Neural Net Generated Seismic Facies Map and its Application in various Geologic Environments : Examples from South Texas Basin

A new technology of classifying a seismic interval parallel to a horizon in a 3D volume based on the shape of the wiggle traces and its geologic use will be presented here. Since the seismic traces contain all relevant information, such as, reflection patterns, phase, frequency, amplitude etc., the trace shape is a fundamental property of the seismic data. A map showing the distribution of similar trace shapes is like a facies map showing similar geologic features and is defined here as a "seismic facies map". Seismic facies maps can be created by using Stratimagic, CGG-Petrosystems’ latest 3D seismic stratigraphic interpretation software. The software uses a neural network technology to create a set of model traces by an unsupervised learning process on a subset of the data and then organizes the model traces showing progressive changes in them. Each model trace is assigned a color and a number. These model traces represent the diversity of trace shapes observed within the interval, which may vary from a few milliseconds to hundreds of milliseconds. Then every trace within the actual seismic interval is correlated to all the model traces and is classified to belong to the same class to which it bears highest degree of correlation. The trace is assigned the same number and color of the model trace. At the end a similarity map or a seismic facies map is created. No input from well data is needed in making a seismic facies map. This technology is licensed from Elf Aquitaine. As examples of this technology, several facies maps from a 3D survey in central South Texas will be presented with geological interpretations. • In an Upper Wilcox seismic facies map we were able to identify many features of a fluvial deltaic river system, such as, fluvial channel fills, braided deposits, point bars, crevasse splays, fan delta, abandoned delta etc. • Using seismic facies map the extent of Lower Wilcox onlapping horizons on the base of Lavaca Channel was determined and was confirmed by onlap mapping. • Using facies and other attribute maps we were able to identify broad areas of porosity development in Cretaceous Edwards limestone, which is a major hydrocarbon producer in this area. • Facies maps of an interval around Sligo limestone showed a linear NE-SW trending reef at the shelf edge for the entire 14km length of the survey. We were also able to interpret parallel interior reefs, back reef sediment filled basins, patchy reefs and tidal flats from the facies maps. The process is extremely fast and many facies classifications can be performed in a relatively short time for several horizon intervals. This enables the interpreter to effectively scan through the data quickly and to concentrate in areas of significance, where the classification process can be repeated in prospect size scale.