A Neural Stochastic Optimization Framework for Oil Parameter Estimation

  • Rafael E. Banchs
  • Hector Klie
  • Adolfo Rodriguez
  • Sunil G. Thomas
  • Mary F. Wheeler
Conference paper

DOI: 10.1007/11875581_18

Part of the Lecture Notes in Computer Science book series (LNCS, volume 4224)
Cite this paper as:
Banchs R.E., Klie H., Rodriguez A., Thomas S.G., Wheeler M.F. (2006) A Neural Stochastic Optimization Framework for Oil Parameter Estimation. In: Corchado E., Yin H., Botti V., Fyfe C. (eds) Intelligent Data Engineering and Automated Learning – IDEAL 2006. IDEAL 2006. Lecture Notes in Computer Science, vol 4224. Springer, Berlin, Heidelberg

Abstract

The main objective of the present work is to propose and evaluate a neural stochastic optimization framework for reservoir parameter estimation, for which a history matching procedure is implemented by combining three independent sources of spatial and temporal information: production data, time-lapse seismic and sensor information. In order to efficiently perform large-scale parameter estimation, a coupled multilevel, stochastic and learning search methodology is proposed. At a given resolution level, the parameter space is globally explored and sampled by the simultaneous perturbation stochastic approximation (SPSA) algorithm. The estimation and sampling performed by SPSA is further enhanced by a neural learning engine that evaluates the objective function sensitiveness with respect to parameter estimates in the vicinity of the most promising optimal solutions.

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2006

Authors and Affiliations

  • Rafael E. Banchs
    • 1
  • Hector Klie
    • 2
  • Adolfo Rodriguez
    • 2
  • Sunil G. Thomas
    • 2
  • Mary F. Wheeler
    • 2
  1. 1.GPS, TSCPolytechnic University of CataloniaBarcelonaSpain
  2. 2.CSM, ICESThe University of Texas at AustinUSA

Personalised recommendations