Auto-segmentation technique for SEM images using machine learning: Asphaltene deposition case study

Gesho, Masakazu; Chaisoontornyotin, Wattana; Elkhatib, Omar; Goual, Lamia

doi:10.1016/j.ultramic.2020.113074

Cited by 13 publications

(3 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The asphaltene content of this crude oil was measured to be 0.02 wt % using ASTM D6560-12 . Despite this small amount, the asphaltenes in Bakken crude have a strong adsorption tendency on surfaces even from very good solvents like toluene. − The oil was filtered through a 5 μm filter followed by a 0.5 μm filter and doped with 5 vol % di-iodomethane (99% from Sigma-Aldrich) to produce a different X-ray attenuation for the oil phase compared to the nondoped brine.…”

Section: Methodsmentioning

confidence: 99%

Pore-Scale Study of Wettability Alteration and Fluid Flow in Propped Fractures of Ultra-Tight Carbonates

Elkhatib

Xie

Mohamed³

et al. 2023

Langmuir

Self Cite

View full text Add to dashboard Cite

The in situ change in oil flow behavior inside propped fractures due to wettability alteration of proppant grains and fracture surfaces was thoroughly investigated for the first time in this study. A series of microscale flow experiments were performed in mixed-wet fractured and propped miniature ultra-tight carbonate cores where the effect of wettability on oil bridging and fracture oil layer integrity was probed during oil production. During the initial production, proppant wettability changed toward an intermediate-wet state (contact angle (CA) = 96°) while that of fracture surfaces became strongly oil-wet (CA = 139°). Consequently, the fracture oil layer grew in size on both fracture surfaces and imbibed into the proppant pack through piston-like displacement and pore body filling until oil bridges were formed during oil injection. However, subsequent waterflooding induced thinning and rupturing of those bridges due to the accompanying reduction in the threshold capillary pressure of the proppant at higher aging times. The in situ chemical treatment of the proppant by a cationic surfactant (dodecyl tri-methyl ammonium bromide) could reverse its wettability toward weakly water-wet state (CA = 78°) after oil solubilization from the sand grains followed by substitutive surfactant adsorption. Surfactant injection also impacted the wettability of the fracture surface due to oil solubilization, reducing its mean contact angle down to an intermediate range (CA = 99°). As a result, the following oil production cycle yielded a smaller fracture oil layer. The surfactant effect on proppant wettability lasted for 2 weeks while its effect on fracture wettability lasted for more than 6 weeks. Similar flow cycles were performed with an anionic nanoparticle (graphene quantum dot) with hydrogen bonding ability. The nanoparticle solution yielded a quick reduction of the proppant and fracture surface contact angles to nearly 77° and 115°, respectively. Proppant wettability alteration occurred because the nanoparticles self-assembled at the three-point contact region between adsorbed oil and quartz surfaces, leading to oil solubilization in intermediate-wet regions while oil-wet regions remained unchanged. Therefore, re-introducing oil into the fracture instantaneously re-instated the initial wettability state of proppant grains (CA = 88°), deeming the nanoparticle solution ineffective. This study revealed that oil production through hydraulic fractures can be enhanced by monitoring the wettability of the proppant pack. If the production has a high water cut, it is beneficial to use chemical agents that reduce the proppant contact angles to a weakly water-wet state in order to preserve the hydraulic conductivity of the oil layer.

show abstract

Section: Methodsmentioning

confidence: 99%

Pore-Scale Study of Wettability Alteration and Fluid Flow in Propped Fractures of Ultra-Tight Carbonates

Elkhatib

Xie

Mohamed³

et al. 2023

Langmuir

Self Cite

View full text Add to dashboard Cite

show abstract

“…There are numerous segmentation methods for SEM images proposed in the literature. These methods may be either supervised [4][5][6] or unsupervised. 7,8 Supervised segmentation models are trained in a specific data set and therefore have limited applicability taking into account the large spectrum of used acquisition parameters and the differences in the composition of analysed samples.…”

Section: Introductionmentioning

confidence: 99%

Segmentation of SEM images of multiphase materials: When Gaussian mixture models are accurate?

Chatzigeorgiou

Vrigkas

Beazi-Katsioti

et al. 2022

Journal of Microscopy

View full text Add to dashboard Cite

Scanning electron microscopy has been a powerful technique to investigate the structural and chemical properties of multiphase materials on micro and nanoscale due to its high-resolution capabilities. One of the main outcomes of the SEM-based analysis is the calculation of the fractions of material components constituting the multiphase material by means of the segmentation of their back scattered electron SEM images. In order to segment multiphase images, Gaussian mixture models (GMMs) are commonly used based on the deconvolution of the image pixel histogram. Despite its extensive use, the accuracy of GMM predictions has not been validated yet. In this paper, we proceed to a systematic study of the evaluation of the accuracy and the limitations of the GMM method when applied to the segmentation of a four-phase material. To this end, first, we build a modelling framework and propose an index to quantify the accuracy of GMM predictions for all phases. Then we apply this framework to calculate the impact of collective parameters of image histogram on the accuracy of GMM predictions. Finally, some rules of thumb are concluded to guide SEM users about the suitability of using GMM for the segmentation of their SEM images based only on the inspection of the image histogram. A suitable histogram for GMM is a histogram with number of peaks equal to the number of Gaussian components, and if that is not the case, kurtosis and skewness should be smaller than 2.35 and 0.1, respectively.

show abstract

“…and then focus on a particular analysis (e.g., textures, edges, histograms) [ 55 ]. SEM pictures may be already statistically described by AI methods [ 56 ]. One can use the picture luminosity to recover the structure of surfaces which is a standard approach in material science.…”

Section: Introductionmentioning

confidence: 99%

The Proposal and Necessity of the Numerical Description of Nano- and Microplastics’ Surfaces (Plastisphere)

2021

View full text Add to dashboard Cite

The constantly growing amount of synthetic materials < 5 mm, called microplastics (MPs), is fragmented in the environment. Thus, their surface, Plastisphere, is substantially increasing forming an entirely new ecological niche. It has already been extensively studied by microbiologists observing the biofilm and by material scientists interested in the weathering of polymer materials. This paper aims to construct a bridge between the physical and chemical description of the Plastisphere and its microbiological and ecological significance. Various algorithms, based on the analysis of pictures obtained by scanning electron microscopy (SEM), are proposed to describe in detail the morphology of naturally weathered polymers. In particular, one can study the size and distribution of fibres in a standard filter, search the synthetic debris for mapping, estimate the grain size distribution, quantitatively characterize the different patterns of degradation for polymer spheres and ghost nets, or calculate the number of pores per surface. The description and visualization of a texture, as well as the classification of different morphologies present on a surface, are indispensable for the comprehensive characterization of weathered polymers found inside animals (e.g., fishes). All these approaches are presented as case studies and discussed within this work.

show abstract

Auto-segmentation technique for SEM images using machine learning: Asphaltene deposition case study

Cited by 13 publications

References 35 publications

Pore-Scale Study of Wettability Alteration and Fluid Flow in Propped Fractures of Ultra-Tight Carbonates

Pore-Scale Study of Wettability Alteration and Fluid Flow in Propped Fractures of Ultra-Tight Carbonates

Segmentation of SEM images of multiphase materials: When Gaussian mixture models are accurate?

The Proposal and Necessity of the Numerical Description of Nano- and Microplastics’ Surfaces (Plastisphere)

Contact Info

Product

Resources

About