The tools of machine learning, petrophysics, well logs, and bi-variate statistics are applied in an integrated methodology to identify and discriminate reservoirs with hydrocarbon storage capacity. While the use of any one of these methods is familiar, their application together is unique.
Application of the unsupervised Machine learning using SOM clearly demonstrate the strike and geomorphology of the Pliocene marine turbidities. The southern segment of the channel penetrated with the three wells are very well defined after posting the wells. No significant difference on the neurons (hexagons) at the locations of the three wells which reflects the similarity of reservoir nature, thickness, sand content and pay thickness. A significant other channel is resolved to the east of the main channel that is not detected using the conventional spectral decomposition.
Examination of vertical seismic profile (VSP) data with unsupervised machine learning technology is a rigorous way to compare the fabric of down-going, illuminating, P and S wavefields with the fabric of up-going reflections and interbed multiples created by these wavefields.
The key to this presentation is showing examples of how the SOM classification process has led to hydrocarbon discoveries in different types of depositional environments. Examples of cases in which the decision was made not to drill a well, thus avoiding a potential dry hole, will also be shown.
By using statistical tools such as Attribute Selection, which uses Principal Component Analysis (PCA), and Multi-Attribute Classification using Self Organizing Maps (SOM), a multi-attribute 3D seismic volume can be “classified.” PCA reduces a large set of seismic attributes to those that are the most meaningful. The output of the PCA serves as the input to the SOM, a form of unsupervised neural network, which when combined with a 2D color map facilitates the identification of clustering within the data volume.