基于单位超球面上Mean Shift聚类的地震子波盲估计  

Blind Estimation of Seismic Wavelet on Unit Hypersphere with Mean Shift

作　　者：萧蕴诗[1] 赵彦青[1] 程成[2] 

机构地区：[1]同济大学电子与信息工程学院,上海201804 [2]苏州科技大学电子与信息工程学院,苏州215009

出　　处：《计算机科学》2017年第5期33-36,共4页Computer Science

摘　　要：石油勘探领域中,地震信号可以看作地震子波与地震反射系数的褶积。由于缺乏先验知识,地震反褶积本质上是一个盲过程。针对带状独立分量分析方法估计子波的多解性,以及地震子波的单位模长约束。对子波空间进行了单位超球面建模,进而研究了这种特定几何空间的黎曼度量及梯度,并由此构造了单位超球面上的Mean Shift聚类算法,最后依据聚类结果求取子波平均。模型实验与实际资料应用结果表明,与带状独立分量分析方法估计的地震子波相比,通过该方法估计的地震子波保真度更高,与设计子波相似度更高,反褶积处理后能够有效提高地震资料的分辨率。Seismic data can be described by convolution of seismic wavelet and reflectivity sequence in seismic explora- tion. Seismic deconvolution is essentially a blind process due to lack of priori knowledge. Wavelet estimation by BICA has multiple solutions and the solutions conform to unit norm constraint. In this paper, a wavelet space model was estab- lished on unit hypersphere and its riemannian metric and gradient were studied, then a Mean Shift clustering algorithm on unit hypersphere was presented and an average wavelet can be estimated by the clustering result. Results of synthetic data and real data show that, compared with the BICA method, estimated wavelet has higher fidelity and similarity to the designed wavelet, and real data have higher resolution after deconvolution.

关 键 词：盲反褶积 地震子波 单位超球面 黎曼梯度 Mean Shift聚类 

分 类 号：TP911[自动化与计算机技术] O186[理学—数学]