Articles | Volume 7, issue 4
https://doi.org/10.5194/se-7-1125-2016
https://doi.org/10.5194/se-7-1125-2016
Research article
 | 
19 Jul 2016
Research article |  | 19 Jul 2016

Phase segmentation of X-ray computer tomography rock images using machine learning techniques: an accuracy and performance study

Swarup Chauhan, Wolfram Rühaak, Hauke Anbergen, Alen Kabdenov, Marcus Freise, Thorsten Wille, and Ingo Sass

Related authors

GeoLaB – Geothermal Laboratory in the crystalline Basement: synergies with research for a nuclear waste repository
Thomas Kohl, Ingo Sass, Olaf Kolditz, Christoph Schüth, Wolfram Rühaak, Jürgen Schamp, Judith Bremer, Bastian Rudolph, Katharina Schätzler, and Eva Schill
Saf. Nucl. Waste Disposal, 2, 135–136, https://doi.org/10.5194/sand-2-135-2023,https://doi.org/10.5194/sand-2-135-2023, 2023
Short summary
Demonstrating the possibility of safe operation in the first phase of the site selection procedure in Germany
Michael Werres, Frederik Fahrendorf, Thomas Lohser, and Wolfram Rühaak
Saf. Nucl. Waste Disposal, 2, 179–180, https://doi.org/10.5194/sand-2-179-2023,https://doi.org/10.5194/sand-2-179-2023, 2023
Short summary
A new tool to automatise the characterisation of fracture networks from 3D point cloud data
Lionel Bertrand, Claire Bossennec, Wan-Chiu Li, Cédric Borgese, Bruno Gavazzi, Matthis Frey, Yves Géraud, Marc Diraison, and Ingo Sass
EGUsphere, https://doi.org/10.5194/egusphere-2023-1316,https://doi.org/10.5194/egusphere-2023-1316, 2023
Preprint archived
Short summary
Expected and deviating evolutions in representative preliminary safety assessments – a focus on glacial tunnel valleys
Paulina Müller, Eva-Maria Hoyer, Anne Bartetzko, and Wolfram Rühaak
E&G Quaternary Sci. J., 72, 73–76, https://doi.org/10.5194/egqsj-72-73-2023,https://doi.org/10.5194/egqsj-72-73-2023, 2023
Short summary
TransPyREnd: a code for modelling the transport of radionuclides on geological timescales
Christoph Behrens, Elco Luijendijk, Phillip Kreye, Florian Panitz, Merle Bjorge, Marlene Gelleszun, Alexander Renz, Shorash Miro, and Wolfram Rühaak
Adv. Geosci., 58, 109–119, https://doi.org/10.5194/adgeo-58-109-2023,https://doi.org/10.5194/adgeo-58-109-2023, 2023
Short summary

Related subject area

Geophysics
Post-Caledonian tectonic evolution of the Precambrian and Paleozoic platform boundary zone offshore Poland based on the new and vintage multi-channel reflection seismic data
Quang Nguyen, Michal Malinowski, Stanisław Mazur, Sergiy Stovba, Małgorzata Ponikowska, and Christian Hübscher
Solid Earth, 15, 1029–1046, https://doi.org/10.5194/se-15-1029-2024,https://doi.org/10.5194/se-15-1029-2024, 2024
Short summary
Geodynamic controls on clastic-dominated base metal deposits
Anne C. Glerum, Sascha Brune, Joseph M. Magnall, Philipp Weis, and Sarah A. Gleeson
Solid Earth, 15, 921–944, https://doi.org/10.5194/se-15-921-2024,https://doi.org/10.5194/se-15-921-2024, 2024
Short summary
Seismic wave modeling of fluid-saturated fractured porous rock: including fluid pressure diffusion effects of discretely distributed large-scale fractures
Yingkai Qi, Xuehua Chen, Qingwei Zhao, Xin Luo, and Chunqiang Feng
Solid Earth, 15, 535–554, https://doi.org/10.5194/se-15-535-2024,https://doi.org/10.5194/se-15-535-2024, 2024
Short summary
Comparison of surface-wave techniques to estimate S- and P-wave velocity models from active seismic data
Farbod Khosro Anjom, Frank Adler, and Laura Valentina Socco
Solid Earth, 15, 367–386, https://doi.org/10.5194/se-15-367-2024,https://doi.org/10.5194/se-15-367-2024, 2024
Short summary
Integration of automatic implicit geological modelling in deterministic geophysical inversion
Jérémie Giraud, Guillaume Caumon, Lachlan Grose, Vitaliy Ogarko, and Paul Cupillard
Solid Earth, 15, 63–89, https://doi.org/10.5194/se-15-63-2024,https://doi.org/10.5194/se-15-63-2024, 2024
Short summary

Cited articles

Amigó, E., Gonzalo, J., Artiles, J., and Verdejo, F.: A comparison of extrinsic clustering evaluation metrics based on formal constraints, Inform. Retrieval, 12, 461–486, 2009.
Aretz, A., Bär, K., Götz, A. E., and Sass, I.: Outcrop analogue study of Permocarboniferous geo-thermal sandstone reservoir formations (northern Upper Rhine Graben, Germany): impact of mineral content, depositional environment and diagenesis on petrophysical properties, Int. J. Earth Sci., 105, 1431–1452, https://doi.org/10.1007/s00531-015-1263-2 2016.
Bradley, A. P.: The use of the area under the ROC curve in the evaluation of machine learning algorithms, Pattern Recogn., 30, 1145–1159. 1997.
Breiman, L.: Bagging predictors, Mach. Lear., 24, 123–140, 1996.
Download
Short summary
Machine learning techniques are a promising alternative for processing (phase segmentation) of 3-D X-ray computer tomographic rock images. Here the performance and accuracy of different machine learning techniques are tested. The aim is to classify pore space, rock grains and matrix of four distinct rock samples. The porosity obtained based on the segmented XCT images is cross-validated with laboratory measurements. Accuracies of the different methods are discussed and recommendations proposed.