← Back to Sessions

Signal Detection With Neural Networks in Dark Fiber Seismic Data

Description: 

Distributed Acoustic Sensing (DAS) provides continuous and high-resolution spatial monitoring capabilities along the entire length of the optical fibers where the ground deformation caused by seismic activity is measured in strain or strain rate. Telecom cables, known as dark fibers, offer a spatially dense and cost-effective alternative for seismic data collection in urban areas. We demonstrated recording seismic signals with a telecom cable provided by the Istanbul Metropolitan Municipality along the Sea of Marmara on the Anatolian side of Istanbul from February to mid-March in 2023. The collected data involves various seismic signals, such as teleseismic and local earthquakes, including the East Anatolian earthquakes in February 2023 and their aftershocks, controlled explosions, traffic, and other cultural noise.

This research aims to demonstrate the detection of local seismic activity in and around Istanbul using DAS data. Monitoring local seismicity is essential to better understand the tectonics and seismic activity in a region. However, it is challenging to detect or discriminate small earthquakes where the higher spatial resolution of DAS may be advantageous. To this end, we first visually inspect all earthquakes (local and teleseismic) and compare our observations to data recorded by nearby strong-motion seismometers. Our goal is to generate a training set to detect local events with natural networks, specifically those that are difficult to observe by visual inspection. Since we have a limited data set from Istanbul, which makes the training challenging, we explore generating additional data from nearby strong-motion seismometers to be included in the training set by converting them to DAS units. To test the robustness of our tools, we will also demonstrate them with a larger data set collected in Athens by the ETH Zurich group. We will present our observations in DAS data compared to those recorded by classical seismometers in Istanbul and the initial results of our seismic event detection with neural networks for DAS.

Session: Advancing Seismology with Distributed Fiber Optic Sensing [Poster Session]

Type: Poster

Date: 5/3/2024

Presentation Time: 08:00 AM (local time)

Presenting Author: Austin

Student Presenter: Yes

Invited Presentation: 

Authors