The development of an optimal artificial neural network model for estimating initial, irreducible water saturation - Australian reservoirs
Date
2005
Authors
Goda, H.
Maier, H.
Behrenbruch, P.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Conference paper
Citation
Proceedings [electronic resource] : APOGCE 2005, SPE Asia Pacific Oil & Gas Conference and Exhibition, 5-7 April 2005, Jakarta, Indonesia / pp. 513-527
Statement of Responsibility
Conference Name
Asia Pacific Oil & Gas Conference and Exhibition (2005 : Jakarta, Indonesia)
Abstract
Initial, irreductible water saturation, S <inf>wir</inf> is an important parameter that needs to be determined accurately when attempting to characterize hydrocarbon reservoirs. S <inf>wir</inf> is also one of the key parameters in relative permeability relationships. Furthermore, an unrepresentative value of S <inf>wir</inf> may lead to invalid residual oil saturation estimates when the latter is correlated with the former. S <inf>wi</inf> may have a dependence on several other parameters, including: absolute rock permeability, porosity, pore size distribution and capillary pressure. The above parameters are directly influenced by geological deposition and subsequent changes, such as diagenesis effects (for example clay-filled pores). It is a common practice to measure S <inf>wir</inf> utilizing representative core plugs by measuring capillary pressure with a centrifuge, at speeds equivalent to the maximum representative (reservoir) capillary pressure. However, a semi-empirical model that could estimate S <inf>wir</inf> to a good degree of accuracy would be of significant value. Over the last few years, artificial neural networks have found their application in petroleum engineering. In some cases such models have outperformed models employing conventional statistical and regression analysis. In this study, an Artificial Neural Network (ANN) model has been developed for the prediction of S <inf>wi</inf> (specifically irreducible saturation, S <inf>wir</inf>) using data from a number of onshore and offshore Australian hydrocarbon basins. The paper outlines a methodology for developing ANN models and the results obtained indicate that the ANN model developed is successful in predicating values of S <inf>wir</inf> over the range of data used for calibration. This neural network based model is believed to be unique for Australian reservoirs Copyright 2005, Society of Petroleum Engineers Inc.