Prediction of reservoir permeability based on PCA and Support Vector Regression

By studying of the logging technology and basic characteristics of the reservoir together with the logging parameters and core parameters which related to reservoir permeability,a reservoir permeability predicting method is introduced based on the Principal Component Analysis(PCA) and Support Vector Regression(SVR) according to the traditional predicting methods of reservoir permeability.The PCA is used to reduce the dimensionality of the logging parameters and core parameters through which the optimizing relevant parameters of permeability are chosen.Then,the optimized relevant logging parameters and core parameters are imported to the SVR to predict reservoir permeability.The experimental results show that the extracted parameters through the PCA have a good relevance with the reservoir permeability,and the SVR has a high accuracy.It has been shown the strengths and practical application of the PCA and SVR used for the prediction of the reservoir permeability.