A new approach to improve neural networks' algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network (SCMNN)

Karimpouli, Sadegh; Fathianpour, Nader; Roohi, Jaber

doi:10.1016/j.petrol.2010.07.003

Cited by 94 publications

(30 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the context of flows within porous media ANN's have been used for a variety of applications that include, e.g., prediction of gas diffusion layer properties within polymer electrolyte membrane (PEM) fuel cells (Lobato et al, 2010;Kumbur et al, 2008), prediction of dialysis performance in ultrafiltration (Godini et al, 2010), hygrothermal property characterization in porous soils (Coelho et al, 2009), oil saturation and petrophysical property predictions in oilfield sands (Boadu 2001), groundwater contamination and pollutant infiltration forecasting (Tabach et al, 2007), simulating cross-flow filtration processes (Silva and Flauzino, 2008), optimization of groundwater remediation problems (Johnson and Rogers, 2000;Rogers and Dowla, 1994), large-scale water resource management (Yan and Minsker, 2006), permeability modeling in petroleum reservoir management (Karimpouli et al, 2010), water/wastewater treatment using various homogeneous and heterogeneous nano-catalytic processes (Khataee and Kasiri, 2010), determination of stress-strain characteristics in composites (Lefik et al, 2009) and characterization of outflow parameters influencing fractured aquifers outflows (Lallahem and Mania, 2003). For example, Rogers and Dowla (1994) proposed an ANN-based groundwater management model for optimizing aquifer remediation.…”

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media

Hanspal

Allison

Deka

et al. 2012

Journal of Hydroinformatics

View full text Add to dashboard Cite

The dynamic effect in two-phase flow in porous media indicated by a dynamic coefficient τ depends on a number of factors (e.g. medium and fluid properties). Varying these parameters parametrically in mathematical models to compute τ incurs significant time and computational costs. To circumvent this issue, we present an artificial neural network (ANN)-based technique for predicting τ over a range of physical parameters of porous media and fluid that affect the flow. The data employed for training the ANN algorithm have been acquired from previous modeling studies. It is observed that ANN modeling can appropriately characterize the relationship between the changes in the media and fluid properties, thereby ensuring a reliable prediction of the dynamic coefficient as a function of water saturation. Our results indicate that a double-hidden-layer ANN network performs better in comparison to the single-hidden-layer ANN models for the majority of the performance tests carried out. While single-hidden-layer ANN models can reliably predict complex dynamic coefficients (e.g. water saturation relationships) at high water saturation content, the double-hidden-layer neural network model outperforms at low water saturation content. In all the cases, the single- and double-hidden-layer ANN models are better predictors in comparison to the regression models attempted in this work.

show abstract

Section: Artificial Neural Network (Anns)mentioning

confidence: 99%

Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media

Hanspal

Allison

Deka

et al. 2012

Journal of Hydroinformatics

View full text Add to dashboard Cite

show abstract

“…Although in general these systems have met with somewhat modest success, there are some indications that careful use of spike timings can facilitate very general forms of computation [20]. Moreover, researchers have shown preliminary work in which polychronization can be used with reservoir computing methods to perform supervised classification tasks [25,33]. Our work continues along these lines by exploring the extent to which purely unsupervised learning can exploit polychronization with temporally-dependent data to build time-aware representations that facilitate traditional classification.…”

Section: Previous Workmentioning

confidence: 95%

A Scale and Translation Invariant Approach for Early Classification of Spatio-Temporal Patterns Using Spiking Neural Networks

Rekabdar

Nicolescu

Saffar

et al. 2015

Neural Process Lett

View full text Add to dashboard Cite

This paper addresses the problem of encoding and classifying spatio-temporal patterns, which are typical for human actions or gestures. The proposed method has the following main contributions: (i) it requires a very small number of training examples, (ii) it accepts variable sized input patterns, (iii) it is invariant to scale and translation, and (iv) it enables early recognition, from only partial information of the pattern. The underlying representation employed is a spiking neural network with axonal conductance delay. We designed a novel approach for mapping spatio-temporal patterns to spike trains, which are used to stimulate the network. The pattern features emerge in the network as a result of this stimulation in the form of polychronous neuronal groups, which are used for classification. The proposed method is validated on a set of gestures representing the digits from 0 to 9, extracted from video data of a human drawing the corresponding digits. The paper presents a comparison with several other standard pattern recognition approaches. The results show that the proposed approach significantly outperforms these methods, it is invariant to scale and translation, and it has the ability to recognize patterns from only partial information.

show abstract

“…Equation (2) represents that the committee machine gives smaller errors than the average of all the experts [20,21]:…”

Section: Neural Network and Committee Machinementioning

confidence: 99%

Desirability Improvement of Committee Machine to Solve Multiple Response Optimization Problems

Golestaneh

Ismail

Ariffin

et al. 2013

Advances in Artificial Neural Systems

View full text Add to dashboard Cite

Multiple response optimization (MRO) problems are usually solved in three phases that include experiment design, modeling, and optimization. Committee machine (CM) as a set of some experts such as some artificial neural networks (ANNs) is used for modeling phase. Also, the optimization phase is done with different optimization techniques such as genetic algorithm (GA). The current paper is a development of recent authors' work on application of CM in MRO problem solving. In the modeling phase, the CM weights are determined with GA in which its fitness function is minimizing the RMSE. Then, in the optimization phase, the GA specifies the final response with the object to maximize the global desirability. Due to the fact that GA has a stochastic nature, it usually finds the response points near to optimum. Therefore, the performance the algorithm for several times will yield different responses with different GD values. This study includes a committee machine with four different ANNs. The algorithm was implemented on five case studies and the results represent for selected cases, when number of performances is equal to five, increasing in maximum GD with respect to average value of GD will be eleven percent. Increasing repeat number from five to forty-five will raise the maximum GD by only about three percent more. Consequently, the economic run number of the algorithm is five.

show abstract

A new approach to improve neural networks' algorithm in permeability prediction of petroleum reservoirs using supervised committee machine neural network (SCMNN)

Cited by 94 publications

References 8 publications

Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media

Artificial neural network (ANN) modeling of dynamic effects on two-phase flow in homogenous porous media

A Scale and Translation Invariant Approach for Early Classification of Spatio-Temporal Patterns Using Spiking Neural Networks

Desirability Improvement of Committee Machine to Solve Multiple Response Optimization Problems

Contact Info

Product

Resources

About