Application of artificial neural network for estimation of formation permeability in an iranian reservoir

Yeganeh, M ; Sharif University of Technology | 2009

499 Viewed
  1. Type of Document: Article
  2. Publisher: European Association of Geoscientists and Engineers, EAGE , 2009
  3. Abstract:
  4. The permeability is one of the most important reservoir parameters and its accurate prediction is necessary for reservoir management and enhancement. Although many empirical formulas are derived regarding permeability and porosity in sandstone reservoirs [1], these correlations cannot be modified accurately in carbonate reservoir for the wells which are not cored and there is no welltest data. Therefore estimation of these parameters is a challenge in reservoirs with no coring sample and welltest data. One of the most powerful tools to estimate permeability from well logs is Artificial Neural Network (ANN) whose advantages and disadvantages have been discussed by several authors [2]. In this paper, 767 core data sets and their corresponding well logs were taken from five wells of a reservoir in south west of IRAN. Depth, NPHI, PHOB, DT and total porosity were used as the input data and horizontal permeability obtained by coring was as target data. 60% of these data points were used for training and the remaining for predicting the permeability (validation and test).An ANN was developed and a correlation coefficient of 0.965 was obtained by comparing permeability predictions and the actual measurements. Data sets are well log and core data of a reservoir
  5. Keywords:
  6. Estimation ; Exhibitions ; Neural networks ; Porosity ; Well logging ; Accurate prediction ; Carbonate reservoir ; Correlation coefficient ; Formation permeability ; Permeability and porosities ; Permeability prediction ; Reservoir parameters ; Sandstone reservoirs ; Petroleum reservoir engineering
  7. Source: 1st International Petroleum Conference and Exhibition, Shiraz, 4 May 2009 through 6 May 2009 ; 2009
  8. URL: https://geopersia.ut.ac.ir/article_56089_1dfe9f3ecdbc56e9b1876321eae020d7.pdf