| 地震预警现地PGV连续预测的最小二乘支持向量机模型 |
| |
| 引用本文： | 宋晋东,余聪,李山有.地震预警现地PGV连续预测的最小二乘支持向量机模型[J].地球物理学报,2021,64(2):555-568. |
| |
| 作者姓名： | 宋晋东 余聪 李山有 |
| |
| 作者单位： | 中国地震局工程力学研究所,哈尔滨150080;中国地震局地震工程与工程振动重点实验室,哈尔滨150080;中国地震局工程力学研究所,哈尔滨150080;中国地震局地震工程与工程振动重点实验室,哈尔滨150080;中国地震局工程力学研究所,哈尔滨150080;中国地震局地震工程与工程振动重点实验室,哈尔滨150080 |
| |
| 摘 要： | 为提升现地仪器地震烈度预测的准确性与连续性,研究面向地震预警的PGV连续预测模型.以中国仪器地震烈度标准的计算参数:0.1~10 Hz带通滤波三分向矢量合成速度峰值PGV为预测目标,利用日本K-net与KiK-net台网P波触发后1~10 s强震数据,基于人工智能中的机器学习方法-最小二乘支持向量机,选取7种特征参数作为输入构建最小二乘支持向量机PGV预测模型LSSVM-PGV.结果表明,本文建立的LSSVM-PGV模型在训练数据集与测试数据集上的预测误差标准差变化趋于一致,具备泛化性能;P波触发后3 s预测PGV与实测PGV即可整体符合1∶1关系,随着时间窗的增长,PGV预测的误差标准差显著减小、并在P波触发后6 s趋向收敛,具备准确连续预测能力;对比同为P波触发后3 s的常用P d-PGV模型,LSSVM-PGV模型的PGV预测误差标准差明显减小,“小值高估”与“大值低估”现象明显改善,预测准确性得到提升.熊本地震序列的震例分析表明,对于6.5级以下地震,LSSVM-PGV模型最多在P波触发后3 s即可预测出与实测PGV整体符合1∶1关系的PGV;对于7.3级主震,由于其破裂过程的复杂性,P波触发后3 s的预测结果出现一定程度的低估,但随着时间窗增长至6 s时,预测PGV与实测PGV符合1∶1关系、并直到10 s整体趋势保持一致.本文构建的LSSVM-PGV模型可用于现地地震预警仪器地震烈度的预测.
|
| 关 键 词： | 最小二乘支持向量机 现地 地震预警 速度峰值PGV 熊本地震序列 |
Continuous prediction of onsite PGV for earthquake early warning based on least squares support vector machine |
| |
| SONG JinDong,YU Cong,LI ShanYou.Continuous prediction of onsite PGV for earthquake early warning based on least squares support vector machine[J].Chinese Journal of Geophysics,2021,64(2):555-568. |
| |
| Authors: | SONG JinDong YU Cong LI ShanYou |
| |
| Institution: | (Institute of Engineering Mechanics,China Earthquake Administration,Harbin 150080,China;Key Laboratory of Earthquake Engineering and Engineering Vibration of China Earthquake Administration,Harbin 150080,China) |
| |
| Abstract: | In order to improve the accuracy and continuity of the on-site instrumental seismic intensity prediction,studying the PGV continuous prediction model for earthquake early warning.Predicting the 0.1~10 Hz band-pass filtered three-components vector synthetic peak velocity,the Chinese instrument seismic intensity standard,using the Japanese K-net and KiK-net network strong earthquake data in the 1~10 s time window after P wave arrivals,based on the machine learning method in artificial intelligence,least squares support vector machine,selecting 7 kinds of feature parameters as input to construct the least squares support vector machine PGV prediction model LSSVM-PGV.The results show that the prediction error standard deviation of the LSSVM-PGV model established in this paper on the training data set and the test data set tends to be consistent,LSSVM-PGV model has generalization performance.The predicted PGV and the measured PGV in 3 s after P wave arrivals can meet the 1∶1 relationship as a whole,as the time window increases,the standard deviation of the PGV prediction error decreases significantly,and tends to converge in 6 s after P wave arrivals,this shows that the LSSVM-PGV model has accurate continuous prediction capabilities.Compared with the common P d-PGV model that is also the 3 s after P wave arrivals,the standard deviation of the PGV prediction error of the LSSVM-PGV model is significantly reduced,“overestimation on small value”and“underestimation on large value”phenomena have been significantly improved,and prediction accuracy has been improved.The analysis of earthquake examples of the Kumamoto earthquake sequence shows that for earthquakes below M j6.5,the LSSVM-PGV model can predict a PGV that conforms to the 1∶1 relationship with the measured PGV overall at most 3 s after P wave arrivals.For the M j7.3 main shock,due to the complexity of its rupture process,the predicted results in 3 s after P wave arrivals are somewhat underestimated,but as the time window grows to 6 s,the predicted PGV and the measured PGV are in a 1∶1 relationship,and the overall trend remains consistent until 10 s.The LSSVM-PGV model constructed in this paper can be used to predict the instrumental seismic intensity of on-site earthquake early warning. |
| |
| Keywords: | Least squares support vector machine On-site Earthquake early warning PGV Kumamoto earthquake sequence |
| 本文献已被 CNKI 维普 万方数据 等数据库收录！ |
|
