Abstract
Automatic classification of seismic reflection data plays an important role in reservoir characterization and petroleum geosciences. Recently, the relevance vector machines (RVM) have attracted substantial interest in data classification literature. The RVM is a Bayesian variant of support vector machine (SVM) that can surmount the limitations of other conventional methods. The main purpose of this study is to show the effectiveness of RVM as a linear classifier to classify the variation in seismic data. In this study, we explored the potentials of RVM in identifying anomalous seismic reflection signals. First, the efficiency of RVM technique is compared with other conventional methods (SVM and probabilistic neural network (PNN)), and then a multi-class RVM algorithm based on the Gaussian approximation model is used to successfully classify synthetic and field seismic data. The result of this study shows that RVM is successful in the determination of gas-bearing zone in one of the Iranian southern oil fields.
This is a preview of subscription content, log in via an institution to check access.
Similar content being viewed by others
References
Ahmadi MA (2011) Prediction of asphaltene precipitation using artificial neural network optimized by imperialist competitive algorithm”. J Pet Explor Prod Technol 1(2–4):99–106
Ahmadi MA, Ebadi M, Hosseni SM (2014) Prediction breakthrough time of water coning in the fractured reservoirs by implementing low parameter support vector machine approach. Fuel 117:579–589
Ahmadi MA, Hasanvand MZ, Bahadori A (2015a) A least-squares support vector machine approach to predict temperature drop accompanying a given pressure drop for the natural gas production and processing systems. Int J Ambient Energy 38(2):122–129. https://doi.org/10.1080/01430750.2015.1055515
Ahmadi MA, Soleimani R, Lee M, Kashiwao T, Bahadori A (2015b) Determination of oil well production performance using artificial neural network (ANN) linked to the particle swarm optimization (PSO) tool. Petroleum 1(2):118–132
Aminzadeh F (2000) Reservoir parameter estimation using a hybrid neural network. Comput Geosci 26:860–875
ASCE Task Committee on Application of the Artificial Neural Networks in Hydrology (2000) Artificial neural networks in hydrology II: hydrologic applications. J Hydrol Eng ASCE 5(2):124–137
Atsanos N, Likes A, Tzikas DJ (2009) Sparse bayesian modeling whit adaptive kernel learning. IEEE Trans Neural Netw 20(6):926–937
Bagheri M, Riahi MA (2014) Seismic facies analysis from well logs based on supervised classification scheme with different machine learning techniques. Arab J Geosci 8(9):7153–7161. https://doi.org/10.1007/s12517-014-1691-5
Berger JO (1985) Statistical decision theory and bayesian analysis, 2nd edn. Springer, New York
Burges CJC, Schölkopf B (1997) Improving the accuracy and speed of support vector learning machines. In: Mozer MC, Jordan MI, Petsche T (eds) Advances in neural information processing systems, vol 9. MIT Press, Cambridge, pp 375–381
Damoulas T, Girolami M, Ying Y, Campbell C (2008) Inferring sparse kernel combinations and relevance vectors: an application to subcellular localization of proteins. Bioinformatics 24(10):1264–1270
Duin RPW, Loog M, Pekalska EP, Tax DMJ (2010) Feature-based dissimilarity space classification, ICPR, LNCS 6388, pp 46–55
He W, Yow KC, Guo Y (2012) Recognition of human activities using a multiclass relevance vector machine. Opt Eng 51(017):202
Kecman V (2001) Learning and soft computing: support vector machines, neural networks, and fuzzy logic models. MIT Press, Cambridge
Kunstmann H, Kinzelbach W, Siegfried T (2002) Conditional first-order second moment method and its application to the quantification of uncertainty in groundwater modeling. Water Resour Res 38(4):1035
Lima CAM, Coelho ALV, Chagas S (2009) Automatic EEG signal classification for epilepsy diagnosis with relevance vector machines. Expert Syst Appl 36:10054–10059
Lima CAM, Coelho ALV, Madeo RCB, Peres SM (2015) Classification of electromyography signals using relevance vector machines and fractal dimension. Neural Comput Appl. https://doi.org/10.1007/s00521-015-1953-5
Liong S, Sivapragasam C (2002) Flood stage forecasting with support vector machines. J Am Water Resour Assoc 38(1):173–186
Lippmann RP (1989) Pattern classification using neural networks. IEEE Communications Magazine, November 1989
MacKay DJ (1992) Bayesian methods for adaptive models. Ph.D. thesis, Dept. of Computation and Neural Systems, California Institute of Technology, Pasadena, CA
McCulloch Warren, Pitts Walter (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133
Nazari A, Riahi MA, Heidari B (2017) Detection of gas bearing intervals using S-transform and AVO analysis. Carbon Evaporites 32(1):53–61
Ozer S, Haider MA, Langer DL, Van der Kwast TH (2009) Prostate cancer localization with multispectral MRI based on relevance vector machines. Conference Paper in Proceedings/IEEE International Symposium on Biomedical Imaging: from nano to macro. IEEE International Symposium on Biomedical Imaging, June 2009
Psorakis I, Damoulas T, Girolami MA (2010) Multiclass relevance vector machines: sparsity and accuracy. IEEE Trans Neural Netw 21(10):1588–1598
Rochester N, Holland JH, Habit LH, Duda WL (1956) Tests on a cell assembly theory of the action of the brain, using a large digital computer. IRE Trans Inform Theory 2(3):80–93. https://doi.org/10.1109/tit.1956.1056810
Rosenblatt F (1958) The perceptron: a probabilistic model for information storage and organization in the brain. Psychol Rev 65(6):386–408. https://doi.org/10.1037/h0042519
Schölkopf B, Smola AJ (2002) Learning with kernels: support vector machines, regularization, optimization, and beyond. MIT Press, Cambridge
Tipping ME (2000) The relevance vector machine. In: Solla SA, Leen TK, Muller K-R (eds) Advances in neural information processing systems, vol 12. MIT Press, pp 652–658
Tipping M (2001) Sparse bayesian learning and the relevance vector machine. J Mach Learn Res 1:211–244
Vapnik V (1963) Pattern recognition using generalized portrait method. Autom Remote Control 24:774–780
Vapnik V (1982) Estimation of dependencies based on empirical data. Springer, New York
Vapnik V (1992) Principles of risk minimization for learning theory. In Moodey JE, Hanson SJ, Lippmann RP (eds) Advances in Neural Information Processing Systems, vol 4, pp 831–838
Vapnik V (1995) The nature of statistical learning theory. Springer-Verlag, New York
Vapnik V (1998) Statistical learning theory. Wiley, New-York
Wahba G (1985) A comparison of GCV and GML for choosing the smoothing parameter in the generalized spline-smoothing problem. Ann Stat 4:1378–1402
Acknowledgements
The authors acknowledge the research council at the University of Tehran for supporting this research.
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Mohebian, R., Riahi, M.A. & Afjeh, M. Detection of the gas-bearing zone in a carbonate reservoir using multi-class relevance vector machines (RVM): comparison of its performance with SVM and PNN. Carbonates Evaporites 33, 347–357 (2018). https://doi.org/10.1007/s13146-017-0411-0
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s13146-017-0411-0