Using multi-attribute transforms to predict log properties from seismic data

Abstract

In this paper, a new method for predicting well log properties from seismic data is described. The analysis data consists of a series of target logs from wells which tie a 3-D seismic volume. The objective is to derive a multi-attribute transform, linear or non­linear, between a subset of the attributes and the target log values. The selected subset is determined by a process of forward step-wise regression, which derives increasingly larger subsets of attributes. In the linear mode, the transform consists of a series of weights, which are derived by least-squares minimisation. In the non-linear mode, an artificial neural network is used. Cross-validation is used to estimate the reliability of the derived multi-attribute transform. This method is applied to a real data set. We see a continuous improvement in prediction power as we progress from single-attribute regression to linear multi-attribute prediction to neural network prediction. This improvement is evident not only on the training data, but more importantly, on the validation data. In addition, the neural network shows a significant improvement in resolution over that from linear regression.