Estimation of reservoir parameter using a hybrid neural network

Estimation of an oil field's reservoir properties using seismic data is a c rucial issue. The accuracy of those estimates and the associated uncertaint y are also important information. This paper demonstrates the use of the k- fold cross validation technique to obtain confidence bound on an Artificial Neural Network's (ANN) accuracy statistic from a finite sample set. In add ition, we also show that an ANN's classification accuracy is dramatically i mproved by transforming the ANN's input feature space to a dimensionally sm aller, new input space. The new input space represents a feature space that maximizes the Linear separation between classes. Thus, the ANN's convergen ce time and accuracy are imporved because the ANN must merely find nonlinea r perturbations to the starting linear decision boundaries. These technique for estimating ANN accuracy bounds and feature space transformations are d emonstrated on the problem of estimating the sand thickness in an oil field reservoir based only on remotely sensed seismic data. (C) 1999 Elsevier Sc ience B.V. All rights reserved.