Matching Time-Lapse Seismic Data Using Neural Networks

G043 MATCHING TIME-LAPSE SEISMIC DATA USING NEURAL NETWORKS Abstract 1 In this paper we use artificial neural networks to cross-equalise one vintage of time-lapse seismic data to another. The networks act as three-dimensional non-linear operators and are therefore capable of correcting for both spatial and temporal mismatches; indeed the mismatches can also be non-stationary. In general the networks are described by a relatively small number of parameters and this in turn helps maintain stability. We illustrate the benefits of the neural network matching method on a North Sea time-lapse dataset. In this case the method successfully identified and applied a