Journal cover Journal topic
Solid Earth An interactive open-access journal of the European Geosciences Union

Journal metrics

  • IF value: 3.495 IF 3.495
  • IF 5-year<br/> value: 3.386 IF 5-year
    3.386
  • CiteScore<br/> value: 3.70 CiteScore
    3.70
  • SNIP value: 0.783 SNIP 0.783
  • SJR value: 1.039 SJR 1.039
  • IPP value: 1.987 IPP 1.987
  • h5-index value: 20 h5-index 20
Solid Earth, 7, 1125-1139, 2016
https://doi.org/10.5194/se-7-1125-2016
© Author(s) 2016. This work is distributed under
the Creative Commons Attribution 3.0 License.
Research article
19 Jul 2016
Phase segmentation of X-ray computer tomography rock images using machine learning techniques: an accuracy and performance study
Swarup Chauhan1, Wolfram Rühaak1,2, Hauke Anbergen3, Alen Kabdenov3, Marcus Freise3, Thorsten Wille3, and Ingo Sass1,2 1Department of Geothermal Science and Technology, Institute of Applied Geosciences, Technische Universität Darmstadt, Darmstadt, Germany
2Darmstadt Graduate School of Excellence Energy Science and Engineering, Technische Universität Darmstadt, Darmstadt, Germany
3APS Antriebs-, Prüf- und Steuertechnik GmbH, Göttingen, Rosdorf, Germany
Abstract. Performance and accuracy of machine learning techniques to segment rock grains, matrix and pore voxels from a 3-D volume of X-ray tomographic (XCT) grayscale rock images was evaluated. The segmentation and classification capability of unsupervised (k-means, fuzzy c-means, self-organized maps), supervised (artificial neural networks, least-squares support vector machines) and ensemble classifiers (bragging and boosting) were tested using XCT images of andesite volcanic rock, Berea sandstone, Rotliegend sandstone and a synthetic sample. The averaged porosity obtained for andesite (15.8 ± 2.5 %), Berea sandstone (16.3 ± 2.6 %), Rotliegend sandstone (13.4 ± 7.4 %) and the synthetic sample (48.3 ± 13.3 %) is in very good agreement with the respective laboratory measurement data and varies by a factor of 0.2. The k-means algorithm is the fastest of all machine learning algorithms, whereas a least-squares support vector machine is the most computationally expensive. Metrics entropy, purity, mean square root error, receiver operational characteristic curve and 10 K-fold cross-validation were used to determine the accuracy of unsupervised, supervised and ensemble classifier techniques. In general, the accuracy was found to be largely affected by the feature vector selection scheme. As it is always a trade-off between performance and accuracy, it is difficult to isolate one particular machine learning algorithm which is best suited for the complex phase segmentation problem. Therefore, our investigation provides parameters that can help in selecting the appropriate machine learning techniques for phase segmentation.

Citation: Chauhan, S., Rühaak, W., Anbergen, H., Kabdenov, A., Freise, M., Wille, T., and Sass, I.: Phase segmentation of X-ray computer tomography rock images using machine learning techniques: an accuracy and performance study, Solid Earth, 7, 1125-1139, https://doi.org/10.5194/se-7-1125-2016, 2016.
Publications Copernicus
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.
Machine learning techniques are a promising alternative for processing (phase segmentation) of...
Share