Lithological Facies Identification in Iranian Largest Gas Field: A Comparative Study of Neural Network Methods

Abstract

Determination of different facies in an underground reservoir with the aid of various applicable neural network methods can improve the reservoir modeling. Accordingly facies identification from well logs and cores data information is considered as the most prominent recent tasks of geological engineering. The aim of this study is to analyze and compare the five artificial neural networks (ANN) approaches with identification of various structures in a rock facies and evaluate their capability in contrast to the labor intensive conventional method. The selected networks considered are Backpropagation Neural Networks (BPNN), Radial Basis Function (RBF), Probabilistic Neural Networks (PNN), Competitive Learning (CL) and Learning Vector Quantizer (LVQ). All these methods have been applied in four wells of South Pars field, Iran. Data of three wells were employed for the networks training purpose and the fourth one was used to test and verify the trained network predictions. The results have demonstrated that all approaches have the ability of facies modeling with more than 65% of precision. According to the performed analysis, RBF, CL and LVQ methods could model the facies with the accuracy between 66 and 68 percent while PNN and BPNN techniques are capable of making predictions with more than 72% and 88.5% of precision, respectively. It can be concluded that the BPNN can generate most accurate results in comparison to the other type of networks but it is important to note that the other factors such as consuming the amount of time taken, simplicity and the less adjusted parameters as well as the acquired precisions should be considered. As a result, the model evaluation analysis used in this study can be useful for prospective surveys and cost benefit facies identification.

Diagenesis and diagenetic facies distribution prediction of Chang 8 tight oil reservoir in Maling area, Ordos Basin, NW China

“…In recent years, neural network methods such as probabilistic neural networks (PNNs) (Kakouei et al, 2014;Rafik et al, 2016;Maurya et al, 2018) or artificial neural networks (ANNs) (Wang et al, 2012(Wang et al, , 2014Ghosh et al, 2016) have been widely used for the prediction of reservoir information. PNNs have been proven highly accurate for the prediction of shale lithofacies (Wang et al, 2015), so we used this method for data analysis.…”