Research on Early Judgment of Earthquake Sequence Types Based on SVM
详细信息
- 责任者：Li Dongmei (Lanzhou Institute of Seismology ; CEA ; Lanzhou 730000 ; China) ; Zhou Cuiying
- 刊名：Journal of Seismological Research
- 出版年：2013
- 卷期：36(1)
- 关键词：地震序列 ; seismic sequence ; 地震预测 ; earthquake prediction ; 中国 ; China
- 页码：p.69-73
- 图表：illus., 4 tables, 13 refs.
- 分类号：0500
- issnNo：ISSN1000-0666
- isbnNo：CN53-1062/P
摘要
In the environment of Matlab, we construct Support Vector Machine （SVM） to build a kind of nonlinear mapping relationship between seismic sequence characteristic parameter and sequence type, and do the early pre- dictions of earthquake sequence types. On the basis of Ms≥5.0 earthquake sequences in China since 1970, we divide the data in 5 time scales according to one, two, three, five and seven days after the earthquake and apply the SVM to the early predictions of earthquake sequence types. The results show that it achieves good recognition and fast processing speed, and has a strong practicability.