Hybrid Event Detection and Phase-Picking Algorithm Using Convolutional and Recurrent Neural Networks

Zhou Yijian; Yue Han; Kong Qingkai; Zhou Shiyong

首页> 外文期刊>Seismological research letters >Hybrid Event Detection and Phase-Picking Algorithm Using Convolutional and Recurrent Neural Networks

【24h】

Hybrid Event Detection and Phase-Picking Algorithm Using Convolutional and Recurrent Neural Networks

机译：使用卷积和经常性神经网络的混合事件检测和相位拣选算法

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

We developed a hybrid algorithm using both convolutional and recurrent neural networks (CNNs and RNNs, respectively) to pick phases from archived continuous waveforms in two steps. First, an eight-layer CNN is trained to detect earthquake events from 30-second-long three-component seismograms. The event seismograms are then sent to a two-layer bidirectional RNN to pick P- and S-arrival times. The data for training and validation and testing of the networks are obtained from the continuous waveforms of 16 stations recording the aftershock sequence of the 2008 Wenchuan earthquake. The augmented training set has 135,966 P-S-wave arrival-time pairs. The CNN achieved 94% and 98% hit rate for event and noise segments in the test set, respectively. The RNN picking accuracies for P- and S waves are -0.03 +/- 0.48 (mean error +/- standard deviation) and 0.03 +/- 0.56 s, respectively.

机译：我们使用卷积和经常性神经网络（CNNS和RNN）的杂交算法开发了两个步骤中的归档连续波形的阶段。首先，训练八层CNN以检测来自30秒长的三组分地震图的地震事件。然后将事件地图发送到两层双向RNN以选择P-和S到达时间。用于训练和验证和测试网络的数据是从16个站点记录2008年汶川地震的余震序列的连续波形获得的。增强培训集具有135,966个P-S波到达 - 时间对。 CNN分别为试验集中的事件和噪声段进行了94％和98％的命中率。对于P - 和S波的RNN挑选精度分别为-0.03 +/- 0.48（平均误差+/-标准偏差）和0.03 +/- 0.56秒。

著录项

来源
《Seismological research letters》 |2019年第3期|共9页
作者
Zhou Yijian; Yue Han; Kong Qingkai; Zhou Shiyong;
展开▼
作者单位

Peking Univ Sch Earth &

Space Sci 5 Yiheyuan Rd Beijing 100871 Peoples R China;

Peking Univ Sch Earth &

Space Sci 5 Yiheyuan Rd Beijing 100871 Peoples R China;

Univ Calif Berkeley Berkeley Seismol Lab 209 McCone Hall Berkeley CA 94720 USA;

Peking Univ Sch Earth &

Space Sci 5 Yiheyuan Rd Beijing 100871 Peoples R China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类地震学;
关键词

相似文献

外文文献
中文文献
专利

1. Hybrid Event Detection and Phase-Picking Algorithm Using Convolutional and Recurrent Neural Networks [J] . Zhou Yijian, Yue Han, Kong Qingkai, Seismological research letters . 2019,第3期

机译：使用卷积和经常性神经网络的混合事件检测和相位拣选算法
2. Bidirectional LSTM Malicious webpages detection algorithm based on convolutional neural network and independent recurrent neural network [J] . Wang Huan-huan, Yu Long, Tian Sheng-wei, Applied Intelligence: The International Journal of Artificial Intelligence, Neural Networks, and Complex Problem-Solving Technologies . 2019,第8期

机译：基于卷积神经网络和独立复发神经网络的双向LSTM恶意网页检测算法
3. Adverse Drug Event Detection Using a Weakly Supervised Convolutional Neural Network and Recurrent Neural Network Model [J] . Min Zhang, Guohua Geng Information . 2019,第9期

机译：使用弱监督卷积神经网络和递归神经网络模型的药品不良事件检测
4. Detection of Cardiac Events in Echocardiography Using 3D Convolutional Recurrent Neural Networks [C] . Adrian MeidellFiorito, Andreas Østvik, Erik Smistad, IEEE International Ultrasonics Symposium . 2018

机译：使用3D卷积递归神经网络在超声心动图中检测心脏事件
5. Convolutional and recurrent neural networks for pedestrian detection [D] . Balaji, Vivek Arvind. 2016

机译：用于行人检测的卷积和经常性神经网络
6. Convolutional Recurrent Neural Network-Based Event Detection in Tunnels Using Multiple Microphones [O] . Nam Kyun Kim, Kwang Myung Jeon, Hong Kook Kim 2019

机译：基于多麦克风的基于卷积递归神经网络的隧道事件检测
7. Detection of Bleeding Events in Electronic Health Record Notes Using Convolutional Neural Network Models Enhanced With Recurrent Neural Network Autoencoders: Deep Learning Approach [O] . Rumeng Li, Baotian Hu, Feifan Liu, 2019

机译：用经常性神经网络自动化器增强卷积神经网络模型检测电子健康记录笔记中的出血事件：深度学习方法

Hybrid Event Detection and Phase-Picking Algorithm Using Convolutional and Recurrent Neural Networks

摘要

著录项

相似文献

相关主题

期刊订阅