Permeability is a key parameter associated with the characterization of any hydrocarbon reservoir.\r\nIn fact, it is not possible to have accurate solutions to many petroleum engineering problems without\r\nhaving accurate permeability value. The conventional methods for permeability determination\r\nare core analysis and well test techniques. These methods are very expensive and time consuming.\r\nTherefore, attempts have usually been carried out to use artificial neural network for identification\r\nof the relationship between the well log data and core permeability. In this way, recent works on\r\nartificial intelligence techniques have led to introduce a robust machine learning methodology\r\ncalled support vector machine. This paper aims to utilize the SVM for predicting the permeability\r\nof three gas wells in the Southern Pars field. Obtained results of SVM showed that the correlation\r\ncoefficient between core and predicted permeability is 0.97 for testing dataset. Comparing the\r\nresult of SVM with that of a general regression neural network GRNN revealed that the SVM\r\napproach is faster and more accurate than the GRNN in prediction of hydrocarbon reservoirs\r\npermeability.
Loading....