本文主要是对k-means算法向空间的推广，是利用震源位置关于它们的中心的全局方差最小化准则将数据点集划分为群集，从而提出了一种可以通过地震目录反演地震断层的方法。通过计算每个群集全空间位置的协方差张量，将空间中的点集划分为断层形状的群集。给定地震目录，就可以输出符合数据空间结构的最优集的平面段。每个平面段在它的位置、大小和取向上都有明显的区别。该算法成功地通过了合成数据集的检验，对重构地震断层有重要意义。

The arctic is a generalization of the k-means method, that partitions a set of data points into clusters, using a global minimization criterion of the variance of the hypocenters locations about their center of mass,thus proposed a possible inversion of seismic faults by earthquake catalog methods. By calculating the covariance tensor full spatial location of each cluster, the space is divided into a cluster fault point set shape. Given a catalog of seismic events, the output is the optimal set of plane segments that fits the spatial structure of the data. Each plane segment is fully characterized by its location, size, and orientation. The algorithm has successfully passed the test of synthetic data sets, which is important to reconstruct earthquake faults.