Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation
Abstract The introduction of deep learning techniques has revolutionized the automated segmentation of digital rock images. These methods enable precise evaluations of critical properties such as porosity and fluid flow characteristics, thereby enhancing the efficiency of reservoir characterization....
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-07211-2 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849402571522834432 |
|---|---|
| author | Mazaher Hayatdavoudi Mohammad Emami Niri Ahmad Kalhor |
| author_facet | Mazaher Hayatdavoudi Mohammad Emami Niri Ahmad Kalhor |
| author_sort | Mazaher Hayatdavoudi |
| collection | DOAJ |
| description | Abstract The introduction of deep learning techniques has revolutionized the automated segmentation of digital rock images. These methods enable precise evaluations of critical properties such as porosity and fluid flow characteristics, thereby enhancing the efficiency of reservoir characterization. This study explores the application of state-of-the-art Convolutional Neural Network (CNN) architectures for analyzing rock micro-CT images, aiming to enhance reservoir characterization efficiency. Specifically, we implement various deep learning models, including Fully Convolutional Networks, Encoder-Decoder Models, Multi-Scale Networks, Dilated Convolution Models, and Attention-Based Models. The segmentation performance of these CNN architectures is benchmarked against the traditional Otsu thresholding method using a dataset of 5,000 2D slices of ten distinct sandstone types, each with a voxel resolution of 2.25 × 2.25 × 2.25 µm. Our evaluation utilizes pixel-wise accuracy metrics such as F1-score, binary-IOU, Recall, and Precision. To replicate the physics of pore-scale fluid movement, various numerical simulation methods such as the Lattice Boltzmann Method (LBM), Pore Network Modeling (PNM), and Computational Fluid Dynamics (CFD) are employed to predict the permeability and rock formation factor of a blind sample, using CNNs for image segmentation. Our findings reveal that advanced CNNs significantly outperform the Otsu method in both pixel-wise segmentation accuracy and fluid flow simulation performance. Among all CNNs, EfficientNetB0-Unet, VGG16-Unet, and Enet exhibit exceptional performance in segmenting complex pore structures, as evidenced by their high F1-scores and binary-IOU metrics as well as accurate predictions of porosity, permeability, and formation factor. |
| format | Article |
| id | doaj-art-b5058c13568c4b22bd77db7c1a3e243f |
| institution | Kabale University |
| issn | 2045-2322 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj-art-b5058c13568c4b22bd77db7c1a3e243f2025-08-20T03:37:30ZengNature PortfolioScientific Reports2045-23222025-07-0115112110.1038/s41598-025-07211-2Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluationMazaher Hayatdavoudi0Mohammad Emami Niri1Ahmad Kalhor2Institute of Petroleum Engineering, School of Chemical Engineering, College of Engineering, University of TehranInstitute of Petroleum Engineering, School of Chemical Engineering, College of Engineering, University of TehranSchool of Electrical and Computer Engineering, College of Engineering, University of TehranAbstract The introduction of deep learning techniques has revolutionized the automated segmentation of digital rock images. These methods enable precise evaluations of critical properties such as porosity and fluid flow characteristics, thereby enhancing the efficiency of reservoir characterization. This study explores the application of state-of-the-art Convolutional Neural Network (CNN) architectures for analyzing rock micro-CT images, aiming to enhance reservoir characterization efficiency. Specifically, we implement various deep learning models, including Fully Convolutional Networks, Encoder-Decoder Models, Multi-Scale Networks, Dilated Convolution Models, and Attention-Based Models. The segmentation performance of these CNN architectures is benchmarked against the traditional Otsu thresholding method using a dataset of 5,000 2D slices of ten distinct sandstone types, each with a voxel resolution of 2.25 × 2.25 × 2.25 µm. Our evaluation utilizes pixel-wise accuracy metrics such as F1-score, binary-IOU, Recall, and Precision. To replicate the physics of pore-scale fluid movement, various numerical simulation methods such as the Lattice Boltzmann Method (LBM), Pore Network Modeling (PNM), and Computational Fluid Dynamics (CFD) are employed to predict the permeability and rock formation factor of a blind sample, using CNNs for image segmentation. Our findings reveal that advanced CNNs significantly outperform the Otsu method in both pixel-wise segmentation accuracy and fluid flow simulation performance. Among all CNNs, EfficientNetB0-Unet, VGG16-Unet, and Enet exhibit exceptional performance in segmenting complex pore structures, as evidenced by their high F1-scores and binary-IOU metrics as well as accurate predictions of porosity, permeability, and formation factor.https://doi.org/10.1038/s41598-025-07211-2Convolution neural networkDigital rock physicsLattice Boltzmann methodPore network modelingComputational fluid dynamicsRock micro-CT image segmentation |
| spellingShingle | Mazaher Hayatdavoudi Mohammad Emami Niri Ahmad Kalhor Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation Scientific Reports Convolution neural network Digital rock physics Lattice Boltzmann method Pore network modeling Computational fluid dynamics Rock micro-CT image segmentation |
| title | Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation |
| title_full | Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation |
| title_fullStr | Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation |
| title_full_unstemmed | Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation |
| title_short | Comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation |
| title_sort | comparative analysis of sandstone microtomographic image segmentation using advanced convolutional neural networks with pixelwise and physical accuracy evaluation |
| topic | Convolution neural network Digital rock physics Lattice Boltzmann method Pore network modeling Computational fluid dynamics Rock micro-CT image segmentation |
| url | https://doi.org/10.1038/s41598-025-07211-2 |
| work_keys_str_mv | AT mazaherhayatdavoudi comparativeanalysisofsandstonemicrotomographicimagesegmentationusingadvancedconvolutionalneuralnetworkswithpixelwiseandphysicalaccuracyevaluation AT mohammademaminiri comparativeanalysisofsandstonemicrotomographicimagesegmentationusingadvancedconvolutionalneuralnetworkswithpixelwiseandphysicalaccuracyevaluation AT ahmadkalhor comparativeanalysisofsandstonemicrotomographicimagesegmentationusingadvancedconvolutionalneuralnetworkswithpixelwiseandphysicalaccuracyevaluation |