气候变化领域集成服务门户(CCPortal): Automated Seismic Source Characterization Using Deep Graph Neural Networks

CCPortal

DOI	10.1029/2020GL088690
	Automated Seismic Source Characterization Using Deep Graph Neural Networks
	van den Ende M.P.A.; Ampuero J.-P.
发表日期	2020
ISSN	0094-8276
卷号	47 期号:17
英文摘要	Most seismological analysis methods require knowledge of the geographic location of the stations comprising a seismic network. However, common machine learning tools used in seismology do not account for this spatial information, and so there is an underutilized potential for improving the performance of machine learning models. In this work, we propose a graph neural network (GNN) approach that explicitly incorporates and leverages spatial information for the task of seismic source characterization (specifically, location and magnitude estimation), based on multistation waveform recordings. Even using a modestly-sized GNN, we achieve model prediction accuracy that outperforms methods that are agnostic to station locations. Moreover, the proposed method is flexible to the number of seismic stations included in the analysis and is invariant to the order in which the stations are arranged, which opens up new applications in the automation of seismological tasks and in earthquake early warning systems. ©2020. American Geophysical Union. All Rights Reserved.
英文关键词	Deep neural networks; Earthquakes; Location; Machine learning; Earthquake early warning systems; Geographic location; Graph neural networks; Machine learning models; Magnitude estimation; Seismic networks; Spatial informations; Waveform recording; Neural networks; artificial neural network; automation; earthquake event; knowledge; machine learning; prediction; seismic source; seismology; waveform analysis
语种	英语
来源期刊	Geophysical Research Letters
文献类型	期刊论文
条目标识符	http://gcip.llas.ac.cn/handle/2XKMVOVA/169835
作者单位	IRD, CNRS, Observatoire de la Côte d'Azur, Université Côte d'Azur, Géoazur, France
推荐引用方式 GB/T 7714	van den Ende M.P.A.,Ampuero J.-P.. Automated Seismic Source Characterization Using Deep Graph Neural Networks[J],2020,47(17).
APA	van den Ende M.P.A.,&Ampuero J.-P..(2020).Automated Seismic Source Characterization Using Deep Graph Neural Networks.Geophysical Research Letters,47(17).
MLA	van den Ende M.P.A.,et al."Automated Seismic Source Characterization Using Deep Graph Neural Networks".Geophysical Research Letters 47.17(2020).