The Application Of Seismic Attributes To Reservoir Prediction In Dixi Area Of Junggar Basin

Seismic attribute analysis technology can fully excavate the formation,lithology and fluid information contained in the seismic data.It is one of the effective methods for seismic reservoir prediction and plays an important role in the field of oil and gas exploration and development.Taking the theoretical study of seismic attributes as the starting point,the thesis elaborated the current research status and development trend of seismic attributes at home and abroad,introduced the classification and extraction methods of seismic attributes in detail,and specifically analyzed and studied the seismic attribute optimization method of Kernel principal component analysis,Genetic algorithm and BP neural network method to predict reservoir parameters,laid a theoretical foundation for the application of seismic attributes for reservoir prediction.Based on the theoretical research,the thesis takes the actual three-dimensional engineering area in the Dixi area in the Junggar Basin as an example,and uses seismic attributes to carry out reservoir parameter prediction research.First,a variety of methods were used to extract the 42 seismic attributes of the target layer;then the seismic attributes were optimized based on correlation analysis and kernel principal component analysis;and then the improved GA-BP neural network algorithm was used to predict the sand body thickness and porosity distribution of the target layer in the study area;finally,according to the sand body thickness and porosity of the target layer,calculate the reservoir evaluation coefficient,and use this as a basis to divide the favorable storage area.Through actual drilling and logging data,the predicted sand body thickness and porosity plan are verified,and the overall conformity is high,and the favorable reservoir area divided is consistent with the actual drilling results.