地震数据油气预测中的属性优化方法

An attribute optimization method in oil and gas prediction with seismic data

江汉石油学院物探系,计算机系, 荆州, 434102

Jianghan Petroleum Institute, Jingzhou 434102

本文简单介绍了智能信息处理中新出现的RoughSet（RS）理论及属性选择方法,从双相介质地震波传播理论角度,探讨了地震数据油气预测属性优化原理,提出了基于RS理论的地震数据油气预测属性优化方法。实际应用表明；本方法速度快、易实现,而且在优选属性、最大程度地减少提取地震属性种数、提高分类正确率等方面,明显优于其它方法。本方法将成为地震数据油气预测的一种有效手段。

In the paper we briefly introduce the Rough Set (RS) theory, which is a new theory in intelligent information processing, and the attribllte selection method. From the angle of seismic wave propagation theory in two-phase media, we rnake an approach to the attribute optimization principle in oil and gas prediction with seismic data and put forward an attribute optimization method on the basis of the RS theory. The application result indicates that the rnethod is fast in speed and can be realized easily. Moreover, the method is superior to other methods in selecting the attribute, decreasing the number of seismic attributes to be extracted, and improving the classification correctness. It can become an effective means for oil and gas prediction with seismic data.