Spatial Deep Deconvolution U-Net for Traffic Analyses with Distributed Acoustic Sensing

no code implementations • 7 Dec 2022 • Siyuan Yuan, Martijn van den Ende, Jingxiao Liu, Hae Young Noh, Robert Clapp, Cédric Richard, Biondo Biondi

In response, we introduce a self-supervised U-Net model that can suppress background noise and compress car-induced DAS signals into high-resolution pulses through spatial deconvolution.

Automated Seismic Source Characterisation Using Deep Graph Neural Networks

1 code implementation • 16 Sep 2020 • Martijn van den Ende, Jean-Paul Ampuero

Most seismological analysis methods require knowledge of the geographic location of the stations comprising a seismic network.

BIG-bench Machine Learning Graph Neural Network +1