surveying was performed next on these models. From seismic response of the synthetic models, a large number of seismic attributes were identified as candidates for porosity estimation. Classes of attributes such as energy, instantaneous, and frequency attributes were included amongst others. Applying sensitivity analysis, the two most significant attributes were determined as Envelope Weighted Phase and Envelope Weighted Frequency, which were subsequently used in our machine learning algorithms. In particular, we used feed-forward artificial neural networks (FNN) and support vector regression machines (SVR) to develop relationships between the known synthetic attributes and synthetic porosity values in a given setting. The FNN consists of six neurons in a single hidden layer and the SVR method uses a Gaussian radial basis function. Compared with real values from the well data, we observed that SVM outperforms FNN due to its better handling of noise and model complexity.
- Alimoradi, A., Moradzadeh, A. and Bakhtiari, M.R., 2011. Modifying Gassmann equation todetermine the effect of pores sizes in carbonate reservoirs characterization. Petrol. Science,under review.
- An, P., 1994. The effect of random noise in lateral reservoir characterization using feedforwardneural networks. Expanded Abstr., 64th Ann. Internat. SEG Mtg., Los Angeles: 787-790.
- An, P. and Moon, W.M., 1993. Reservoir characterization using feedforward neural networks.
- Expanded Abstr., 63rd Ann. Internat. SEG Mtg., Washington D.C.: 258-262.
- An, P., Moon, W.M. and Kalantzis, F., 1997. Reservoir Property Estimation Using the Seismic
- Waveform and Feedforward Neural Networks. Report for Schlumberger.
- Batyrshin, I., Kaynak, O. and Rudas, I., 2002. Fuzzy modeling based on generalized conjunctionoperations. IEEE Transact. Fuzzy Syst., 10: 678-683.
- Batyrshin, I., Sheremetov, L., Markov, M. and Panova, A., 2005. Hybrid method for porosityclassification in carbonate formations. J. Petrol. Science Engin., 47: 35-50.
- Chih-Hung, W., Gwo-Hshiung, T. and Rong-Ho, L., 2009. A novel hybrid genetic algorithm for
- Kernel function and parameter optimization in support vector regression. Expert Syst.Applic., 36: 4725-4735.
- Demuth, H. and Beale, M., 2002. Neural Network Toolbox for Use with MATLAB, Version 3.0,742pp.dGB Earth Sciences, 2008. Seismic Software & Services, OpendTect, Version 4.0
- Duda, R.A., Hart, P.E. and Stork, D.G., 2002. Pattern Classification. Springer Verlag, Berlin.RESERVOIR POROSITY DETERMINATION 345
- Edalat, A. and Siahkoohi, H., 2007. Description of one of the Iranian hydrocarbon reservoirs usingseismic facies analysis. Iran. Geophys. J., 11: 37-49.
- Hagan, M.T., Demuth, H.B. and Beale, M., 1996. Neural Network Design. PWS PublishingCompany, Boston, MA.
- Jang, J.S.R., Sun, C.T. and Mizutani, E., 1997. Neuro-Fuzzy and Soft Computing: A
- Computational Approach to Learning and Machine Intelligence. Prentice Hall, EnglewoodCliffs, NJ.
- Lia, Q., Licheng, J. and Yingjuan, H., 2007. Adaptive simplification of solution for support vectormachine. Pattern Recogn., 40: 972-980.
- Lim, J.S., 2005. Reservoir properties determination using fuzzy logic and neural networks from welldata in offshore Korea. J. Petrol. Sci. Engin., 49: 182-192.
- Liu, H., Wen, S., Li, W., Xu, C. and Hu, C., 2009. Study on identification of oil/gas and waterzones in geological logging based on support-vector machine. Fuzzy Inform. Engin., 2,AISC 62: 849-857.
- Liu, H., Yao, X., Zhang, R., Liu, M., Hu, Z. and Fan, B., 2006. The accurate QSPR models topredict the bioconcentration factors of nonionic organic compounds based on the Heuristicmethod and support vector machine. Chemosphere, 63: 722-733.
- Malvic, T. and Prskalo, S., 2007. Some benefits of the neural approach in porosity prediction casestudy from Benicanci Field. NAFTA, 58: 455-461.
- Mavko, G., Mukerji, T. and Dvorkin, J., 2009. The Rock Physics Handbook. Cambridge UniversityPress, Cambridge.
- Mohaghegh, S., Arefi, R., Ameri, S., Amini, K. and Nutter, R., 1996. Petroleum reservoircharacterization with the aid of artificial neural networks. J. Petrol. Sci. Engin., 16:263-274.
- Mohaghegh, S., Popa, A., Koperna, G. and Hill, D., 1999. Reducing the Cost of Field-Scale Log
- Analysis Using Virtual Intelligence Techniques. SPE 57454, Tulsa, OK.
- Nikravesh, M., Aminzadeh, F. and Zadeh, L.A., 2003. Soft Computing and Intelligent DataAnalysis. Elsevier Science Publishers, Amsterdam.
- Pezeshk, S., Camp, C.V. and Karprapu, S., 1996. Geophysical log interpretation using neuralnetwork ASCE. J. Comput. Civil Engin., 10: 136-142.
- Quang-Anh, T., Xing, L. and Haixin, D., 2005. Efficient performance estimate for one-classsupport vector machine. Pattern Recogn. Lett., 26: 1174-1182.
- Raymer, L.L., Hunt, E.R. and Gardner, J.S., 1980. An improved sonic transit time-to-porositytransform. SPWLA Transact., 21st Ann. SPWLA Symp., Paper P, Tulsa, OK.
- Scholkopf, B., Smola, A.J. and Muller, K.R., 1998. Nonlinear component analysis as a Kerneleigenvalues problem. Neural Comput., 10: 1299-1319.
- Wang, W.J., Xu, Z.B., Lu, W.Z. and Zhang, X.Y., 2003. Determination of the spread parameterin the Gaussian Kernel for classification and regression. Neurocomput., 55: 643-663.
- Wyllie, M.R.J., Gregory, A.R. and Gardner, L.W., 1958. An experimental investigation of factorsaffecting elastic wave velocities in porous media. Geophysics, 23: 459-493.
