EEI ATTRIBUTES FOR FLUID DISCRIMINATION USING FUZZY LABELED MULTICLASS SUPPORT VECTOR MACHINE

In exploration seismology, automatic seismic facies analysis to discriminate different facies and fluid content is an essential task to reduce future drilling risks. There are different seismic attributes as learning features and various learning methods for automatic seismic facies analysis. Previous studies have proved that selecting efficient seismic attributes is more crucial than the learning method. Therefore, it is logical to pay more attention to the choice of proper attributes. The extended elastic impedance (EEI) attributes belong to prestack seismic attributes, and they are functions of compressional velocity, shear velocity, density, and chi angles. The Chi angle is the virtual incident angle and changes between-90 to +90 degrees. The innovative method demonstrates the role of fluid replacement modeling (FRM) for the supervised selection of EEI attributes at suitable chi angles as input features to train an intelligent model for the discrimination of reservoir fluid contents. The method starts with FRM to model different fluid contents of the reservoir (100% brine, 100% oil, and 100% gas) using borehole data. Then, efficient EEI (Chi) logs are selected according to the results of the EEI template analysis. Thus, EEI seismic attributes at selected Chi angle are calculated from prestack seismic data by amplitude versus offset (AVO) analysis and EEI inversion. Then, labeling of the EEI attributes is performed by fuzzy c-mean clustering (FCM). By considering membership functions, a fuzzy concept is an appropriate tool for soft clustering and an appealing method for seismic interpretation. Afterward, a classifier model of the multiclass support vector machine (SVM) is trained using the fuzzy labeled samples to predict the fluid type of unseen data. The method was applied to a 3D prestack seismic data of an oil sand reservoir in the Persian Gulf to predict the fluid distribution map at the top of the reservoir. The reservoir contains a considerable amount of gas cap. Only one borehole data drilled in the oil column is available for FRM and fluid EEI template analysis. The available fluid distribution map confirms the accuracy of the resulted fluid distribution map based on the modeling of all the wells in different locations of the reservoir. This confirmation proves the application of the proposed method in fluid pore identification.