An official website of the United States government
Abstract Distributed Acoustic Sensing (DAS) is an emerging technology for earthquake monitoring and subsurface imaging. However, its distinct characteristics, such as unknown ground coupling and high noise level, pose challenges to signal processing. Existing machine learning models optimized for conventional seismic data struggle with DAS data due to its ultra-dense spatial sampling and limited manual labels. We introduce a semi-supervised learning approach to address the phase-picking task of DAS data. We use the pre-trained PhaseNet model to generate noisy labels of P/S arrivals in DAS data and apply the Gaussian mixture model phase association (GaMMA) method to refine these noisy labels and build training datasets. We develop PhaseNet-DAS, a deep learning model designed to process 2D spatio-temporal DAS data to achieve accurate phase picking and efficient earthquake detection. Our study demonstrates a method to develop deep learning models for DAS data, unlocking the potential of integrating DAS in enhancing earthquake monitoring.
more »
« less
An autoencoder-based deep learning model for enhancing noise characterization and microseismic event detection in underground longwall coal mines using distributed acoustic sensing monitoring
The longwall mining method is designed to optimize coal extraction through controlled roof caving, which inevitably induces seismicity. This research employs a distributed acoustic sensing (DAS) system incorporating a fire-safe fiber-optic cable strategically installed underground within an operational longwall coal mine. Despite lower sensitivity than traditional seismometers, DAS sensing technology benefits from dense sensor spacing and close proximity to the active face, where many microseismic events occur. To automatically detect seismic events within the voluminous DAS data records, we employ convolutional autoencoder deep learning models that can be used for anomaly (potential seismic event) detection in power spectral density (PSD) images of DAS recordings. The kernel density estimation (KDE) technique is used to calculate the probability density function (PDF) for the density scores of the latent space (representation of compressed data). We then use this calculated parameter as a threshold to distinguish between the PSD associated with background noise and with potential seismic events. The DAS monitoring system in conjunction with the developed deep learning model could enhance longwall coal mining safety and efficiency by offering valuable data from its densely deployed multichannel sensors near mining operations.
more »
« less
- Award ID(s):
- 2310948
- PAR ID:
- 10525717
- Publisher / Repository:
- ARMA, American Rock Mechanics Association
- Date Published:
- Format(s):
- Medium: X
- Location:
- Golden, Colorado
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Internal structures of the Moon are key to understanding the origin and evolution of the Earth–Moon system and other planets. The Apollo Passive Seismic Experiment detected thousands of lunar seismic events and vastly improved our understanding of the Moon’s interior. However, some critical questions like the state and composition of the core remain unsolved largely due to the sparsity of the Apollo seismic stations and the strong scattering of seismic waves in the top layer of the Moon. In this study, we propose the concept of a fiber seismic network on the Moon and discuss its potential in overcoming the challenges in imaging deep Moon structures. As an emerging technique, distributed acoustic sensing (DAS) can provide a cost-efficient solution for large-aperture and dense seismic network deployment in harsh environments. We compute lunar synthetic seismograms and evaluate the performance of DAS arrays of different configurations in retrieving the hidden core reflected seismic phase ScS from the strong scattered waves. We find that, compared to a sparse conventional seismic network, a fiber seismic network using tens of kilometers of cable can dramatically increase the chance of observing clear ScS by array stacking. Our results indicate that DAS could provide new opportunities for the future lunar seismic surveys, but more efforts and further evaluations are required to develop a space-proof DAS.more » « less
-
SUMMARY In this study, I demonstrate that distributed acoustic sensing (DAS) raw strain rate data can directly be used to estimate spectral source parameters through an Empirical Green's Function (EGF) deconvolution analysis. Previously, DAS had been widely used in passive seismology to image the subsurface and analyze ground motion variations by converting strain or strain rate to particle velocity or acceleration prior to analysis. In this study, spectral analysis is applied to the PoroTomo joint DAS and seismic Nodal array in the Brady Hot Springs geothermal field to obtain source parameters for two M4 earthquakes via EGF analysis, where nearly collocated smaller events are used as an EGF to remove path and site effects. The EGF workflow is applied to raw DAS strain rate data without conversion to particle velocities and raw Nodal seismic data. The DAS and Nodal results are very consistent with similar features of spectral ratios, corner frequencies and moment ratios for the same event pairs. The uncertainty due to stacked spectral measurement is much lower on the DAS array, suggesting better stability of spectral shape measurement, possibly due to the much denser spatial sampling. The uncertainty due to model fitting is similar between DAS and Nodal arrays with slightly lower uncertainty on the DAS array. These observations demonstrate potential for directly using the strain rate measurements from DAS arrays for earthquake source characterizations.more » « less
-
ABSTRACT Distributed acoustic sensing (DAS) technology is an emerging field of seismic sensing that enables recording ambient noise seismic data along the entire length of a fiber-optic cable at meter-scale resolution. Such a dense spatial resolution of recordings over long distances has not been possible using traditional methods because of limited hardware resources and logistical concerns in an urban environment. The low spatial resolution of traditional passive seismic acquisition techniques has limited the accuracy of the previously generated velocity profiles in many important urban regions, including the Reno-area basin, to the top 100 m of the underlying subsurface. Applying the method of seismic interferometry to ambient noise strain rate data obtained from a dark-fiber cable allows for generating noise cross correlations, which can be used to infer shallow and deep subsurface properties and basin geometry. We gathered DAS ambient noise seismic data for this study using a 12 km portion of a dark-fiber line in Reno, Nevada. We used gathered data to generate and invert dispersion curves to estimate the near-surface shear-wave velocity structure. Comparing the generated velocity profiles with previous regional studies shows good agreement in determining the average depth to bedrock and velocity variations in the analyzed domain. A synthetic experiment is also performed to verify the proposed framework further and better understand the effect of the infrastructural cover along the cable. The results obtained from this research provide insight into the application of DAS using dark-fiber lines in subsurface characterization in urban environments. It also discusses the potential effects of the conduit that covers such permanent fiber installations on the produced inversion results.more » « less
-
Abstract New technologies such as low-cost nodes and distributed acoustic sensing (DAS) are making it easier to continuously collect broadband, high-density seismic monitoring data. To reduce the time to move data from the field to computing centers, reduce archival requirements, and speed up interactive data analysis and visualization, we are motivated to investigate the use of lossy compression on passive seismic array data. In particular, there is a need to not only just quantify the errors in the raw data but also the characteristics of the spectra of these errors and the extent to which these errors propagate into results such as detectability and arrival-time picks of microseismic events. We compare three types of lossy compression: sparse thresholded wavelet compression, zfp compression, and low-rank singular value decomposition compression. We apply these techniques to compare compression schemes on two publicly available datasets: an urban dark fiber DAS experiment and a surface DAS array above a geothermal field. We find that depending on the level of compression needed and the importance of preserving large versus small seismic events, different compression schemes are preferable.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Proceeding:
- The DOI is not currently available.
