基于支持向量机的地震多属性综合解释技术应用研究

摘要

This theme gives the process to predict reservoir parameters based on the support vector machine.We predictes the percentage of sandstone to mudstone,porosity and oil saturation of SZ36-1 by the support vector machine combined with seismic attributes which are optimizated by the Rough set theory as the input vector.The results show that the method has higher prediction accuracy to predict reservoir parameters.%给出基于支持向量机方法的储层参数预测流程。以粗糙集理论优选出的地震属性为输入向量,利用支持向量机方法对渤海SZ36-1的砂泥岩百分比、孔隙度与含油饱和度进行预测。实例应用表明,利用此方法预测储层参数的精度较高。