欢迎访问《地震》,

地震 ›› 2008, Vol. 28 ›› Issue (3): 55-60.

• • 上一篇    下一篇

地震前兆综合预测支持向量机模型研究

武安绪1, 张永仙2, 张晓东2, 李平安1, 穆会泳1, 鲁亚军1   

  1. 1.北京市地震局, 北京 100080;
    2.中国地震台网中心, 北京 100045
  • 收稿日期:2007-09-27 修回日期:2007-12-21 出版日期:2008-07-31 发布日期:2021-10-29
  • 作者简介:武安绪(1967-), 男, 河南邓州人, 副研究员, 主要从事地震预测与系统等研究。
  • 基金资助:
    国家科技攻关项目(2006BAC01B03-04-04; 03-02-03); 地震科学联合基金(A07058)

Study on model of support vector machine for synthetic prediction of seismic precursors

WU An-xu1, ZHANG Yong-xian2, ZHANG Xiao-dong2, LI Ping-an1, MU Hui-yong1, LU Ya-jun1   

  1. 1. Earthquake Administration of Beijing Municipality, Beijing 100080;
    2. China Earthquake Networks Center, CEA, Beijing 100045, China
  • Received:2007-09-27 Revised:2007-12-21 Online:2008-07-31 Published:2021-10-29

摘要: 该文介绍了支持向量机算法的原理与回归方法。 采用支持向量机中的非线性回归算法与理论公式产生的多维样本, 对其进行了数值仿真实验。 利用该方法和地震前兆异常建立了最佳地震综合预测模型, 对获得的最佳模型进行了内符检验, 得出最佳模型的预测结果与实际震例的地震震级基本一致。 综合分析认为, 支持向量机无论在学习或者预测精度方面不但具有很大的优越性和具有较强的外推泛化能力, 而且基于支持向量机回归算法建立的地震前兆综合预测模型是可行的, 其获得的知识可较为准确地实现对主震震级的综合预测。

关键词: 支持向量机, 地震前兆, 典型震例, 综合预测

Abstract: The principle of support vector machine (SVM) and its regression algorithm is introduced in this paper. The multidimensional samples from theoretical formula are tested by using of SVM. The best model for synthetic prediction of seismic precursors is established according to the SVM algorithm and the seismic precursory anomalies, and it is tested by using of the testing samples. It indicates that the forecast result of the best mode and earthquake magnitude of real seismic examples are basically consistent. It shows that the support vector machine algorithm has an obvious superiority whatever on machine learning or prediction accuracy, and the model for synthetic prediction of seismic precursors based on the SVM theory is feasible, and it can forecast the magnitude of main earthquakes more accurately.

Key words: Support vector machine (SVM), Seismic cursor, Typical earthquake example, Synthetic forecast

中图分类号: