Facing massive seismic data,it is urgent to automatically detect earthquakes and determine their arrival times accurately.Based on the support vector machine technology,we developed a method by using two classifiers SSD and SPS to automatically identify seismic body-wave phases and automatically determine their arrival times.Compared with the traditional automatic phasepicking methods,our method can more accurately identify both the seismic phases from noises,and the S phases from P phases.Moreover,we employ the array strategy to further effectively improve the accuracy of phase-detection.%面对海量地震资料,自动准确地拾取震相并确定其到时的需求非常迫切.基于支持向量机技术,本文提出了使用两个分类器SSD和SPS自动识别地震体波震相并自动拾取其到时的方法.相比于传统的自动拾取方法,本文方法能够更准确地识别震相并区分P波和S波.进一步地,我们提出了利用台阵资料辅助识别震相的方案,有效地提高了地震震相拾取的准确率.
展开▼
