Detecting micro fractures: a comprehensive comparison of conventional and machine-learning-based segmentation methods

Lee, Dongwon; Karadimitriou, Nikolaos; Ruf, Matthias; Steeb, Holger

doi:https://doi.org/10.5194/se-13-1475-2022

Articles | Volume 13, issue 9

https://doi.org/10.5194/se-13-1475-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

https://doi.org/10.5194/se-13-1475-2022

© Author(s) 2022. This work is distributed under
the Creative Commons Attribution 4.0 License.

Articles | Volume 13, issue 9

Research article

|

27 Sep 2022

Research article |

| 27 Sep 2022

Detecting micro fractures: a comprehensive comparison of conventional and machine-learning-based segmentation methods

Dongwon Lee, Nikolaos Karadimitriou, Matthias Ruf, and Holger Steeb

Download

Final revised paper (published on 27 Sep 2022)
Preprint (discussion started on 01 Jun 2022)

Interactive discussion

Status: closed

RC1:
'Comment on egusphere-2022-400', Anonymous Referee #1, 03 Jul 2022

Dear authors,

I much enjoyed reading your paper, which was well-written and presented. Please find my review, attached.

Best regards,

Citation: https://doi.org/10.5194/egusphere-2022-400-RC1
- AC1: 'Reply on RC1', Dongwon Lee, 08 Aug 2022
  
  Dear Reviewer,
  We would like to thank you very much for your insightful comments. We believe that after the review process our article has significantly improved.
  We trust that we have adequately addressed your comments/remarks/concerns in the revised article. We believe that after having performed the necessary improvements, the article can be considered for publication with the journal.
  Once again, thank you very much for your assistance in total.
  Sincerely yours,
  Dongwon Lee, Nikolaos Karadimitriou, Matthias Ruf & Holger Steeb.
  
  Citation: https://doi.org/10.5194/egusphere-2022-400-AC1
RC2:
'Comment on egusphere-2022-400', Anonymous Referee #2, 05 Jul 2022

Dear editor/authors,

I have found this work highly relevant, well-written and structured. Therefore, I would like to recommend it for publication. Please find attached some minor commets.

Kind regards.

Citation: https://doi.org/10.5194/egusphere-2022-400-RC2
- AC2: 'Reply on RC2', Dongwon Lee, 08 Aug 2022
  
  Dear Reviewer,
  We would like to thank you very much for your insightful comments. We believe that after the review process our article has significantly improved.
  We trust that we have adequately addressed your comments/remarks/concerns in the revised article. We believe that after having performed the necessary improvements, the article can be considered for publication with the journal.
  Once again, thank you very much for your assistance in total.
  Sincerely yours,
  Dongwon Lee, Nikolaos Karadimitriou, Matthias Ruf & Holger Steeb.
  
  Citation: https://doi.org/10.5194/egusphere-2022-400-AC2

Peer review completion

AR: Author's response | RR: Referee report | ED: Editor decision | EF: Editorial file upload

AR by Dongwon Lee on behalf of the Authors (08 Aug 2022) Author's response Author's tracked changes Manuscript

ED: Publish as is (15 Aug 2022) by David Healy

ED: Publish as is (15 Aug 2022) by Federico Rossetti (Executive editor)

AR by Dongwon Lee on behalf of the Authors (16 Aug 2022)

Short summary

This research article focuses on filtering and segmentation methods employed in high-resolution µXRCT studies for crystalline rocks, bearing fractures, or fracture networks, of very small aperture. Specifically, we focus on the identification of artificially induced (via quenching) fractures in Carrara marble samples. Results from the same dataset from all five different methods adopted were produced and compared with each other in terms of their output quality and time efficiency.