A New Improved Threshold Segmentation Method for Scanning Images of Reservoir Rocks Considering Pore Fractal Characteristics

Lin, Wei; Li, Xizhe; Yang, Zhengming; Lin, Li; Xiong, Shengwu; Wang, Zhiyuan; Wang, Xiangyang; Xiao, Qi

doi:10.1142/s0218348x18400030

Cited by 54 publications

(34 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previous fractal studies on the pore structure of tight oil and shale gas reservoirs show that they have good fractal characteristics (Lin et al 2017(Lin et al , 2018Wang et al 2019). To quantitatively characterize the heterogeneity of shale reservoirs, we used fractal theory to quantitatively characterize the microscopic heterogeneity of shale oil and tight sandstone reservoirs.…”

Section: Fractal Characteristics Of Micro-nano-pores In Shale Oil Resmentioning

confidence: 99%

Characteristics of micro- and nano-pores in shale oil reservoirs

Xia

Yang

Gao

et al. 2020

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

Porosity is the most common form of reservoirs, and its size, shape, and connectivity directly affect the capacity of oil and gas storage and production. To study the micro–nano-pore structure characteristics of shale oil reservoirs and quantitatively characterize its heterogeneity, this work uses high-precision high-pressure mercury intrusion (HPMI) experimental techniques to study the micro–nano-pore structure characteristics of shale oil, and based on the experimental data, fractal theory is used to quantitatively characterize its heterogeneity. The results of the study show that the micro–nano-pores in the shale oil reservoir are concentrated and continuous, and the pore radius is mainly distributed among the range of 30–500 nm, nanoscale pores are an important part of the pores of the shale oil reservoir. The fractal dimension of the shale oil reservoir is larger than the fractal dimension of typical tight oil reservoirs, indicating that the heterogeneity of shale oil reservoir is stronger. The research results have some theoretical and practical significance for the production of inter-salt shale oil reservoirs.

show abstract

Section: Fractal Characteristics Of Micro-nano-pores In Shale Oil Resmentioning

confidence: 99%

Characteristics of micro- and nano-pores in shale oil reservoirs

Xia

Yang

Gao

et al. 2020

J Petrol Explor Prod Technol

Self Cite

View full text Add to dashboard Cite

show abstract

“…dλ (13) where [λ 1 , λ 2 ] is a specified infrared band range, (λ, T ) represents emissivity of the material under a specific band and temperature. c 1 and c 2 are the first and second radiation constant respectively.…”

Section: Appendix a Infrared Radiation Calculationmentioning

confidence: 99%

Synthetic IR Image Refinement Using Adversarial Learning With Bidirectional Mappings

Zhang

et al. 2019

IEEE Access

View full text Add to dashboard Cite

Collecting a large dataset of real infrared (IR) images is expensive, time-consuming, and even unavailable in some specific scenarios. With recent progress in machine learning, it has become more feasible to replace real IR images with qualified synthetic IR images in learning-based IR systems. However, this alternative may fail to achieve the desired performance, due to the gap between real and synthetic IR images. Inspired by adversarial learning for image-to-image translation, we propose the Synthetic IR Refinement Generative Adversarial Network (SIR-GAN) to narrow this gap. By learning the bidirectional mappings between two unpaired domains, the realism of the simulated IR images generated from the IR Simulator are significantly improved, where the source domain contains a large number of simulated IR images, where the target domain contains a limited quantity of real IR images. Specifically, driven by the idea of transferring infrared characteristic and protect target semantic information simultaneously, we propose a SIR refinement loss to consider an infrared loss and a structure loss further to the adversarial loss and the consistency loss. To further reduce the gap, stabilize training, and avoid artefacts, we modify the proposed algorithm by developing a training strategy, adding the U-net in the generators, using the dilated convolution in the discriminators and invoking the N-Adam acts as the optimizer. Qualitative, quantitative, and ablation study experiments demonstrate the superiority of the proposed approach compared with the state-of-the-art techniques in terms of realism and fidelity. In addition, our refined IR images are evaluated in the context of a feasibility study, where the accuracy of the trained classifier is significantly improved by adding our refined data into a small real-data training set.

show abstract

“…Weiming Wang et al 12 studied the morphological characteristics and size distribution of nanoscale pores in the volcanic rocks of the Haerjiawu Formation using the results of low temperature nitrogen adsorption experiments and fractal geometry theory. Considering the relationship between the porosity of rocks and the fractal characteristics of pore structures, Lin et al 13 proposed a new improved image segmentation method, which used the calculated porosity of core images as a constraint to obtain the best threshold.…”

Section: Overview Of Work Presented In This Special Issuementioning

confidence: 99%

An Introduction to Fractal-Based Approaches in Unconventional Reservoirs — Part I

Cai

Zhang

et al. 2018

Fractals

View full text Add to dashboard Cite

In recent years, unconventional reservoirs have drawn tremendous attention worldwide. This special issue collects a series of recent works on various fractal-based approaches in unconventional reservoirs. The topics covered in this introduction include fractal characterization of pore (throat) structure and its influences on the physical properties of unconventional rocks, fractal characteristics of crack propagation in coal and fluid flow in rock fracture network under shearing, porous flow phenomena and gas adsorption mechanism, fractal geophysical method in reservoirs.

show abstract

A New Improved Threshold Segmentation Method for Scanning Images of Reservoir Rocks Considering Pore Fractal Characteristics

Cited by 54 publications

References 32 publications

Characteristics of micro- and nano-pores in shale oil reservoirs

Characteristics of micro- and nano-pores in shale oil reservoirs

Synthetic IR Image Refinement Using Adversarial Learning With Bidirectional Mappings

An Introduction to Fractal-Based Approaches in Unconventional Reservoirs — Part I

Contact Info

Product

Resources

About