Carbonate reservoir fracture‐cavity system identification based on the improved YOLOv5s deep learning algorithm DOI Creative Commons

Xiaoyong Feng,

Kai Zhao, Jianguo Zhang

et al.

Energy Science & Engineering, Journal Year: 2024, Volume and Issue: 12(6), P. 2643 - 2660

Published: May 27, 2024

Abstract In carbonate reservoirs characterized by the fracture‐cavity system as storage spaces, drilling process is highly prone to loss of fluid. This not only affects efficiency but can also lead severe accidents, such blowouts. Therefore, it crucial understand distribution pattern these fractures. However, formation rock systems, being controlled various factors, difficult precisely identify. limitation hampers efficient development types oil and gas fields. paper presents a case study M5 5 sub‐section reservoir in Sulige gasfield, proposing an improved You Only Look Once v5s (YOLOv5s) deep learning algorithm. It utilizes enhanced training with conventional logging data identify response characteristics fractures reservoirs. And its identification results have been confirmed be accurate fracture obtained through different means, core samples, cast thin section photographs, imaging data, seismic attributes. method incorporates Ghost convolution module replace Conv backbone network YOLOv5s model, modifies C3 into Bottleneck module, effectively making model more lightweight. Additionally, Convolutional Block Attention Module integrated Neck network, enhancing model's feature extraction capabilities. Finally, employs Efficient Intersection over Union Loss function instead Complete Loss, reducing network's regression loss. The validation using actual demonstrate that this achieves average recognition accuracy 87.3% for system, which 3% improvement baseline (YOLOv5s). enhancement beneficial locating fluid positions

Language: Английский

The impact of grain size heterogeneity on the performance of low-salinity waterflooding in carbonate formations DOI

Amin Toupchian,

Hassan Mahani, Shahab Ayatollahi

et al.

Fuel, Journal Year: 2023, Volume and Issue: 356, P. 129513 - 129513

Published: Aug. 29, 2023

Language: Английский

Citations

11
Evaluation of mechanical properties of porous media materials based on deep learning: Insights from pore structure DOI
Zhaodong Xi, Shuheng Tang, Songhang Zhang

et al.

Fuel, Journal Year: 2024, Volume and Issue: 371, P. 131923 - 131923

Published: May 20, 2024

Language: Английский

Citations

4
Interporosity Flow Between Matrix and Fractures in Carbonates: A Study of its Impact on Oil Production DOI
Dmitriy A. Martyushev, Inna N. Ponomareva, Shadfar Davoodi

et al.

Arabian Journal for Science and Engineering, Journal Year: 2024, Volume and Issue: unknown

Published: Sept. 2, 2024

Language: Английский

Citations

4
Pore network modeling of gas–water two-phase flow in deformed multi-scale fracture-porous media DOI Creative Commons

Dai-Gang Wang,

Yushan Ma, HU Zhe

et al.

Petroleum Science, Journal Year: 2025, Volume and Issue: unknown

Published: March 1, 2025

Language: Английский

Citations

0
CO2 Storage Behavior in Nanopores: Implications for CO2 Sequestration in Ultra-Tight Geological Formations DOI

Guodai Wu,

Bingxiang Huang,

Lijun Cheng

et al.

Industrial & Engineering Chemistry Research, Journal Year: 2023, Volume and Issue: 62(34), P. 13677 - 13686

Published: Aug. 15, 2023

The fatal challenge that human beings are currently facing is global warming as a result of excessive CO2 emission in the atmosphere. sequestration, gaseous injection into ultra-tight geological sites, regarded promising approach to achieve reduction substantially. In this work, emphasis paid storage potential inside depleted shale or coal seam where presence nanopores rich, and molecules store both bulk adsorption states nanopores. microscopic characterization on behavior nanospace, particularly quantitative description difference between states, still lacking. With intention shed light nanoconfined behavior, simple yet robust theoretical work rooting chemical equilibrium each molecule entire system implemented, shift critical properties due nanoconfinement effect coupled. Then, density can be described function distance away from nanopore wall; found accumulate more densely while approaching wall, suggesting an perspective. Results show (a) adsorption-phase thickness insensitive size, ranging 0.58 0.64 nm, ratio over could reach 1–2 orders magnitude; (b) amount 2 nm able 7.2 times macropores, displaying unique advantage formations sequestration conventional oil/gas reservoirs; (c) increasing pressure improve total performance, improvement magnitude at low-pressure range great 2.9 high-pressure range. This provides doable framework investigate existence nanopores, enriching basis identify favorable sites for sequestration.

Language: Английский

Citations

10
Impacts of interactions with low-mineralized water on permeability and pore behavior of carbonate reservoirs DOI Creative Commons
Dmitriy A. Martyushev, Inna N. Ponomareva,

Vasiliy I. Chernykh

et al.

Energy Geoscience, Journal Year: 2024, Volume and Issue: 5(4), P. 100340 - 100340

Published: Aug. 28, 2024

Language: Английский

Citations

3
Distribution patterns of waterflooded oil and gas distribution in carbonate reservoirs based on a triple porosity model DOI

Hongda Gao,

Linsong Cheng,

Pin Jia

et al.

Physics of Fluids, Journal Year: 2025, Volume and Issue: 37(3)

Published: March 1, 2025

Weakly volatile fracture-pore type carbonate reservoirs are characterized by the presence of fractures and complex pore structures, yet fluid distribution patterns across different types remain unclear. To address this, this study categorizes pores into fractures, large pores, small based on observations from cast thin sections. Significant differences in flow characteristics found among these fractures. Building upon parameter characterization methods established previous research, paper integrates improves approaches, developing a comprehensive calculation method for permeability, capillary pressure, relative permeability applicable to types. Based three-phase model fracture–large pore–small triple porosity system is developed, successfully simulating migration oil gas under various development methods. The results indicate that during depletion stage, remaining primarily resides pores; after water injection, recovery increases significantly. However, later stages exhibit an “oil-locking” phenomenon, while show “residual gas.” A comparison injection indicates asynchronous production can help maintain reservoir pressure stability reduce utilization This provides important theoretical foundation efficient weakly reservoirs.

Language: Английский

Citations

0
Clay mineral content and their impact on reservoir quality: Insight into the carbonate reservoirs oil fields, Central-Eastern Russia DOI Creative Commons
Dmitriy A. Martyushev, Shadfar Davoodi,

Anastasia D. Anickaeva

et al.

Petroleum Research, Journal Year: 2025, Volume and Issue: unknown

Published: April 1, 2025

Language: Английский

Citations

0
Effect of non-uniform swelling on coal multiphysics during gas injection: The triangle approach DOI Creative Commons
Yifan Huang, Jishan Liu, Yaoyao Zhao

et al.

Journal of Rock Mechanics and Geotechnical Engineering, Journal Year: 2023, Volume and Issue: 16(4), P. 1362 - 1372

Published: July 27, 2023

In current dual porosity/permeability models, there exists a fundamental assumption that the adsorption-induced swelling is distributed uniformly within representative elementary volume (REV), irrespective of its internal structures and transient processes. However, both processes can lead to non-uniform swelling. this study, we hypothesize responsible for why coal permeability in experimental measurements not only controlled by effective stress but also affected We propose concept triangle composed paths characterize evolution serve as core link coupled multiphysics. A path determined dimensionless volumetric ratio ratio. Different have same start end point, each represents unique case. The diagonal case uniform while two perpendicular boundaries localized all intermediate cases populate inside triangle. corresponding relations between response multiphysics are established coefficient. define method approach models path-based ones. proposed verified against long-term measurement strains under constant stress. Our results demonstrate during gas injection, responses close dependence on path, future experiments field predictions, must be considered. ©2023 Institute Rock Soil Mechanics, Chinese Academy Sciences. Production hosting Elsevier B.V. This an open access article CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).

Language: Английский

Citations

6
Effects of Reservoir Heterogeneity on CO2 Dissolution Efficiency in Randomly Multilayered Formations DOI Creative Commons
Xiaoyu Fang, Yanxin Lv, Chao Yuan

et al.

Energies, Journal Year: 2023, Volume and Issue: 16(13), P. 5219 - 5219

Published: July 7, 2023

Carbon dioxide (CO2) dissolution is the secondary trapping mechanism enhancing long-term security of CO2 in confined geological formations. injected into a randomly multilayered formation will preferentially migrate along high permeability layers, increasing efficiency. In this study, sequential Gaussian simulation adopted to construct stratified saline formations, and two-phase flow based on MRST established illustrate spatial mobility distribution migration. The results show that gravity index G heterogeneity σY2 are two predominant factors controlling transports. migration shows totally different under heterogeneity. When discrepancy relatively larger, migrates horizontal layer without accompanying vertical For controlled by index, governed supercritical gaseous characteristics. medium upward lateral characteristics plume determined smaller, key factor influencing Permeability decisive determining final This investigation reservoirs provides an effective reference for storage.

Language: Английский

Citations

4