Quantitative evaluation of unconsolidated sandstone heavy oil reservoirs based on machine learning

Wang, Zhao; Tang, Hongming; Hou, Yanan; Shi, Hongfu; Li, Jingling; Yang, Tao; Feng, Yanhuan; Wang, Meng

doi:10.1002/gj.4604

Cited by 6 publications

(3 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulated particle migration takes place within the fluid flow field, with a fluid density of 1.04 g/cm 3 based on the properties of crude oil in the Bohai A oilfield. 32,33 The fluid viscosity is set to 10 mPa•s 33,34 (Table 1).…”

Section: Numerical Simulation Parametermentioning

confidence: 99%

“…Simulated particle migration occurs within the fluid flow field, with a fluid density of 1.04 g/cm 3 based on the properties of crude oil in Bohai A oilfield. Simulated particle migration takes place within the fluid flow field, with a fluid density of 1.04 g/cm 3 based on the properties of crude oil in the Bohai A oilfield 32,33 . The fluid viscosity is set to 10 mPa·s 33,34 (Table 1).…”

Section: Numerical Simulation and Laser Engraving Throat Modelmentioning

confidence: 99%

See 1 more Smart Citation

Analysis of damage mechanisms and controlling factors of fine particle migration in unconsolidated sandstone reservoirs based on reservoir classification

Wang,

Yin,

Tang

et al. 2024

Energy Science & Engineering

Self Cite

View full text Add to dashboard Cite

Particle migration in oil and gas reservoirs is a common phenomenon in the process of oil and gas development, and is considered to be an important reason for the damage of reservoir permeability and the reduction of oil and gas productivity. The mechanism of this phenomenon includes the desorption, migration, and precipitation of particles, which eventually clogs the throat and causes reservoir damage. Therefore, it is necessary to accurately characterize the complex mechanism of particle migration and identify the main controlling factors of particle migration, which is very important for efficient oilfield development and plugging solution. First, the reservoir types are divided into three types and the pore structure models of different types of reservoirs are established. Then, computational fluid dynamics and discrete element coupling method numerical simulation and microscopic visualization of pore throat structure model were combined, to characterize the rules of particles and migration, and analyze the main controlling factors. Finally, a typical model of particle migration and clogging is established. The results show that particle size/throat and particle concentration are the key factors affecting particle plugging, and particle migration has the least effect on the permeability of Type I reservoir and the greatest damage to Type III reservoir. According to the mechanical and hydrodynamic behavior of particles in porous media, three mechanisms and six modes of particle plugging are proposed.

show abstract

Section: Numerical Simulation Parametermentioning

confidence: 99%

Section: Numerical Simulation and Laser Engraving Throat Modelmentioning

confidence: 99%

Analysis of damage mechanisms and controlling factors of fine particle migration in unconsolidated sandstone reservoirs based on reservoir classification

Wang,

Yin,

Tang

et al. 2024

Energy Science & Engineering

Self Cite

View full text Add to dashboard Cite

show abstract

“…The commonly used reservoir classification methods based on logging interpretation are limited by linear relationships and empirical formulas. Therefore, Wang et al (2023) proposes using machine learning algorithms to overcome these limitations and accurately classify reservoirs based on their complex and nonlinear geological characteristics. The study considered four representative evaluation parameters and used an improved K-means method to establish a reservoir classification evaluation system.…”

Section: Research Outputs Of This Special Issuementioning

confidence: 99%

Application of artificial intelligence in geotechnical and geohazard investigations

et al. 2023

View full text Add to dashboard Cite

The application of artificial intelligence (AI) and big data in geohazard investigations has gained popularity due to the development of machine learning algorithms and data collection methods. Previous studies have compared and applied various machine learning‐based methods, such as conventional machine learning, deep learning, and transfer learning in different areas. This special issue provides state‐of‐the‐art information on the use of AI in geotechnical research, particularly in the Three Gorges Reservoir (TGR) area and adjoining regions. The aim of this volume is to serve as a reference for future researchers interested in exploring the potential of AI in geohazard investigations. It is hoped that this special issue will contribute to the development of guidelines for enhancing the application of AI and big data in geotechnical research, thereby improving our understanding of geological terrains and their associated hazards.

show abstract

Probabilistic classification of surrounding rock mass of tunnels based on fully Bayesian Gaussian process classification (fB‐GPC) with consideration of influencing factors selection

Song,

Zhao,

2024

Geological Journal

View full text Add to dashboard Cite

Rock mass classification is of great significance in guiding the design and construction of tunnels, which is often determined through single‐factor or multi‐factor classification methods based on some readily available rock indices, for example, dynamic elastic modulus, degree of tectonization, and so forth. Although these methods work reasonably well in some cases, they tend to lead to inaccurate classification results due to the pre‐selected main factor or function forms, especially for tunnels with complex geological conditions. Alternatively, the classification may be achieved with the aid of some machine learning (ML) methods, which are data‐driven, hence bypassing pre‐determination of the mathematical function forms of the main factor(s). Note although these ML methods perform well in the classification of surrounding rock mass, they generally employ all measurements of readily available rock indices as input variables, which might lead to excessive model complexity and a potential decrease in generalization performance. In this paper, a fully Bayesian Gaussian process classification (fB‐GPC) approach is proposed for probabilistic classification of surrounding rock mass, which is data‐driven and can select the optimal combination of main factors that affect rock mass classification. A real‐life example is used to illustrate and validate the proposed approach. Results show that the proposed fB‐GPC method performs very well in determination of the most important factor for classification of surrounding rock mass, with an area under the receiver operating characteristic curve (AUC) of around 0.98. A sensitivity study is also performed to systematically examine the accuracy and robustness of the proposed approach in this study.

show abstract

Quantitative evaluation of unconsolidated sandstone heavy oil reservoirs based on machine learning

Cited by 6 publications

References 59 publications

Analysis of damage mechanisms and controlling factors of fine particle migration in unconsolidated sandstone reservoirs based on reservoir classification

Analysis of damage mechanisms and controlling factors of fine particle migration in unconsolidated sandstone reservoirs based on reservoir classification

Application of artificial intelligence in geotechnical and geohazard investigations

Probabilistic classification of surrounding rock mass of tunnels based on fully Bayesian Gaussian process classification (fB‐GPC) with consideration of influencing factors selection

Contact Info

Product

Resources

About