Mapping the Gas Column in an Aquifer Gas Storage with Neural Network Techniques
An approach using seismic attributes and neural networks to map the gas extent was tested. The study was part of a reservoir project characterising a gas storage. AVO modelling and processing was done beforehand to define the extent of the gas distribution but lead to no clear conclusion. Seismic attributes showed indications of the gas extent but also were not conclusive. The neural network classification integrated three seismic attributes leading to a clearer delineation of the gas extent compared to the AVO results. The case study showed a successful application of neural networks which was used to solve a highly ambiguous problem.
KeywordsSeismic Line Seismic Modelling Pore Fill Seismic Attribute Amplitude Envelope
Unable to display preview. Download preview PDF.
- 1.Haghon, S., 1994. Neural Networks, A comprehensive Foundation, MacMillan College Publishing Co., NY.Google Scholar
- 2.Heggland, R., Meldahl, P., de Groot, P. and Aminzadeh, F., 2000. Seismic chimney interpretation examples from the North Sea and the Gulf of Mexico American Oil and Gas Reporter.Google Scholar