Evaluation of image segmentation techniques for image-based rock property estimation

Purswani, Prakash; Karpyn, Zuleima T.; Enab, Khaled; Huang, Xiaolei

doi:10.1016/j.petrol.2020.107890

Cited by 44 publications

(16 citation statements)

References 64 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…TWS has different training features (e.g., image filters) that can be selected as per different training needs, such as noise reduction (e.g., gaussian blur), detection of objects boundaries (e.g., sobel), extraction of information related to image texture and localization of membrane-like structures (e.g., structure) (Hall et al, 2009; Arganda-Carreras et al, 2017). TWS has been successfully used in segmenting geological samples without requiring prefiltering steps (Garfi et al, 2020; Purswani et al, 2020). Therefore, we used the TWS to segment XCT images of the slag sample, and we used the default classifier of TWS, which is the fast random forest that uses 200 trees, constructed while considering 2 random features.…”

Section: Methodsmentioning

confidence: 99%

Image-Based Analysis of Weathered Slag for Calculation of Transport Properties and Passive Carbon Capture

Khudhur

Macente

MacDonald

et al. 2022

Microscopy and Microanalysis

View full text Add to dashboard Cite

Weathering of silicate-rich industrial wastes such as slag can reduce emissions from the steelmaking industry. During slag weathering, different minerals spontaneously react with atmospheric CO2 to produce calcite. Here, we evaluate the CO2 uptake during slag weathering using image-based analysis. The analysis was applied to an X-ray computed tomography (XCT) dataset of a slag sample associated with the former Ravenscraig steelworks in Lanarkshire, Scotland. The element distribution of the sample was studied using scanning electron microscopy (SEM), coupled with energy-dispersive spectroscopy (EDS). Two advanced image segmentation methods, namely trainable WEKA segmentation in the Fiji distribution of ImageJ and watershed segmentation in Avizo ® 9.3.0, were used to segment the XCT images into matrix, pore space, calcite, and other precipitates. Both methods yielded similar volume fractions of the segmented classes. However, WEKA segmentation performed better in segmenting smaller pores, while watershed segmentation was superior in overcoming the partial volume effect presented in the XCT data. We estimate that CO2 has been captured in the studied sample with an uptake between 20 and 17 kg CO2/1,000 kg slag for TWS and WS, respectively, through calcite precipitation.

show abstract

Section: Methodsmentioning

confidence: 99%

Image-Based Analysis of Weathered Slag for Calculation of Transport Properties and Passive Carbon Capture

Khudhur

Macente

MacDonald

et al. 2022

Microscopy and Microanalysis

View full text Add to dashboard Cite

show abstract

“…Compared with other sensitivity analysis methods, the Sobol method has a relatively stable sampling method, which can grade the sensitivity to the contribution proportion of the output variance through parameters and is a more efficient method to quantitatively identify the sensitivity of different parameters. The specific model of Sobol sensitivity analysis is shown in equations ( 5)- (9).…”

Section: Methodsmentioning

confidence: 99%

“…The construction of relative permeability models is based on data feedback from adequate relative permeability experiments. However, the current relative permeability determination experiments are still based on the steady-state multiphase core displacement, which has some shortcomings [9][10][11]. First, a single core cannot reflect the pore characteristics of the entire reservoir, while equivalent conditional experiments on multiple cores imply significant consumption of time and cost.…”

Section: Introductionmentioning

confidence: 99%

Intelligent Microfluidics Research on Relative Permeability Measurement and Prediction of Two-Phase Flow in Micropores

et al. 2021

View full text Add to dashboard Cite

Relative permeability is a key index in resource exploitation, energy development, environmental monitoring, and other fields. However, the current determination methods of relative permeability are inefficient and invisible without considering wetting order and pore structure characteristics either. In this study, microfluidic experiments were designed for figuring out key factors impacting on the two-phase relative permeability. The optimized intelligent image recognition was established for saturation extraction. The deep learning was conducted for the prediction of two-phase permeability based on the inputs from microfluidic experiments and image recognition and optimized. Results revealed that phase saturation, wetting order, and pore topology were the key factors influencing the two-phase relative permeability, with the importance of 38.22%, 34.84%, and 26.94%, respectively. The deep learning-based relative permeability model performed well, with MSE < 0.05 and operational efficiency of 3 ms/epoch. Aiming at relative permeability model optimization, on the one hand, the dividing ratio of training set and testing set for flooding phase relative permeability prediction achieved the highest prediction accuracy at 7 : 3, while that for displaced phase was 6 : 4. On the other hand, tanh() activation function performed 40% more accurate than the sigmoid() activation function.

show abstract

“…Liang and Zou proposed an improved semisupervised SVM-FCM algorithm method (CSVM-FCM) based on chaos to segment rock images (Liang and Zou, 2020). Purswani et al compared the effectiveness of different image segmentation techniques in the analysis of porous media image data (Purswani et al, 2020). Sun et al (2019) used a clustering superpixel segmentation algorithm combining color, spatial location, and texture to identify and separate waste rock and raw coal.…”

Section: Introductionmentioning

confidence: 99%

Automatic batch recognition of rock deformation areas based on image segmentation methods

Yuan

Nie

et al. 2023

Front. Earth Sci.

View full text Add to dashboard Cite

Image recording and analysis is an important but time-consuming method for understanding the rock mechanics mechanism. In this paper, a method for automatic batch identification of rock deformation areas is proposed. We crop the original image to remove irrelevant background. And we use adaptive threshold segmentation, region growth segmentation and global threshold segmentation and combine the characteristics of the image to identify the rock deformation area. Finally, we use image morphology processing to make the recognition result more accurate. For validation, 359 images of the rock samples of the uniaxial compression test were quickly identified. The identification time was approximately 5′56.83′. The average relative error of the method in the X and Y directions is 10.88% and 8.60%, respectively. In addition, using the identification results and the stress-strain curve, it was found that the water content and initial crack length of rock increase, and the compressive strength decreases; the effect of the initial fracture inclination on the compressive strength of the rock is not obvious.

show abstract

Evaluation of image segmentation techniques for image-based rock property estimation

Cited by 44 publications

References 64 publications

Image-Based Analysis of Weathered Slag for Calculation of Transport Properties and Passive Carbon Capture

Image-Based Analysis of Weathered Slag for Calculation of Transport Properties and Passive Carbon Capture

Intelligent Microfluidics Research on Relative Permeability Measurement and Prediction of Two-Phase Flow in Micropores

Automatic batch recognition of rock deformation areas based on image segmentation methods

Contact Info

Product

Resources

About