1887
  1. Home
  2. Conferences
  3. Conference Proceedings
  4. Fifth EAGE Conference on Petroleum Geostatistics
  5. Conference paper

Abstract

Summary

Distributed acoustic sensing (DAS) is a promising technology for monitoring for instance geo-energy and geohazards applications. However, the large amount of data generated by DAS can be challenging to analyze, and there is a need for developing tools that can process data effectively for decision support systems. We propose a two-step approach for detecting events in DAS data. First, we use DBSCAN to cluster the data into groups of points that are likely to be caused by the same event. Then, we use multiple convolutional neural networks (CNNs) to classify the clusters into different event types. The proposed approach has several advantages: it is able to detect events of arbitrary shape and size, it is robust to noise, and it is able to classify events into a variety of different types. We evaluate the methods on a DAS dataset collected at the Gløshaugen campus of the Norwegian University of Science and Technology. Our results show that the approach can achieve an accuracy of 87% in classifying events.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202335049
2023-11-27
2025-07-08

  • From This Site

    /content/papers/10.3997/2214-4609.202335049
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Anwar, I., Carey, B., Johnson, P., & Donahue, C. (2022). Detecting and characterizing fluid leakage through wellbore flaws using fiber-optic distributed acoustic sensing.ARMA US Rock Mechanics/Geomechanics Symposium, ARMA–2022.
     [Google Scholar]
  2. Binder, G., & Tura, A. (2020). Convolutional neural networks for automated microseismic detection in downhole distributed acoustic sensing data and comparison to a surface geophone array.Geophysical Prospecting, 68(9), 2770–2782.
     [Google Scholar]
  3. Ester, M., Kriegel, H.-P., Sander, J., Xu, X., et al. (1996). A density-based algorithm for discovering clusters in large spatial databases with noise.kdd, 96(34), 226–231.
     [Google Scholar]
  4. He, K., Zhang, X., Ren, S., & Sun, J. (2016). Deep residual learning for image recognition.Proceedings of the IEEE conference on computer vision and pattern recognition, 770–778.
     [Google Scholar]
  5. Lee, D., Aune, E., Langet, N., & Eidsvik, J. (2023). Ensemble and self-supervised learning for improved classification of seismic signals from the Åknes rockslope.Mathematical Geosciences, 55(3), 377–400.
     [Google Scholar]
  6. Pedersen, Å., Westerdahl, H., Thompson, M., Sagary, C., & Brenne, J. (2022). A north sea case study: Does das have potential for permanent reservoir monitoring?83rd EAGE Annual Conference & Exhibition, 2022(1), 1–5.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202335049
Loading
Detecting Events in Distributed Acoustic Sensing Data Using DBSCAN and CNNs
Conference Proceedings 2023, 1 (2023); https://doi.org/10.3997/2214-4609.202335049
/content/papers/10.3997/2214-4609.202335049
/content/papers/10.3997/2214-4609.202335049
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error