A seismic lithofacies prediction method and device based on naive Bayesian classification

• Main Authors: ZHENG LIANDI, LIU RUIHONG, YANG QINLIN, ZHU BOHUA, LI YANG, DONG QINGYUAN, TIAN JIANHUA, CAO SHAOLEI
• Format: Patent
• Language: Chinese; English
• Published: 12.12.2017
• Subjects: DETECTING MASSES OR OBJECTS; GEOPHYSICS; GRAVITATIONAL MEASUREMENTS; MEASURING; PHYSICS; TESTING

The invention relates to the field of seismic reservoir prediction and provides a seismic lithofacies prediction method and device based on naive Bayesian classification. The method is characterized in that Bayesian classification is applied to reservoir prediction research; based on rock physical analysis and elastic parameter inversion, naive Bayesian classification is employed to perform prediction on lithological characters and fluid, so that the multiplicity of solutions of reservoir prediction is reduced, quantitative evaluation can be performed on uncertainty of prediction results and the accuracy of seismic lithofacies prediction can be improved remarkably. 本发明涉及地震储层预测领域，具体涉及基于朴素贝叶斯分类的地震岩相预测方法和装置。该方法将贝叶斯分类应用到储层预测研究中，以岩石物理分析和弹性参数反演为基础，并采用朴素贝叶斯分类统计对岩性、流体等进行预测，降低储层预测多解性，还可对预测结果的不确定性进行定量评价，能够显著提高地震岩相预测的准确性。