地震到达时间采集分布式声学传感数据,使用半监督学习
Weiqiang Zhu1,2, Ettore Biondi3, Jiaxuan Li3
1Seismological Laboratory, Division of Geological and Planetary Sciences, California Institute of Technology, Pasadena, CA, USA. zhuwq@berkeley.edu.
Nature communications
|December 11, 2023
概括
我们开发了一种半监督的深度学习方法,PhaseNet-DAS,以使用分布式声学传感 (DAS) 数据改善地震检测. 这种方法解决了DAS信号处理方面的挑战,增强了地震监测能力.
科学领域:
- 地质物理学 地质物理学
- 地震学 地震学
- 机器学习 机器学习
背景情况:
- 分布式声学传感 (DAS) 为地震监测和地下成像提供了新的功能.
- DAS数据带来了独特的挑战,包括高噪音水平和未知的地面合,阻碍了传统的地震信号处理.
- 现有的机器学习模型在与DAS数据的超密度空间采样和有限的标记示例作斗争.
研究的目的:
- 开发一种强大的半监督学习方法,用于在分布式声学传感 (DAS) 数据中准确地选择相位.
- 创建一个专门的深度学习模型,PhaseNet-DAS,适合处理2D时空DAS数据.
- 通过利用DAS技术来提高地震检测效率和准确性.
主要方法:
- 使用预训练的PhaseNet模型生成DAS数据中P/S波到达的初始标签,尽管噪音很大.
- 采用高斯混合模型相关联 (GaMMA) 方法来完善这些噪音标签并构建可靠的训练数据集.
- 开发和实施了PhaseNet-DAS,这是一种专门为二维时空DAS数据分析而设计的深度学习架构.
主要成果:
- 通过半监督方法成功生成了用于DAS数据的精细训练数据集.
- 从DAS数据直接获得地震到达的精确相位选择.
- 使用开发的PhaseNet-DAS模型展示了高效的地震检测能力.
结论:
- 拟议的半监督学习方法有效地解决了处理用于地震应用的DAS数据的挑战.
- 使用DAS,PhaseNet-DAS提供了一种可行的深度学习解决方案,用于使用DAS准确的相位选择和地震检测.
- 这项研究为整合DAS技术铺平了道路,以显著增强地震监测系统.
更多相关视频
06:01Semi-Automated Analysis of Peak Amplitude and Latency for Auditory Brainstem Response Waveforms Using R
Published on: December 9, 2022
2.5K
09:09Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
459
相关概念视频
01:20Cluster Sampling Method
Appropriate sampling methods ensure that samples are drawn without bias and accurately represent the population. Because measuring the entire population in a study is not practical, researchers use samples to represent the population of interest.
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
To choose a cluster sample, divide the population into clusters (groups) and then randomly select some of the clusters. All the members from these clusters are in the cluster sample. For example, if you randomly sample four departments from your...
01:11Sampling Continuous Time Signal
In signal processing, a continuous-time signal can be sampled using an impulse-train sampling technique, followed by the zero-order hold method. Impulse-train sampling involves the use of a periodic impulse train, which consists of a series of delta functions spaced at regular intervals determined by the sampling period. When a continuous-time signal is multiplied by this impulse train, it generates impulses with amplitudes corresponding to the signal's values at the sampling points.
In the...
In the...