%0 Journal Article
%9 ACL : Articles dans des revues avec comité de lecture répertoriées par l'AERES
%A van den Ende, M. P. A.
%A Ampuero, Jean-Paul
%T Automated seismic source characterization using deep graph neural networks
%D 2020
%L fdi:010079752
%G ENG
%J Geophysical Research Letters
%@ 0094-8276
%K earthquake source seismology ; machine learning ; graphs
%M ISI:000572406100035
%N 17
%P e2020GL088690 [11 ]
%R 10.1029/2020gl088690
%U https://www.documentation.ird.fr/hor/fdi:010079752
%> https://www.documentation.ird.fr/intranet/publi/2020/10/010079752.pdf
%V 47
%W Horizon (IRD)
%X 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.
%$ 066 ; 122