【摘要】 本文阐述了支持向量回归(SVR)理论及其特性,提出了基于SVR的次年最大震级的预测方法,并对所选样本进行训练和预测,结果与实际值符合较好,理论分析和实例结果验证了基于SVR的震级预测方法比BP神经网络具有更高的预测精度和可靠性。更多还原

【Abstract】 This article introduces the basic theory and characteristics of Support Vector Regression(SVR) and advances a method to predict the next year biggest earthquake based on SVR.This method has been applied to our selected data set,and the forecasts are in good agreement with the measurement results.The comparison indicates that the accuracy and reliability of the SVR method are better than those of BP neural network method.更多还原