Vol. 20 No. 3 (2017) Cover Image
Vol. 20 No. 3 (2017)

Published: June 30, 2017

Pages: 737-743

Articles

Comparison of Different Types of Fitness Functions to Choose the Appropriate Attributes for Porosity Prediction

Muna Hadi Saleh 1 Hadeel M. Tuama 1
1 Electrical Eng. Dep. University of Baghdad
History
  • Received: February 28, 2017
  • Available Online: June 14, 2017

Abstract

Porosity is one of the most important reservoir characteristics because it indicates to fluid collection. Several techniques used to get good porosity prediction, so, in this study we employed seismic attributes and well log data in a genetic algorithm to get the best porosity prediction. The study attempt to enhance the performance of genetic algorithm for attribute selection and therefore porosity prediction by applying genetic algorithm on different types of fitness functions like average mean square error fitness, average correlation coefficients fitness and performance index fitness. Also, used two methods to represent attributes in genetic algorithm. Different witnesses applied to choose the appropriate fitness function that gives high porosity prediction.

Keywords

References

  1. A. Adekanle and P. Enikanselu, “Porosity prediction from seismic inversion properties over ‘XLD’ field, Niger Delta,” Am. J. Sci. Ind. Res., vol. 4, no. 1, pp. 31–35, 2013.
  2. Subrahmanyam and P. Rao, H, 2008," Seismic Attributes- A Review", International Conference and Exposition on Petroleum Geophysics, P. 398.
  3. F. Herrera, M. Lozano, and J. L. Verdegay, “Tackling Real-Coded Genetic Algorithms:
  4. Operators and Tools for Behavioural Analysis,” Artif. Intell. Rev., vol. 12, no. 4, pp. 265–319, 1998.
  5. A. Hosseini, M. Ziaii, A. K. Rouhani, A. Roshandel, R. Gholami, and J. Hanachi, “Artificial Intelligence for prediction of porosity from Seismic Attributes : Case study in the Persian Gulf,” pp. 168–174, 2011.
  6. M. Golub, "an implementation of binary and floating point chromosome representation in Genetic algorithm", 2014.
  7. Muna. H. Saleh, and H. M Tuama, " Novel Multi - Gen Multi Parameter Genetic Algorithm Representation for Attributes Selection and Porosity Prediction ", International Journal of Computer Applications, v. 141, no. 4, P. 34 - 39, 2016.
  8. L. H. Randy and , E. H. Sue,” practical Genetic algorithms”, Wiley, 2004.
  9. T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? -Arguments against avoiding RMSE in the literature,” Geosci. Model Dev., vol. 7, no. 3, pp. 1247–1250, 2014.
  10. D. Shen and Z. Lu, “Computation of Correlation Coefficient and Its Confidence Interval,” Sugi 31, pp. 1–6, 2006.
  11. K. P. Dorrington and C. a. Link, “Geneticalgorithm/ neural-network approach to seismic attribute selection for well-log prediction,” Geophysics, vol. 69, no. 1, p. 212, 2004.