Neural network training data selection using memory reduced cluster analysis for field model development
A system and method for selecting a training data set from a set of multidimensional geophysical input data samples for training a model to predict target data. The input data may be data sets produced by a pulsed neutron logging tool at multiple depth points in a cases well. Target data may be responses of an open hole logging tool. The input data is divided into clusters. Actual target data from the training well is linked to the clusters. The linked clusters are analyzed for variance, etc. and fuzzy inference is used to select a portion of each cluster to include in a training set. The reduced set is used to train a model, such as an artificial neural network. The trained model may then be used to produce synthetic open hole logs in response to inputs of cased hole log data.
1. A method of operating a hydrocarbon bearing field, comprising:
drilling a plurality of wells in the hydrocarbon bearing field,
performing open hole logging in a subset of the wells,
performing cased hole logging in substantially all of the wells including the subset of wells,
using open hole logging data and cased hole logging data from the subset of wells to train a predictive model to produce synthetic open hole data in response to inputs of cased hole data, and
using the trained predictive model and cased hole data from the wells to produce synthetic open hole data
wherein the subset of wells comprises less than one-half of the plurality of wells.
2. A method according to claim 1 , further comprising using the synthetic open hole data to plan operations for the wells.
3. A method according to claim 1 , wherein the subset of wells comprises less than one-fifth of the plurality of wells.