基于灰关联分析与K-L变换的双重属性优化方法

将灰关联分析和K-L变换有机地结合起来可以实现属性的双重优化。利用灰关联分析实现了地震属性的敏感性分析，并建立了储层参数与属性之间的灰色关联。在此基础上，通过K-L变换将属性空间的高维属性映射为低维属性，且去除了属性之间的相关性，从而有效地解决了属性组合的优化问题。采用BP神经网络对目标进行预测表明，灰关联分析和K-L变换相结合的属性双重优化方法能充分发挥单个方法各自的优点，有助于属性分析、关联以及组合优化问题的解决，从而提高了地震储层预测的运算速度和精度。

Dual optimization of seismic attributes based on Grey association analysis and K-L transform.

Combination of Grey association analysis with K-L transform can realize the dual optimization of attributes.Using Grey association analysis realized the sensibility analysis of seismic attributes and built up Grey association between the reservoir parameters and attributes.On that basis,mapping of high-dimension attributes onto low-dimension attributes in attributes space is carried out by K-L transform and eliminated the correlation among the attributes so that can effectively solve the optimized issue of attributes combination.Using BP neural network for prediction of targets showed that the dual optimization method of seismic attributes combined Grey association analysis with K-L transform can fully display individual advantages of each method,which is a great help to solve the issues of attributes analysis,association and combination optimization,then improves the operation speed and precision of seismic reservoir prediction.