Full text loading...
-
Application of Parallel Neural Networks for Reservoir Characterisation while Drilling
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 63rd EAGE Conference & Exhibition, Jun 2001, cp-15-00334
Abstract
L-18 APPLICATION OF PARALLEL NEURAL NETWORKS FOR RESERVOIR CHARACTERISATION WHILE DRILLING Abstract A new class of networks has been applied to reservoir characterisation using measurements while drilling (MWD) data. The parallel neural network consists of a number of identical networks (experts) trained on identical or overlapping patterns. We demonstrate that this approach is a pragmatic and accurate alternative for converting MWD data to common reservoir parameters such as porosity permeability and water saturation which leads to generation of relative permeability logs for input to real-time reservoir simulation for optimisation of well completion. Parallel Neural Networks Committee machines (CM) belong to