Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin

Chen, Zhuoheng; Liu, Xiaojun; Yang, Jijin; Little, E C; Zhou, Yu

doi:10.1016/j.cageo.2020.104450

Cited by 78 publications

(36 citation statements)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Paleozoic shale gas reservoirs in south China are over-matured, characterized by deep burial, wide distribution, and a complex reservoir pore structure (Chen et al 2010;Guo and Zhang 2014;Nie et al 2009). These characteristics cause difficulties in understanding the pore properties of the reservoirs and the characteristics of shale gas occurrence, presenting a barrier to overcoming the exploration and development bottleneck (Chen et al 2020).…”

Section: Introductionmentioning

confidence: 99%

Simulation of methane adsorption in diverse organic pores in shale reservoirs with multi-period geological evolution

Chen

Zhang

et al. 2021

Int J Coal Sci Technol

View full text Add to dashboard Cite

In shale reservoirs, the organic pores with various structures formed during the thermal evolution of organic matter are the main storage site for adsorbed methane. However, in the process of thermal evolution, the adsorption characteristics of methane in multi type and multi-scale organic matter pores have not been sufficiently studied. In this study, the molecular simulation method was used to study the adsorption characteristics of methane based on the geological conditions of Longmaxi Formation shale reservoir in Sichuan Basin, China. The results show that the characteristics of pore structure will affect the methane adsorption characteristics. The adsorption capacity of slit-pores for methane is much higher than that of cylindrical pores. The groove space inside the pore will change the density distribution of methane molecules in the pore, greatly improve the adsorption capacity of the pore, and increase the pressure sensitivity of the adsorption process. Although the variation of methane adsorption characteristics of different shapes is not consistent with pore size, all pores have the strongest methane adsorption capacity when the pore size is about 2 nm. In addition, the changes of temperature and pressure during the thermal evolution are also important factors to control the methane adsorption characteristics. The pore adsorption capacity first increases and then decreases with the increase of pressure, and increases with the increase of temperature. In the early stage of thermal evolution, pore adsorption capacity is strong and pressure sensitivity is weak; while in the late stage, it is on the contrary.

show abstract

Section: Introductionmentioning

confidence: 99%

Simulation of methane adsorption in diverse organic pores in shale reservoirs with multi-period geological evolution

Chen

Zhang

et al. 2021

Int J Coal Sci Technol

View full text Add to dashboard Cite

show abstract

“…Deep learning was used to remove SEM image noise and improved the measurement accuracy of line edge roughness [ 18 ]. U-Net [ 19 ] was used to analyze SEM images of mineral characterization, which distinguished effectively the mixed matrix mineral particles and organic clay aggregates [ 20 ]. Deep learning was applied to detect nanoparticles in microscopic images and uses Hough algorithm to detect particle edges [ 21 ].…”

Section: Introductionmentioning

confidence: 99%

A Hybrid Crack Detection Approach for Scanning Electron Microscope Image Using Deep Learning Method

et al. 2021

View full text Add to dashboard Cite

The scanning electron microscope (SEM) is widely used in the analysis and research of materials, including fracture analysis, microstructure morphology, and nanomaterial analysis. With the rapid development of materials science and computer vision technology, the level of detection technology is constantly improving. In this paper, the deep learning method is used to intelligently identify microcracks in the microscopic morphology of SEM image. A deep learning model based on image level is selected to reduce the interference of other complex microscopic topography, and a detection method with dense continuous bounding boxes suitable for SEM images is proposed. The dense and continuous bounding boxes were used to obtain the local features of the cracks and rotating the bounding boxes to reduce the feature differences between the bounding boxes. Finally, the bounding boxes with filled regression were used to highlight the microcrack detection effect. The results show that the detection accuracy of our approach reached 71.12%, and the highest mIOU reached 64.13%. Also, microcracks in different magnifications and in different backgrounds were detected successfully.

show abstract

“…Azimi et al 22 used a fully convolutional neural network to address the classification of microstructural constituents of low carbon steel in SEM and Light Optical Microscopy (LOM) images. Chen et al 23 proposed to employ the U-Net framework, 25 widely used in medical image segmentation, to address SEM image segmentation of shale samples and minerals. CNN-based super-resolution techniques have also been applied to the resolution enhancement of low-quality SEM images.…”

Section: Introductionmentioning

confidence: 99%

Machine vision-driven automatic recognition of particle size and morphology in SEM images

Kim

Han

2020

Nanoscale

View full text Add to dashboard Cite

show abstract

Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin

Cited by 78 publications

References 18 publications

Simulation of methane adsorption in diverse organic pores in shale reservoirs with multi-period geological evolution

Simulation of methane adsorption in diverse organic pores in shale reservoirs with multi-period geological evolution

A Hybrid Crack Detection Approach for Scanning Electron Microscope Image Using Deep Learning Method

Machine vision-driven automatic recognition of particle size and morphology in SEM images

Contact Info

Product

Resources

About