Search

Your search keyword '"Shapoval, Artur"' showing total 7 results
Start Over Author "Shapoval, Artur"
7 results on '"Shapoval, Artur"'

3. Pore-GNN: A graph neural network-based framework for predicting flow properties of porous media from micro-CT images.

Author

Alzahrani, Mohammed K., Shapoval, Artur, Chen, Zhixi, and Rahman, Sheikh S.

Subjects
*DEEP learning, *MACHINE learning, *ARTIFICIAL neural networks, *POROUS materials, *SANDSTONE, *COMPUTED tomography
Abstract

This paper presents a hybrid deep learning framework that combines graph neural networks with convolutional neural networks to predict porous media properties. This approach capitalizes on the capabilities of pre-trained convolutional neural networks to extract ndimensional feature vectors from processed three dimensional micro computed tomography porous media images obtained from seven different sandstone rock samples. Subsequently, two strategies for embedding the computed feature vectors into graphs were explored: extracting a single feature vector per sample (image) and treating each sample as a node in the training graph, and representing each sample as a graph by extracting a fixed number of feature vectors, which form the nodes of each training graph. Various types of graph convolutional layers were examined to evaluate the capabilities and limitations of spectral and spatial approaches. The dataset was divided into 70/20/10 for training, validation, and testing. The models were trained to predict the absolute permeability of porous media. Notably, the proposed architectures further reduce the selected objective loss function to values below 35 mD, with improvements in the coefficient of determination reaching 9%. Moreover, the generalizability of the networks was evaluated by testing their performance on unseen sandstone and carbonate rock samples that were not encountered during training. Finally, a sensitivity analysis is conducted to investigate the influence of various hyperparameters on the performance of the models. The findings highlight the potential of graph neural networks as promising deep learning-based alternatives for characterizing porous media properties. The proposed architectures efficiently predict the permeability, which is more than 500 times faster than that of numerical solvers. [ABSTRACT FROM AUTHOR]

Published
2023
Full Text
View/download PDF

4. Investigation of Rock-Fluid Interactions in Carbonate Reservoirs with the Use of Digital Rock Physics

Author

Shapoval, Artur

Subjects
emulsion, wettability, 401907 Petroleum and reservoir engineering, rock-fluid interactions, carbonate reservoirs, micro ct
Abstract

This thesis presents a pore-scale investigation into the mechanisms governing the interactions between water, oil and carbonate rocks using a series of core-flood experiments coupled with micro-CT imaging. Firstly, rock-fluid interactions leading to wettability alteration by seawater (injected in the secondary mode) and modified seawater (by addition or depletion of Ca2+ ion, injected in tertiary mode) are assessed using in-situ contact angle measurements. While the results have confirmed wettability alteration due to injection of the modified seawater (in tertiary mode), this change in wettability was found to be insufficient to fully explain the observed improvement of oil recovery. Secondly, a fluid-fluid interactions analysis methodology was developed and applied to the data generated as part of this thesis (Ca2+ ­enriched brine, Ca2+ depleted brine, SO42- enriched brine). The results show that emulsification is another mechanism responsible for enhancing oil recovery which is caused by reduction in interfacial tension. Data from multiple experiments (micro-CT imaging, stability analysis, surface tension measurements) also suggests that the amount of emulsion generated, and its stability depend on the type of ion added to seawater to modify the water chemistry. Specifically, Ca2+ depleted brine has shown to generate large amount of emulsion. As part of this thesis, a pore-scale direct flow simulation using the Volume-of-Fluid method was developed to model the mechanisms observed in the experimental studies, such as wettability alteration, viscous fingering and interfacial tension reduction. These mechanisms were grouped into two types, capillary-force affecting (contact angle and interfacial tension), and viscous-force affecting (viscous fingering reduction). When comparing the data between the two approaches (laboratory- and numerical experiments) the results show that capillary-force driven mechanisms were insufficient to predict the oil recovery due to development of flow stagnation zones in the sample. However, when the viscous forces were taken in account in estimation of sweep efficiency the displacement is significantly improved and the experimental data match well with that of numerical experiment. As a result, this thesis provides a first comprehensive pore-scale investigation of the physicochemical interactions between oil, water and carbonate rock related to the tertiary injections of modified seawater.

Published
2022
Full Text
View/download PDF

7. Investigation of Rock-Fluid Interactions in Carbonate Reservoirs with the Use of Digital Rock Physics

Author

Shapoval, Artur ; https://orcid.org/0000-0003-3028-5337

Subjects
rock-fluid interactions, carbonate reservoirs, micro ct, emulsion, wettability, anzsrc-for: 401907 Petroleum and reservoir engineering
Abstract

This thesis presents a pore-scale investigation into the mechanisms governing the interactions between water, oil and carbonate rocks using a series of core-flood experiments coupled with micro-CT imaging. Firstly, rock-fluid interactions leading to wettability alteration by seawater (injected in the secondary mode) and modified seawater (by addition or depletion of Ca2+ ion, injected in tertiary mode) are assessed using in-situ contact angle measurements. While the results have confirmed wettability alteration due to injection of the modified seawater (in tertiary mode), this change in wettability was found to be insufficient to fully explain the observed improvement of oil recovery. Secondly, a fluid-fluid interactions analysis methodology was developed and applied to the data generated as part of this thesis (Ca2+ ­enriched brine, Ca2+ depleted brine, SO42- enriched brine). The results show that emulsification is another mechanism responsible for enhancing oil recovery which is caused by reduction in interfacial tension. Data from multiple experiments (micro-CT imaging, stability analysis, surface tension measurements) also suggests that the amount of emulsion generated, and its stability depend on the type of ion added to seawater to modify the water chemistry. Specifically, Ca2+ depleted brine has shown to generate large amount of emulsion. As part of this thesis, a pore-scale direct flow simulation using the Volume-of-Fluid method was developed to model the mechanisms observed in the experimental studies, such as wettability alteration, viscous fingering and interfacial tension reduction. These mechanisms were grouped into two types, capillary-force affecting (contact angle and interfacial tension), and viscous-force affecting (viscous fingering reduction). When comparing the data between the two approaches (laboratory- and numerical experiments) the results show that capillary-force driven mechanisms were insufficient to predict the oil recovery due to development of flow stagnation zones in the sample. However, when the viscous forces were taken in account in estimation of sweep efficiency the displacement is significantly improved and the experimental data match well with that of numerical experiment. As a result, this thesis provides a first comprehensive pore-scale investigation of the physicochemical interactions between oil, water and carbonate rock related to the tertiary injections of modified seawater.

Published
2022

Catalog

Books, media, physical & digital resources
See catalog results