1
|
de Castro Vargas Fernandes J, Duarte Vidal A, Carvalho Medeiros L, Menezes Dos Anjos CE, Surmas R, Gonçalves Evsukoff A. Absolute permeability estimation from microtomography rock images through deep learning super-resolution and adversarial fine tuning. Sci Rep 2024; 14:16704. [PMID: 39030317 PMCID: PMC11271552 DOI: 10.1038/s41598-024-67367-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/14/2024] [Accepted: 07/10/2024] [Indexed: 07/21/2024] Open
Abstract
The carbon capture and storage (CCS) process has become one of the main technologies used for mitigating greenhouse gas emissions. The success of CCS projects relies on accurate subsurface reservoir petrophysical characterization, enabling efficient storage and captured CO 2 containment. In digital rock physics, X-ray microtomography ( μ -CT) is applied to characterize reservoir rocks, allowing a more assertive analysis of physical properties such as porosity and permeability, enabling better simulations of porous media flow. Estimating petrophysical properties through numeric simulations usually requires high-resolution images, which are expensive and time-inefficient to obtain with μ -CT. To address this, we propose using two deep learning models: a super-resolution model to enhance the quality of low-resolution images and a surrogate model that acts as a substitute for numerical simulations to estimate the petrophysical property of interest. A correction process inspired by generative adversarial network (GAN) adversarial training is applied. In this approach, the super-resolution model acts as a generator, creating high-resolution images, and the surrogate network acts as a discriminator. By adjusting the generator, images that correct the errors in the surrogate's estimations are produced. The proposed method was applied to the DeePore dataset. The results shows the proposed approach improved permeability estimation overall.
Collapse
Affiliation(s)
| | - Alyne Duarte Vidal
- COPPE-Federal University of Rio de Janeiro, Mailbox 68506, Rio de Janeiro, Rio de Janeiro, 21941-972, Brazil
| | - Lizianne Carvalho Medeiros
- COPPE-Federal University of Rio de Janeiro, Mailbox 68506, Rio de Janeiro, Rio de Janeiro, 21941-972, Brazil
| | | | - Rodrigo Surmas
- CENPES-Petrobras, Av. Horácio Macedo, 950, Rio de Janeiro, Rio de Janeiro, 21941-915, Brazil
| | | |
Collapse
|
2
|
Samarin A, Postnicov V, Karsanina MV, Lavrukhin EV, Gafurova D, Evstigneev NM, Khlyupin A, Gerke KM. Robust surface-correlation-function evaluation from experimental discrete digital images. Phys Rev E 2023; 107:065306. [PMID: 37464648 DOI: 10.1103/physreve.107.065306] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/23/2022] [Accepted: 04/18/2023] [Indexed: 07/20/2023]
Abstract
Correlation functions (CFs) are universal structural descriptors; surface-surface F_{ss} and surface-void F_{sv} CFs are a subset containing additional information about the interface between the phases. The description of the interface between pores and solids in porous media is of particular importance and recently Ma and Torquato [Phys. Rev. E 98, 013307 (2018)2470-004510.1103/PhysRevE.98.013307] proposed an elegant way to compute these functions for a wide variety of cases. However, their "continuous" approach is not always applicable to digital experimental 2D and 3D images of porous media as obtained using x-ray tomography or scanning electron microscopy due to nonsingularities in chemical composition or local solid material's density and partial volume effects. In this paper we propose to use edge-detecting filters to compute surface CFs in the "digital" fashion directly in the images. Computed this way, surface correlation functions are the same as analytically known for Poisson disks in case the resolution of the image is adequate. Based on the multiscale image analysis we developed a C_{0.5} criterion that can predict if the imaging resolution is enough to make an accurate evaluation of the surface CFs. We also showed that in cases when the input image contains all major features, but do not pass the C_{0.5} criterion, it is possible with the help of image magnification to sample CFs almost similar to those obtained for high-resolution image of the same structure with high C_{0.5}. The computational framework as developed here is open source and available within the CorrelationFunctions.jl package developed by our group. Our "digital" approach was applied to a wide variety of real porous media images of different quality. We discuss critical aspects of surface correlation functions computations as related to different applications. The developed methodology allows applying surface CFs to describe the structure of porous materials based on their experimental images and enhance stochastic reconstructions or super-resolution procedures, or serve as an efficient metrics in machine learning applications due to computationally effective GPU implementation.
Collapse
Affiliation(s)
- Aleksei Samarin
- Schmidt Institute of Physics of the Earth of Russian Academy of Sciences, Moscow 107031, Russia
- Computational Mathematics and Cybernetics, Lomonosov Moscow State University, Moscow 119991, Russia
| | - Vasily Postnicov
- Schmidt Institute of Physics of the Earth of Russian Academy of Sciences, Moscow 107031, Russia
| | - Marina V Karsanina
- Schmidt Institute of Physics of the Earth of Russian Academy of Sciences, Moscow 107031, Russia
| | - Efim V Lavrukhin
- Schmidt Institute of Physics of the Earth of Russian Academy of Sciences, Moscow 107031, Russia
- Computational Mathematics and Cybernetics, Lomonosov Moscow State University, Moscow 119991, Russia
| | - Dina Gafurova
- Oil and Gas Research Institute Russian Academy of Sciences (OGRI RAS) 3, Gubkina Street, Moscow 119333, Russian Federation
| | - Nikolay M Evstigneev
- Federal Research Center "Computer Science and Control" of the Russian Academy of Sciences, Moscow 117312, Russia
| | - Aleksey Khlyupin
- Schmidt Institute of Physics of the Earth of Russian Academy of Sciences, Moscow 107031, Russia
| | - Kirill M Gerke
- Schmidt Institute of Physics of the Earth of Russian Academy of Sciences, Moscow 107031, Russia
| |
Collapse
|
3
|
Buono G, Caliro S, Macedonio G, Allocca V, Gamba F, Pappalardo L. Exploring microstructure and petrophysical properties of microporous volcanic rocks through 3D multiscale and super-resolution imaging. Sci Rep 2023; 13:6651. [PMID: 37095281 PMCID: PMC10126112 DOI: 10.1038/s41598-023-33687-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/08/2022] [Accepted: 04/17/2023] [Indexed: 04/26/2023] Open
Abstract
Digital rock physics offers powerful perspectives to investigate Earth materials in 3D and non-destructively. However, it has been poorly applied to microporous volcanic rocks due to their challenging microstructures, although they are studied for numerous volcanological, geothermal and engineering applications. Their rapid origin, in fact, leads to complex textures, where pores are dispersed in fine, heterogeneous and lithified matrices. We propose a framework to optimize their investigation and face innovative 3D/4D imaging challenges. A 3D multiscale study of a tuff was performed through X-ray microtomography and image-based simulations, finding that accurate characterizations of microstructure and petrophysical properties require high-resolution scans (≤ 4 μm/px). However, high-resolution imaging of large samples may need long times and hard X-rays, covering small rock volumes. To deal with these limitations, we implemented 2D/3D convolutional neural network and generative adversarial network-based super-resolution approaches. They can improve the quality of low-resolution scans, learning mapping functions from low-resolution to high-resolution images. This is one of the first efforts to apply deep learning-based super-resolution to unconventional non-sedimentary digital rocks and real scans. Our findings suggest that these approaches, and mainly 2D U-Net and pix2pix networks trained on paired data, can strongly facilitate high-resolution imaging of large microporous (volcanic) rocks.
Collapse
Affiliation(s)
- Gianmarco Buono
- Istituto Nazionale di Geofisica e Vulcanologia, Osservatorio Vesuviano, Naples, Italy.
| | - Stefano Caliro
- Istituto Nazionale di Geofisica e Vulcanologia, Osservatorio Vesuviano, Naples, Italy
| | - Giovanni Macedonio
- Istituto Nazionale di Geofisica e Vulcanologia, Osservatorio Vesuviano, Naples, Italy
| | - Vincenzo Allocca
- Department of Earth, Environmental and Resources Sciences, University of Naples Federico II, Naples, Italy
| | | | - Lucia Pappalardo
- Istituto Nazionale di Geofisica e Vulcanologia, Osservatorio Vesuviano, Naples, Italy
| |
Collapse
|
4
|
Moassefi M, Faghani S, Khosravi B, Rouzrokh P, Erickson BJ. Artificial Intelligence in Radiology: Overview of Application Types, Design, and Challenges. Semin Roentgenol 2023; 58:170-177. [PMID: 37087137 DOI: 10.1053/j.ro.2023.01.005] [Citation(s) in RCA: 4] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/17/2022] [Revised: 01/16/2023] [Accepted: 01/18/2023] [Indexed: 02/17/2023]
|
5
|
Alqahtani NJ, Niu Y, Wang YD, Chung T, Lanetc Z, Zhuravljov A, Armstrong RT, Mostaghimi P. Super-Resolved Segmentation of X-ray Images of Carbonate Rocks Using Deep Learning. Transp Porous Media 2022. [DOI: 10.1007/s11242-022-01781-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/02/2023]
Abstract
AbstractReliable quantitative analysis of digital rock images requires precise segmentation and identification of the macroporosity, sub-resolution porosity, and solid\mineral phases. This is highly emphasized in heterogeneous rocks with complex pore size distributions such as carbonates. Multi-label segmentation of carbonates using classic segmentation methods such as multi-thresholding is highly sensitive to user bias and often fails in identifying low-contrast sub-resolution porosity. In recent years, deep learning has introduced efficient and automated algorithms that are capable of handling hard tasks with precision comparable to human performance, with application to digital rocks super-resolution and segmentation emerging. Here, we present a framework for using convolutional neural networks (CNNs) to produce super-resolved segmentations of carbonates rock images for the objective of identifying sub-resolution porosity. The volumes used for training and testing are based on two different carbonates rocks imaged in-house at low and high resolutions. We experiment with various implementations of CNNs architectures where super-resolved segmentation is obtained in an end-to-end scheme and using two networks (super-resolution and segmentation) separately. We show the capability of the trained model of producing accurate segmentation by comparing multiple voxel-wise segmentation accuracy metrics, topological features, and measuring effective properties. The results underline the value of integrating deep learning frameworks in digital rock analysis.
Collapse
|
6
|
Welch JL, Xiang J, Mackin SR, Perlman S, Thorne P, O’Shaughnessy P, Strzelecki B, Aubin P, Ortiz-Hernandez M, Stapleton JT. Inactivation of Severe Acute Respiratory Coronavirus Virus 2 (SARS-CoV-2) and Diverse RNA and DNA Viruses on Three-Dimensionally Printed Surgical Mask Materials. Infect Control Hosp Epidemiol 2021; 42:253-260. [PMID: 32783787 PMCID: PMC7463154 DOI: 10.1017/ice.2020.417] [Citation(s) in RCA: 13] [Impact Index Per Article: 4.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/06/2020] [Revised: 08/04/2020] [Accepted: 08/08/2020] [Indexed: 12/20/2022]
Abstract
BACKGROUND Personal protective equipment (PPE) is a critical need during the coronavirus disease 2019 (COVID-19) pandemic. Alternative sources of surgical masks, including 3-dimensionally (3D) printed approaches that may be reused, are urgently needed to prevent PPE shortages. Few data exist identifying decontamination strategies to inactivate viral pathogens and retain 3D-printing material integrity. OBJECTIVE To test viral disinfection methods on 3D-printing materials. METHODS The viricidal activity of common disinfectants (10% bleach, quaternary ammonium sanitizer, 3% hydrogen peroxide, or 70% isopropanol and exposure to heat (50°C, and 70°C) were tested on four 3D-printed materials used in the healthcare setting, including a surgical mask design developed by the Veterans' Health Administration. Inactivation was assessed for several clinically relevant RNA and DNA pathogenic viruses, including severe acute respiratory coronavirus virus 2 (SARS-CoV-2) and human immunodeficiency virus 1 (HIV-1). RESULTS SARS-CoV-2 and all viruses tested were completely inactivated by a single application of bleach, ammonium quaternary compounds, or hydrogen peroxide. Similarly, exposure to dry heat (70°C) for 30 minutes completely inactivated all viruses tested. In contrast, 70% isopropanol reduced viral titers significantly less well following a single application. Inactivation did not interfere with material integrity of the 3D-printed materials. CONCLUSIONS Several standard decontamination approaches effectively disinfected 3D-printed materials. These approaches were effective in the inactivation SARS-CoV-2, its surrogates, and other clinically relevant viral pathogens. The decontamination of 3D-printed surgical mask materials may be useful during crisis situations in which surgical mask supplies are limited.
Collapse
Affiliation(s)
- Jennifer L. Welch
- Medical Service, Iowa City Veterans’ Affairs Medical Center, Iowa City, Iowa
- Department of Internal Medicine, Carver College of Medicine University of Iowa, Iowa City, Iowa
- Department of Microbiology and Immunology, Carver College of Medicine, University of Iowa, Iowa City, Iowa
| | - Jinhua Xiang
- Medical Service, Iowa City Veterans’ Affairs Medical Center, Iowa City, Iowa
- Department of Internal Medicine, Carver College of Medicine University of Iowa, Iowa City, Iowa
- Department of Microbiology and Immunology, Carver College of Medicine, University of Iowa, Iowa City, Iowa
| | - Samantha R. Mackin
- Department of Microbiology and Immunology, Carver College of Medicine, University of Iowa, Iowa City, Iowa
| | - Stanley Perlman
- Department of Microbiology and Immunology, Carver College of Medicine, University of Iowa, Iowa City, Iowa
| | - Peter Thorne
- Department of Occupational and Environmental Health, College of Public Health, University of Iowa, Iowa City, Iowa
| | - Patrick O’Shaughnessy
- Department of Occupational and Environmental Health, College of Public Health, University of Iowa, Iowa City, Iowa
| | | | - Patrick Aubin
- Center for Limb Loss and MoBility (CLiMB), VA Puget Sound Health Care System, Seattle, Washington
- Department of Mechanical Engineering, University of Washington, Seattle, Washington
| | - Monica Ortiz-Hernandez
- Center for Limb Loss and MoBility (CLiMB), VA Puget Sound Health Care System, Seattle, Washington
- Department of Mechanical Engineering, University of Washington, Seattle, Washington
| | - Jack T. Stapleton
- Medical Service, Iowa City Veterans’ Affairs Medical Center, Iowa City, Iowa
- Department of Internal Medicine, Carver College of Medicine University of Iowa, Iowa City, Iowa
- Department of Microbiology and Immunology, Carver College of Medicine, University of Iowa, Iowa City, Iowa
| |
Collapse
|
7
|
Zhang W, Li H, Li Y, Liu H, Chen Y, Ding X. Application of deep learning algorithms in geotechnical engineering: a short critical review. Artif Intell Rev 2021. [DOI: 10.1007/s10462-021-09967-1] [Citation(s) in RCA: 69] [Impact Index Per Article: 23.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 02/08/2023]
|