Prediction of Reservoir Compressibility Using Subsurface Cores, Well Logs, and Seismic Data by Neural Network

Document Type : Research Paper

Authors

1 Department of Mining Engineering, Faculty of Engineering, Urmia University, Urmia, Iran

2 Reservoir Rock and Fluids Research Group, Petroleum Engineering Department, Research Institute of Petroleum Industry, Tehran, Iran

Abstract

This study predicted the three-dimensional pore volume compressibility of carbonate Sarvak Formation from the Bangestan group. Primary data of the model were petrophysical parameters, measured compressibility factor on core samples, conventional well logs, and three-dimensional seismic attributes. The proposed experimental models of compressibility prediction are based on the rock’s porosity. However, due to the structural and textural complexities of carbonate formations, compressibility is not solely a function of the rock’s porosity but also depends on other petrophysical parameters. Neural network algorithms were employed to propagate the compressibility data along the well and to predict the distribution of compressibility within a three-dimensional seismic acquisition area. A probabilistic neural network algorithm resulted in a better correlation than an artificial neural network algorithm. It resulted in a correlation of 85% between the predicted and measured compressibility along logged intervals of the wells. 11 optimum number of seismic attributes were extracted to find the best correlation and minimum error between the generated and target attributes. The correlation coefficient of 91% indicated the high accuracy of the model and the optimal choice of neural network algorithms. The results of this study provide insights into the application of seismic data to the field-wide prediction of static models of reservoir compressibility.

Keywords

Main Subjects

Article Title [Persian]

_

Geopersia

Articles in Press, Accepted Manuscript
Available Online from 27 February 2024

Files

History

  • Receive Date: 09 January 2024
  • Revise Date: 21 February 2024
  • Accept Date: 27 February 2024

Share

How to cite

Statistics