Gutenberg Open Science: Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks

Please use this identifier to cite or link to this item: http://doi.org/10.25358/openscience-7486

Full metadata record

DC Field	Value	Language
dc.contributor.author	Reinhardt, Marcel	-
dc.contributor.author	Jacob, Arne	-
dc.contributor.author	Sadeghnejad, Saeid	-
dc.contributor.author	Cappuccio, Francesco	-
dc.contributor.author	Arnold, Pit	-
dc.contributor.author	Frank, Sascha	-
dc.contributor.author	Enzmann, Frieder	-
dc.contributor.author	Kersten, Michael	-
dc.date.accessioned	2022-08-04T07:24:24Z	-
dc.date.available	2022-08-04T07:24:24Z	-
dc.date.issued	2022	-
dc.identifier.uri	https://openscience.ub.uni-mainz.de/handle/20.500.12030/7500	-
dc.description.abstract	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.	en_GB
dc.language.iso	eng	de
dc.rights	CC BY	*
dc.rights.uri	https://creativecommons.org/licenses/by/4.0/	*
dc.subject.ddc	550 Geowissenschaften	de_DE
dc.subject.ddc	550 Earth sciences	en_GB
dc.title	Benchmarking conventional and machine learning segmentation techniques for digital rock physics analysis of fractured rocks	en_GB
dc.type	Zeitschriftenaufsatz	de
dc.identifier.doi	http://doi.org/10.25358/openscience-7486	-
jgu.type.dinitype	article	en_GB
jgu.type.version	Published version	de
jgu.type.resource	Text	de
jgu.organisation.department	FB 09 Chemie, Pharmazie u. Geowissensch.	de
jgu.organisation.number	7950	-
jgu.organisation.name	Johannes Gutenberg-Universität Mainz	-
jgu.rights.accessrights	openAccess	-
jgu.journal.title	Environmental earth sciences	de
jgu.journal.volume	81	de
jgu.pages.alternative	71	de
jgu.publisher.year	2022	-
jgu.publisher.name	Springer	de
jgu.publisher.place	Berlin	de
jgu.publisher.issn	1866-6299	de
jgu.organisation.place	Mainz	-
jgu.subject.ddccode	550	de
jgu.publisher.doi	10.1007/s12665-021-10133-7	de
jgu.organisation.ror	https://ror.org/023b0x485	-
jgu.subject.dfg	Naturwissenschaften	de
Appears in collections:	DFG-491381577-H

Files in This Item:

	File	Description	Size	Format
	benchmarking_conventional_and-20220729165648776.pdf		18.76 MB	Adobe PDF	View/Open

Show simple item record