Petrophysical data prediction from seismic attributes using committee fuzzy inference system

Abstract

This study presents an intelligent model based on fuzzy systems for making a quantitative formulation between seismic attributes and petrophysical data. The proposed methodology comprises two major steps. Firstly, the petrophysical data, including water saturation (S w) and porosity, are predicted from seismic attributes using various Fuzzy Inference Systems (FIS), including Sugeno (SFIS), Mamdani (MFIS) and Larsen (LFIS). Secondly, a Committee Fuzzy Inference System (CFIS) is constructed using a hybrid Genetic Algorithms-Pattern Search (GA-PS) technique. The inputs of the CFIS model are the output averages of the FIS petrophysical data. The methodology is illustrated using 3D seismic and petrophysical data of 11 wells of an Iranian offshore oil field in the Persian Gulf. The performance of the CFIS model is compared with a Probabilistic Neural Network (PNN). The results show that the CFIS method performed better than neural network, the best individual fuzzy model and a simple averaging method.

Prediction of free flowing porosity and permeability based on conventional well logging data using artificial neural networks optimized by Imperialist competitive algorithm – A case study in the South Pars gas field

“…Moreover, a quantitative formulation for the conventional well logs and their NMR counterparts is a potent method to achieve the aforementioned objective. Several researchers have tried to estimate the petrophysical parameters from the conventional well logs (Kadkhodaie-Ilkhchi et al, 2009a, 2009bMalki and Baldwin, 2002;Rezaee et al, 2008;Shahab Mohaghegh, 2000). Many other researchers have studied applicability of the intelligent systems in geosciences (Jamialahmadi and Javadpour, 2000;Mohaghegh, 2005;Nikravesh et al, 2003;Ogilvie et al, 2002;Saggaf and Nebrija, 2003), but limited studies have focused on the application of the intelligent systems in predicting the NMR logging parameters.…”

NMR Log Prediction from Seismic Attributes: Using Multiple Linear Regression and Neural Network Methods

“…This method analyzes the entire shape of the T 2 distribution, attempting to unlock any information, such as pore throat sizes or grain size diameters, that could be related to permeability. Kadkhodaie et al (2009) developed a fuzzy logic for predicting water saturation and porosity from seismic attributes. The porosity and water saturation data of their study are obtained from core analyzing.…”

“…The establishment of the existence of an intelligent formulation between two sets of data (inputs/outputs) has been the main topic of such studies. Petrophysical parameters, such as porosity, are very important data for hydrocarbon reservoir characterization (Kadkhodaie et al, 2009). Several researchers have worked on predicting them from seismic data or well logs using statistical methods and intelligent systems.…”

Oil‐CO2 minimum miscible pressure (MMP) determination using a stimulated smart approach

“…In this study, worldwide experimental data from open literature were used to construct an improved, integrated intelligent model for estimating oil‐CO 2 MMP . Intelligent systems have had a great appeal for researchers in recent years . However, the quest for higher accuracy causes the development of integrated approaches and committee machines .…”