GSM-SVM在地震震级预测中的应用

针对地震震级影响因子众多且关系重复等问题,为合理预测地震震级,提出了基于网格搜索法优化支持向量机(support vector machine,SVM)的地震震级预测模型。选取地震累积频度、累积释放能量、b值、异常震群个数、地震条带个数、活动周期和相关区震级等7个影响因子,利用主成分分析法(principal component analysis,PCA)去除因子间的冗余信息,降低输入维数,并利用网格搜索法(grid search method,GSM)确定SVM参数C和g,建立震级预测模型,并对测试样本进行预测,与遗传算法(genetic algorithm,GA)和粒子群算法(particle swarm optimization,PSO)预测结果相对比,结果表明:PCA-GSM-SVM模型预测结果平均相对误差为1.29%,具有较高的预测精度。

THE RELATION BETWEEN MAGNITUDE AND FREQUENCY IN ROCKBURST AND ITS APPLICATION IN FORECASTING

The rockburst data of Huafeng and Da’anshan Mine were analysised in this paper. From the statistical results, we know that the relation between magnitude and frequency in rockburst is linear. Using this relation, the maximum magnitude and tendency of rockburst can be predicted.The theory can improve the quantitive prediction level in rockburst.