基于Bagging集成学习算法的地震事件性质识别分类

地震台网在监测地震的同时记录到的非天然震动事件会对后续的科研和预报工作造成较大的影响, 因此快速准确的对天然震动事件与非天然震动事件加以区分就显得尤为重要.本文针对传统人工方法识别地震事件性质的不足之处, 采用Bagging机器学习算法对地震事件性质进行区分.首先选取震中距范围在80~200 km内的地震数据, 之后采用AIC算法自动识别P波到时, 进而用处理后的数据训练模型, 最后使用测试数据对模型进行评估, 准确率可达85%以上.因此, 本文提出的方法可以有效地对天然震动事件与非天然震动事件加以区分.

Seismic event classification based on bagging ensemble learning algorithm

The non-natural vibration events recorded by the Seismic Network while monitoring the earthquake will have a greater impact on the subsequent research and forecasting work. Therefore, it is particularly important to distinguish between natural earthquakes and non-natural vibration events quickly and accurately. In this paper, the Bagging machine learning algorithm is used to distinguish the nature of earthquake events, to improve the inadequacies of traditional artificial methods to identify the nature of earthquake events. Firstly, the seismic data with the epicenter distance in the range of 80~200 km is selected. Then, the AIC algorithm is utilized to automatically identify the arrival time of the P wave. After that, the processed data is used to train the model. Finally, the model is evaluated using the test data, and the accuracy rate is up to 85%. The method proposed in this paper can effectively distinguish between natural earthquakes and non-natural vibration events.