Non-linear Heterogeneous Ensemble Model for Permeability Prediction of Oil Reservoirs

Helmy, Tarek; Rahman, S.; Hossain, Muhammad; Abdelraheem, Abdulaziz
June 2013
Arabian Journal for Science & Engineering (Springer Science & Bu;Jun2013, Vol. 38 Issue 6, p1379
Academic Journal
The ensemble computational model, which uses machine learning techniques to learn partial solutions of a given problem and combines the solutions to obtain a complete solution to the original problem, is increasingly used in both classification and regression problems. Typically the ensemble model performs better than the individual models and ensures better reliability of the model. The investigations of literature reveal that support vector machine (SVM), artificial neural network (ANN) and adaptive neuro-fuzzy inference system (ANFIS) are adopted individually to characterize oil reservoirs. In this paper, an ensemble of SVM, ANN and ANFIS is proposed to predict the permeability of oil reservoirs by using real-life well logs. An ANN model is used to implement a non-linear ensemble strategy. The individual models in the ensemble approach are trained with the datasets obtained by using bagging sampling principle. In this sampling approach, partial datasets for training each model are selected randomly. The simulation results reveal that the proposed ensemble of heterogeneous models outperforms the individual models with respect to correlation coefficient, root mean square error, and execution time. The proposed ensemble model exploits the expertise of each model and increases the generalization capability which is highly desirable for reservoir characterization that requires accurate predictions for maintaining efficient exploration and management of oil resources.


Related Articles

  • Geno-mathematical identification of the multi-layer perceptron. �stermark, Ralf // Neural Computing & Applications;2009, Vol. 18 Issue 4, p331 

    In this paper, we will focus on the use of the three-layer backpropagation network in vector-valued time series estimation problems. The neural network provides a framework for noncomplex calculations to solve the estimation problem, yet the search for optimal or even feasible neural networks...

  • Bounded rationality, neural network and folk theorem in repeated games with discounting. Cho, In-Koo // Economic Theory;1994, Vol. 4 Issue 6, p935 

    The perfect folk theorem (Fudenberg and Maskin [1986]) need not rely on excessively complex strategies. We recover the perfect folk theorem for two person repeated games with discounting through neural networks (Hopfield [1982]) that have finitely many associative units. For any individually...

  • Object recognition in industrial environments using support vector machines and artificial neural networks. Barry, Timothy John; Nagarajah, C. Romesh // International Journal of Advanced Manufacturing Technology;Jul2010, Vol. 48 Issue 5-8, p815 

    This paper presents a comparison between Artificial Neural Networks and Support Vector Machines in the application of classifying automotive wheels in an industrial environment. Performance of these two approaches over a range of classifier parameters on a data set pre-processed in multiple ways...

  • Hardware Approach of ANN Based Iris Recognition for Real-time Biometric Identification. Reaz, Mamun Bin Ibne; Amin, Md. Syedul; Hashim, Fazida Hanim; Asaduzzaman, Khandaker // Journal of Applied Sciences;2011, Vol. 11 Issue 16, p2984 

    Artificial Neural Networks (ANN) are increasingly applied to biometric identification because neural nets have been shown to be technologically powerful and flexible, ideally suited to perform identification analysis. Therefore, it demands the development of a new processing structure that...

  • Application of PCA Based Neural Network in Face Recognition. Gu Liqin // Journal of Convergence Information Technology;Mar2013, Vol. 8 Issue 5, p1034 

    The part of feature extraction is to extract the face information which distinguish from other faces from face images (effective identification information). This paper studies the error back-propagation (BP) neural network classifier. Neural network is a natural classifier, learning according...

  • The Unpredictability of Standard Back Propagation Neural Networks in Classification Applications. Wang, Shouhong // Management Science;Mar95, Vol. 41 Issue 3, p555 

    This note offers an extension of Tam and Kiang (1992). First the weakness of the standard back propagation neural network learning algorithm is discussed, and then a warning is issued regarding the applications of artificial neural networks in the management science field. Also suggested is a...

  • Editorial. MacIntyre, John // Neural Computing & Applications;1999, Vol. 8 Issue 1 

    Editorial. Introduces a series of articles on neural computing and applications.

  • Learning target marketing. Zaitz, Jed // Telephony;01/26/98, Vol. 234 Issue 4, p70 

    Discusses neural clustering, a form of unsupervised learning of artificial intelligence and neural networks. Principles behind neural clustering; Effective usage of neural clustering; Advantage over neural scoring.

  • What Good are Neural Nets? Donaldson, Ian M. // Journal of Information Technology (Routledge, Ltd.);Dec88, Vol. 3 Issue 4, p272 

    Discusses some of the issues that need to be tackled before symbolic or/and neural artificial intelligence can become a reality. Representation of knowledge; Decoding; Inference; Control of combinatorial explosion; Indexing; Prediction and recovery; Dynamic modification; Generalization.


Read the Article


Sorry, but this item is not currently available from your library.

Try another library?
Sign out of this library

Other Topics