Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks
- Publikationstyp:
- Zeitschriftenaufsatz
- Metadaten:
-
- Autoren
- Marcel Reinhardt
- Arne Jacob
- Saeid Sadeghnejad
- Francesco Cappuccio
- Pit Arnold
- Sascha Frank
- Frieder Enzmann
- Michael Kersten
- Autoren-URL
- https://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=fis-test-1&SrcAuth=WosAPI&KeyUT=WOS:000746656100009&DestLinkType=FullRecord&DestApp=WOS_CPL
- DOI
- 10.1007/s12665-021-10133-7
- eISSN
- 1866-6299
- Externe Identifier
- Clarivate Analytics Document Solution ID: YM6AU
- ISSN
- 1866-6280
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- ENVIRONMENTAL EARTH SCIENCES
- Schlüsselwörter
- Fracture segmentation
- Quality
- Digital rock physics
- Random forest algorithm
- Convolutional neural network
- Image processing
- Artikelnummer
- ARTN 71
- Datum der Veröffentlichung
- 2022
- Status
- Published
- Titel
- Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks
- Sub types
- Article
- Ausgabe der Zeitschrift
- 81
Datenquelle: Web of Science (Lite)
- Andere Metadatenquellen:
-
- Abstract
- <jats:title>Abstract</jats:title><jats:p>Image segmentation remains the most critical step in Digital Rock Physics (DRP) workflows, affecting the analysis of physical rock properties. Conventional segmentation techniques struggle with numerous image artifacts and user bias, which lead to considerable uncertainty. This study evaluates the advantages of using the random forest (RF) algorithm for the segmentation of fractured rocks. The segmentation quality is discussed and compared with two conventional image processing methods (thresholding-based and watershed algorithm) and an encoder–decoder network in the form of convolutional neural networks (CNNs). The segmented images of the RF method were used as the ground truth for CNN training. The images of two fractured rock samples are acquired by X-ray computed tomography scanning (XCT). The skeletonized 3D images are calculated, providing information about the mean mechanical aperture and roughness. The porosity, permeability, flow fields, and preferred flow paths of segmented images are analyzed by the DRP approach. Moreover, the breakthrough curves obtained from tracer injection experiments are used as ground truth to evaluate the segmentation quality of each method. The results show that the conventional methods overestimate the fracture aperture. Both machine learning approaches show promising segmentation results and handle all artifacts and complexities without any prior CT-image filtering. However, the RF implementation has superior inherent advantages over CNN. This method is resource-saving (e.g., quickly trained), does not need an extensive training dataset, and can provide the segmentation uncertainty as a measure for evaluating the segmentation quality. The considerable variation in computed rock properties highlights the importance of choosing an appropriate segmentation method.</jats:p>
- Autoren
- Marcel Reinhardt
- Arne Jacob
- Saeid Sadeghnejad
- Francesco Cappuccio
- Pit Arnold
- Sascha Frank
- Frieder Enzmann
- Michael Kersten
- DOI
- 10.1007/s12665-021-10133-7
- eISSN
- 1866-6299
- ISSN
- 1866-6280
- Ausgabe der Veröffentlichung
- 3
- Zeitschrift
- Environmental Earth Sciences
- Sprache
- en
- Artikelnummer
- 71
- Online publication date
- 2022
- Datum der Veröffentlichung
- 2022
- Status
- Published
- Herausgeber
- Springer Science and Business Media LLC
- Herausgeber URL
- http://dx.doi.org/10.1007/s12665-021-10133-7
- Datum der Datenerfassung
- 2022
- Titel
- Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks
- Ausgabe der Zeitschrift
- 81
Datenquelle: Crossref
- Author's licence
- CC-BY
- Autoren
- Marcel Reinhardt
- Arne Jacob
- Saeid Sadeghnejad
- Francesco Cappuccio
- Pit Arnold
- Sascha Frank
- Frieder Enzmann
- Michael Kersten
- Hosting institution
- Universitätsbibliothek Mainz
- Sammlungen
- DFG-491381577-H
- Resource version
- Published version
- DOI
- 10.1007/s12665-021-10133-7
- File(s) embargoed
- false
- Open access
- true
- ISSN
- 1866-6299
- Zeitschrift
- Environmental earth sciences
- Schlüsselwörter
- 550 Geowissenschaften
- 550 Earth sciences
- Sprache
- eng
- Open access status
- Open Access
- Paginierung
- 71
- Datum der Veröffentlichung
- 2022
- Public URL
- https://openscience.ub.uni-mainz.de/handle/20.500.12030/7500
- Herausgeber
- Springer
- Datum der Datenerfassung
- 2022
- Datum, an dem der Datensatz öffentlich gemacht wurde
- 2022
- Zugang
- Public
- Titel
- Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks
- Ausgabe der Zeitschrift
- 81
Files
benchmarking_conventional_and-20220729165648776.pdf
Datenquelle: OPENSCIENCE.UB
- Beziehungen:
- Eigentum von