3D Permeability Characterization Based on Pore Structure Analysis and Multi-Parameters Seismic Inversion and Its Application in H Oilfield

Chen, Xin; Wang, Guihai; Wang, Zhaofeng; Liu, Zundou; Liu, Zhaowei; Cui, Yi; Tian, Wenyuan; Wei, Xiaodong; Hou, Liugen; Yang, Ke; Chen, Gang; Yaliang, Xia; Xi, Yan; Zhang, Zeren; Liu, Jingluan

doi:10.2523/19180-ms

“…In MorphD, we propose an inventive scheme, the controllable measurable volume (CMV), to substitute for the representative elemental volume (REV) concept [31,[43][44][45][46][47][48]. MorphD finally rebuilds all 3D segmented sections like LEGO [49,50] to predict -without any fluid flow simulation [51][52][53][54] -the 3D permeability [55][56][57] using two parallel and serial aggregation governing equations [58]. MorphD validates the equation's results with polymer-based 3D printed micromodel experiments [21,59,60] (Fig.…”

Section: Introductionmentioning

confidence: 99%

3D Geometrical Untangling of Heterogeneous Fabric Darcy’s Flow using the Morphology Decoder

Alfarisi¹,

Raza²,

Zhang³

et al. 2022

Preprint

1

0

View full text Add to dashboard Cite

Permeability has a dominant influence on the flow behavior of a natural fluid, and without proper quantification, biological fluids (hydrocarbons) and water resources become waste. During the first decades of the 21st century, permeability quantification from nano-microporous media images emerged, aided by 3D pore network flow simulation, primarily using the Lattice Boltzmann simulator. Earth scientists realized that the simulation process holds millions of flow dynamics calculations with accumulated errors and high computing power consumption. Therefore, accuracy and efficiency challenges obstruct planetary exploration. To efficiently and consistently predict permeability with high quality, we propose the morphology decoder. It is a parallel and serial flow reconstruction of machine learning-driven semantically segmented heterogeneous rock texture images of 3D X-ray microcomputerized tomography (µCT) and nuclear magnetic resonance (MRI). For 3D vision, we introduce a controllable measurable volume as a new supervised semantic segmentation, in which a unique set of voxel intensities corresponds to grain and pore throat sizes. The morphology decoder demarks and aggregates the morphology boundaries in a novel way to quantify permeability. The morphology decoder method consists of five novel processes described in this paper. These novel processes are (1) geometrical: 3D permeability governing equation, (2) machine learning: guided 3D property recognition of rock morphology, (3) analytical: 3D image properties integration model for permeability, (4) experimental: MRI permeability imager, and (5) morphology decoder (the process that integrates the other four novel processes).

show abstract

“…In MorphD, we propose an inventive scheme, the Controllable-Measurable-Volume (CMV), to substitute the Representative Elemental Volume (REV) concept [31,[43][44][45][46][47][48]. MorphD finally rebuilds all 3D segmented sections like a LEGO [49,50] to predict -without any fluid flow simulation [51][52][53][54] -the 3D permeability [55][56][57], using two parallel and serial aggregation governing equations [58]. MorphD validates the equation's results with polymer-based 3D printed micromodel experiments [21,59,60] (Fig.…”

Section: Introductionmentioning

confidence: 99%

Morphology Decoder to Predict Heterogeneous Rock Permeability with Machine Learning Guided 3D Vision

Alfarisi¹,

Raza²,

Ouzzane³

et al. 2021

Preprint

1

0

View full text Add to dashboard Cite

<a></a><a>Permeability has a dominant influence on the flow behavior of a natural fluid, and without proper quantification, biological fluids (Hydrocarbons) and water resources become waste. During the first decades of the 21st century, permeability quantification from nano-micro porous media images emerged, aided by 3D pore network flow simulation, primarily using the Lattice Boltzmann simulator. Earth scientists realized that the simulation process holds millions of flow dynamics calculations with accumulated errors and high computing power consumption. Therefore, accuracy and efficiency challenges obstruct planetary exploration. To efficiently, consistently predict permeability with high quality, we propose the Morphology Decoder. It is a parallel and serial flow reconstruction of machine learning-driven semantically segmented heterogeneous rock texture images of 3D X-Ray Micro Computerized Tomography (μCT) and Nuclear Magnetic Resonance (MRI). For 3D vision, we introduce controllable-measurable-volume as new supervised semantic segmentation, in which a unique set of voxel intensity corresponds to grain and pore throat sizes. The morphology decoder demarks and aggregates the morphologies' boundaries in a novel way to quantify permeability. The morphology decoder method consists of five novel processes, which we describe in this paper, these novel processes are (1) Geometrical: 3D Permeability Governing Equation, (2) Machine Learning: Guided 3D Properties Recognition of Rock Morphology, (3) Analytical: 3D Image Properties Integration Model for Permeability, (4) Experimental: MRI Permeability Imager, and (5) Morphology Decoder (the process that integrates the other four novel processes).</a>

show abstract

Morphology Decoder to Predict Heterogeneous Rock Permeability with Machine Learning Guided 3D Vision

Alfarisi¹,

Raza²,

Ouzzane³

et al. 2021

Preprint

View full text Add to dashboard Cite

<a></a><a>Permeability has a dominant influence on the flow behavior of a natural fluid, and without proper quantification, biological fluids (Hydrocarbons) and water resources become waste. During the first decades of the 21st century, permeability quantification from nano-micro porous media images emerged, aided by 3D pore network flow simulation, primarily using the Lattice Boltzmann simulator. Earth scientists realized that the simulation process holds millions of flow dynamics calculations with accumulated errors and high computing power consumption. Therefore, accuracy and efficiency challenges obstruct planetary exploration. To efficiently, consistently predict permeability with high quality, we propose the Morphology Decoder. It is a parallel and serial flow reconstruction of machine learning-driven semantically segmented heterogeneous rock texture images of 3D X-Ray Micro Computerized Tomography (μCT) and Nuclear Magnetic Resonance (MRI). For 3D vision, we introduce controllable-measurable-volume as new supervised semantic segmentation, in which a unique set of voxel intensity corresponds to grain and pore throat sizes. The morphology decoder demarks and aggregates the morphologies' boundaries in a novel way to quantify permeability. The morphology decoder method consists of five novel processes, which we describe in this paper, these novel processes are (1) Geometrical: 3D Permeability Governing Equation, (2) Machine Learning: Guided 3D Properties Recognition of Rock Morphology, (3) Analytical: 3D Image Properties Integration Model for Permeability, (4) Experimental: MRI Permeability Imager, and (5) Morphology Decoder (the process that integrates the other four novel processes).</a>

show abstract

3D Permeability Characterization Based on Pore Structure Analysis and Multi-Parameters Seismic Inversion and Its Application in H Oilfield

Cited by 3 publications

References 6 publications

3D Geometrical Untangling of Heterogeneous Fabric Darcy’s Flow using the Morphology Decoder

3D Geometrical Untangling of Heterogeneous Fabric Darcy’s Flow using the Morphology Decoder

Morphology Decoder to Predict Heterogeneous Rock Permeability with Machine Learning Guided 3D Vision

Morphology Decoder to Predict Heterogeneous Rock Permeability with Machine Learning Guided 3D Vision

Contact Info

Product

Resources

About