Journal articles on the topic 'Rock image'
To see the other types of publications on this topic, follow the link: Rock image.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Rock image.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Otiede, David, and Ke Jian Wu. "The Effect of Image Resolution on the Geometry and Topological Characteristics of 3-D Reconstructed Images of Reservoir Rock Samples." International Journal of Engineering Research in Africa 6 (November 2011): 37–44. http://dx.doi.org/10.4028/www.scientific.net/jera.6.37.
Full textAbstract:
The effect of image resolution on the measured geometry and topological characteristics of network models extracted from 3-D micro-computer tomography images has been investigated. The study was conducted by extracting geologically realistic networks from images of two rock samples, imaged at different resolutions. The rock samples involved were a Castlegate Sandstone and a Carbonate-28 reservoir rock. Two-dimensional images of these rocks were obtained at a magnification of ×50. The carbonate sample was studied at two different resolutions of 0.133 microns and 1.33 microns, while the sandstone was studied at 5.60 microns. Three-dimensional images of these 2-D images were obtained via image reconstruction, to generate the pore architecture models (PAMs) from which networks models of the imaged rocks were extracted with the aid of Pore Analysis software Tools (PATs). The measured geometry and topology (GT) properties included Coordination Number, Pore Shape Factor, Pore Size Distribution, and Pore Connectivity. The results showed that the measured geometry-topology (GT) characteristics of a network model depend greatly on the image resolution used for the model. Depending on the micro-structure of the reservoir rock, a minimum image resolution is necessary to properly define the geometrical and topological characteristics of the given porous medium.
2
Saxena, Nishank, Ronny Hofmann, Amie Hows, Erik H. Saenger, Luca Duranti, Joe Stefani, Andreas Wiegmann, Abdulla Kerimov, and Matthias Kabel. "Rock compressibility from microcomputed tomography images: Controls on digital rock simulations." GEOPHYSICS 84, no. 4 (July 1, 2019): WA127—WA139. http://dx.doi.org/10.1190/geo2018-0499.1.
Full textAbstract:
Rock compressibility is a major control of reservoir compaction, yet only limited core measurements are available to constrain estimates. Improved analytical and computational estimates of rock compressibility of reservoir rock can improve forecasts of reservoir production performance and the geomechanical integrity of compacting reservoirs. The fast-evolving digital rock technology can potentially overcome the need for simplification of pores (e.g., ellipsoids) to estimate rock compressibility as the computations are performed on an actual pore-scale image acquired using 3D microcomputed tomography (micro-CT). However, the computed compressibility using a digital image is impacted by numerous factors, including imaging conditions, image segmentation, constituent properties, choice of numerical simulator, rock field of view, how well the grain contacts are resolved in an image, and the treatment of grain-to-grain contacts. We have analyzed these factors and quantify their relative contribution to the rock moduli computed using micro-CT images of six rocks: a Fontainebleau sandstone sample, two Berea sandstone samples, a Castelgate sandstone sample, a grain pack, and a reservoir rock. We find that image-computed rock moduli are considerably stiffer than those inferred using laboratory-measured ultrasonic velocities. This disagreement cannot be solely explained by any one of the many controls when considered in isolation, but it can be ranked by their relative contribution to the overall rock compressibility. Among these factors, the image resolution generally has the largest impact on the quality of image-derived compressibility. For elasticity simulations, the quality of an image resolution is controlled by the ratio of the contact length and image voxel size. Images of poor resolution overestimate contact lengths, resulting in stiffer simulation results.
3
Tawfeeq, Yahya Jirjees, and Jalal A. Al-Sudani. "Digital Rock Samples Porosity Analysis by OTSU Thresholding Technique Using MATLAB." Iraqi Journal of Chemical and Petroleum Engineering 21, no. 3 (September 30, 2020): 57–66. http://dx.doi.org/10.31699/ijcpe.2020.3.8.
Full textAbstract:
Porosity plays an essential role in petroleum engineering. It controls fluid storage in aquifers, connectivity of the pore structure control fluid flow through reservoir formations. To quantify the relationships between porosity, storage, transport and rock properties, however, the pore structure must be measured and quantitatively described. Porosity estimation of digital image utilizing image processing essential for the reservoir rock analysis since the sample 2D porosity briefly described. The regular procedure utilizes the binarization process, which uses the pixel value threshold to convert the color and grayscale images to binary images. The idea is to accommodate the blue regions entirely with pores and transform it to white in resulting binary image. This paper presents the possibilities of using image processing for determining digital 2D rock samples porosity in carbonate reservoir rocks. MATLAB code created which automatically segment and determine the digital rock porosity, based on the OTSU's thresholding algorithm. In this work, twenty-two samples of 2D thin section petrographic image reservoir rocks of one Iraqi oil field are studied. The examples of thin section images are processed and digitized, utilizing MATLAB programming. In the present study, we have focused on determining of micro and macroporosity of the digital image. Also, some pore void characteristics, such as area and perimeter, were calculated. Digital 2D image analysis results are compared to laboratory core investigation results to determine the strength and restrictions of the digital image interpretation techniques. Thin microscopic image porosity determined using OTSU technique showed a moderate match with core porosity.
4
Nababan, Benyamin Elilaski, Eliza Veronica Zanetta, Nahdah Novia, and Handoyo Handoyo. "ESTIMASI NILAI POROSITAS DAN PERMEABILITAS DENGAN PENDEKATAN DIGITAL ROCK PHYSICS (DRP) PADA SAMPEL BATUPASIR FORMASI NGRAYONG, CEKUNGAN JAWA TIMUR BAGIAN UTARA." Jurnal Geofisika Eksplorasi 5, no. 3 (January 17, 2020): 34–44. http://dx.doi.org/10.23960/jge.v5i3.34.
Full textAbstract:
Reservoir rock permeability and porosity are physical properties of rocks that control reservoir quality. Conventionally, rock porosity and permeability values are obtained from measurements in the laboratory or through well logs. At present, calculation of porosity and permeability can be calculated using digital image processing / Digital Rock Physics (DRP). Core data samples are processed by X-ray diffraction using CT-micro-tomography scan. The result is an image model of the core sample, 2D and 3D images. The combination of theoretical processing and digital images can be obtained from the value of porosity and permeability of rock samples. In this study, we calculated porosity and permeability values using the Digital Rock Physics (DRP) approach in sandstone samples from the Ngrayong Formation, North East Java Basin. The results of the digital image simulation and processing on the Ngrayong Formation sandstone samples ranged in value from 33.50% and permeability around 1267.02 mDarcy.
5
Chen, Yulong, and Hongwei Zhang. "An Improved C-V Model and Application to the Coal Rock Mesocrack Images." Geofluids 2020 (July 17, 2020): 1–11. http://dx.doi.org/10.1155/2020/8852209.
Full textAbstract:
In order to accurately and comprehensively obtain information about coal rock mesocrack images, image processing technique based on partial differential equation (PDE) is introduced in order to expound on the active contour model without edges and overcome the deficiency of the C-V model. The improved C-V model is adopted in order to process mesoimages of coal rocks containing single and multiple cracks and obtain high-quality binary images of coal rock mesocracks and the effective characteristic parameters of coal rock mesostructures through quantitative processing, which will lay solid foundations for the follow-up research into coal rock seepage computation and damage calculation. Studies have shown that, compared to the original C-V model, the improved model achieves better image segmentation effects and more accurate quantitative information about coal rock mesostructures for coal rock mesoimages with low contrast ratios and nonuniform grayscale, a fact showing that it can be applied to the calculation of coal rock permeability and damage factors.
6
Guo, Chenlu, and Zhiyuan Li. "Automatic Rock Classification Algorithm Based on Ensemble Residual Network and Merged Region Extraction." Advances in Multimedia 2022 (March 20, 2022): 1–11. http://dx.doi.org/10.1155/2022/3982892.
Full textAbstract:
Lithology identification of rocks is an important part in the field of oil and gas exploration, mineral exploration, and geological analysis. How to accomplish rock classification is a key issue for the further development of the geology industry. The current main method for classifying rock pictures containing background is to select sample points or disregard the disturbance of the background. For more accurate classification, the rock part extraction method for rock images containing boundaries is designed to eliminate the influence of background. First, the rock parts are extracted based on the image gradient information and color information, respectively. Then, the two images are intersected to realize the refinement of pixel-level information to obtain a pure rock image. Ensemble ResNet18 (ERN18) is designed as an image classification model. It contains basic blocks to reduce the loss of features during the training process. The method breaks the neglect of most previous studies on background interference. The effect of misclassification in certain regions on the results is eliminated by ensemble learning based on the voting method. The classification results are further improved. Compared with the effects of LeNet, AlexNet, and ResNet, ERN18 has achieved significant results.
7
Guha, A., and K. Vinod Kumar. "Potential of thermal emissivity for mapping of greenstone rocks and associated granitoids of Hutti Maski Schist belt, Karnataka." ISPRS - International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XL-8 (November 28, 2014): 423–30. http://dx.doi.org/10.5194/isprsarchives-xl-8-423-2014.
Full textAbstract:
In the present study, different temperature-emissivity separation algorithms were used to derive emissivity images based on processing of ASTER( Advanced spaceborne thermal emission and reflection radiometer) thermal bands. These emissivity images have been compared with each other in terms of geological information for mapping of major rock types in Hutti Maski schist Belt and its associated granitoids. Thermal emissivity images are analyzed conjugately with thermal radiance image, radiant temperature image and albedo image of ASTER bands to understand the potential of thermal emissivity in delineating different rock types of Archaean Greenstone belt. The emissivity images derived using different emissivity extraction algorithms are characterised with poor data dimensionality and signal to noise ratio. Therefore, Inverse MNF false-colour composites(FCC) are derived using bands having better signal to noise(SNR)ratio to enhance the contrast in emissivity. It has been observed that inverse-MNF of emissivity image; which is derived using emissivity-normalisation method is suitable for delineating silica variations in granite and granodioritic gneiss in comparison to other inverse- MNF-emissivity composites derived using other emissivity extraction algorithms(reference channel and alpha residual method). Based on the analysis of ASTER derived emissivity spectra of each rocks, band ratios are derived(band 14/12,band 10/12) and these ratios are used to delineate the rock types based on index based FCC image. This FCC image can be used to delineate granitoids with different silica content. The geological information derived based on processing of ASTER thermal images are further compared with the image analysis products derived using ASTER visible-near-infrared(VNIR) and shortwave infrared(SWIR) bands. It has been observed that delineation of different mafic rocks or greenstone rocks(i.e. separation between chlorite schist and metabasalt) are better in SWIR composites and these composites also provide comparable results with thermal bands in terms of delineation of different types of granitoids.
8
Wang, Cong, Zian Zhang, Yongqiang Zhang, Rui Tian, and Mingli Ding. "GMSRI: A Texture-Based Martian Surface Rock Image Dataset." Sensors 21, no. 16 (August 10, 2021): 5410. http://dx.doi.org/10.3390/s21165410.
Full textAbstract:
CNN-based Martian rock image processing has attracted much attention in Mars missions lately, since it can help planetary rover autonomously recognize and collect high value science targets. However, due to the difficulty of Martian rock image acquisition, the accuracy of the processing model is affected. In this paper, we introduce a new dataset called “GMSRI” that is a mixture of real Mars images and synthetic counterparts which are generated by GAN. GMSRI aims to provide a set of Martian rock images sorted by the texture and spatial structure of rocks. This paper offers a detailed analysis of GMSRI in its current state: Five sub-trees with 28 leaf nodes and 30,000 images in total. We show that GMSRI is much larger in scale and diversity than the current same kinds of datasets. Constructing such a database is a challenging task, and we describe the data collection, selection and generation processes carefully in this paper. Moreover, we evaluate the effectiveness of the GMSRI by an image super-resolution task. We hope that the scale, diversity and hierarchical structure of GMSRI can offer opportunities to researchers in the Mars exploration community and beyond.
9
Schneider, Marc H., Patrick Tabeling, Fadhel Rezgui, Martin G. Lüling, and Aurelien Daynes. "Novel microscopic imager instrument for rock and fluid imaging." GEOPHYSICS 74, no. 6 (November 2009): E251—E262. http://dx.doi.org/10.1190/1.3261801.
Full textAbstract:
Core analysis from reservoir rock plays an important role in oil and gas exploration as it can provide a large number of rock properties. Some of these rock properties can be extracted by image analysis of microscopic rock images in the visible light range. Such properties include the size, shape, and distribution of pores and grains, or more generally the texture, mineral distribution, and so on. A novel laboratory instrument and method allows for easy and reliable core imaging. This method is applicable even when the core sample is in poor shape. The capabilities of this technique can be verified by core images, image interpretation, and dynamic measurements of rock samples during flooding. A microscopic imager instrument is operated in video acquisition mode and can measure additional properties, such as fluid mobility, by detecting the emergence of injected fluids across the core sample.
10
Yosi, Klementin Fairyo. "GAMBAR CADAS PRASEJARAH DI TELUK WONDAMA SEBARAN DAN CERITA RAKYATNYA." Jurnal Penelitian Arkeologi Papua dan Papua Barat 12, no. 2 (January 21, 2021): 97–113. http://dx.doi.org/10.24832/papua.v12i2.233.
Full textAbstract:
ABSTRAKKeberadaan gambar cadas di Teluk Wondama ditulis oleh Galis tahun 1948. Balai Arkeologi Papua tahun 2016 di Pulau Roon. Hasilnya bersifat eksplorasi, belum terfokus pada tipologi gambar cadas. Tahun 2019 Balai Arkeologi Papua melakukan penelitian Tipologi gambar cadas prasejarah di kawasan Teluk Wondama. Selain mengkaji tipologi gambar cadas, juga mengungkap cerita rakyatnya. Tujuan penulisan adalah mengetahui tipologi gambar cadas, seperti apa sebarannya dan apa saja cerita rakyat terkait gambar cadas. Metode penelitian eksploratif dan deskriptif kualitatif. Tahapan penelitian adalah studi kepustakaan, penelitian lapangan, tahap pengolahan data. Dalam pengolahan data menggunakan juga software plugin Dstretch pada aplikasi imajiJ untuk memperjelas gambar. Hasil penelitian menemukan tujuh situs gambar cadas yaitu situs Suanggini, Ambesibui 1, Ambesibui 2, Ambesibui 3, Sanepa, situs Pulau Nuasa dan situs Inuri Kiari. Motif gambar berupa gambar manusia, kadal, ikan, penyu, lingkaran, penanda arah, segitiga, garis, dan gambar tidak teridentifikasi. Kata kunci : Penelitian, Situs, Gambar, Cadas, Pulau. ABSTRACTThe existence rock images in Wondama Bay was written by Galis in 1948. Papua Archaeological in 2016 on Roon Island. The results exploratory, not focused typology rock images. In 2019 Papua Archaeological conducted a typology study rock images prehistoric in Wondama Bay area. In addition to studying typology of rock images, also reveals folklore. The purpose writing is know typology rock images, what are their distribution and what are the folklore related to rock images. Explorative and descriptive qualitative research methods. The stages of research literature study, field research, data processing stage. In processing data also use dstretch plugin software on imageJ application to clarify image. The results found seven rock image sites, Suanggini site, Ambesibui 1, Ambesibui 2, Ambesibui 3, Sanepa, Nuasa Island site and Inuri Kiari site. Image motifs form images humans, lizards, fish, turtles, circles, direction markers, triangles, lines, and images are not identified. Keywords: Research, Site, Image, Cadas, Island.
11
Marathe, Ashutosh, Priya Jain, and Vibha Vyas. "Iterative improved learning algorithm for petrographic image classification accuracy enhancement." International Journal of Electrical and Computer Engineering (IJECE) 9, no. 1 (February 1, 2019): 289. http://dx.doi.org/10.11591/ijece.v9i1.pp289-296.
Full textAbstract:
<p>Rock image classification using image processing has been practiced to assist trained geologists in decision making. However, the study of microstructures of rocks and their use in geological investigations offer challenges in the areas of Image processing and Pattern Classification due to the stochastic nature of the mineral textures that is revealed at the microscopic level. Locally relevant Igneous Rock Microstructure images were classified from Volcanic and Plutonic Rock subtypes. The imaging method used mineral grain size as the key physical feature of classification. Three algorithms, namely Radial Basis Function (RBF) Support Vector Machine classifier; Improved (RBF) Support Vector Machine classifier; and AdaBoost algorithm with Improved RBF Support Vector Machine algorithm as base classifier, were used as a base classifier in a novel ‘Iterative Improved Learning (IIL)’ approach. Implementing the IIL approach in the chosen algorithm resulted in accurately classified images that were added to the training set to enhance the ‘breadth and depth’ of the learning knowledge. The algorithm iterated through all available classifier approaches and compared the inter-classifier performance and knowledge of the misclassified images accumulated during the execution of all algorithms.</p>
12
Zhang, Qiang, Jieying Gu, and Junming Liu. "Research on Coal and Rock Type Recognition Based on Mechanical Vision." Shock and Vibration 2021 (March 12, 2021): 1–10. http://dx.doi.org/10.1155/2021/6617717.
Full textAbstract:
In order to identify different kinds of coal, rock, and gangue, the FPV integrated image transmission camera is used to collect images of 6 types of coal, 8 types of rocks, and 2 types of coal gangue, and the images are processed based on the two-dimensional discrete wavelet transform (2D-DWT) based on the steerable pyramid decomposition (SPD). The maximum likelihood estimation method is used to estimate the parameters, and, the coal and rock types are judged by comparing the similarity of each image. The results show the following: (1) in the eight kinds of rocks, the recognition accuracy of shale and limestone is 90%, that of anorthosite is 95%, and those of other rocks are 100%; (2) the accuracy of comprehensive identification of coal, rock, and gangue is 93%, the comprehensive of coal and gangue is 78%, and the rock classification is 97%; (3) the identification time of 6 types of coal samples, 8 types of rock samples, and 2 types of coal gangue samples are in the range of 2 s∼3 s, which is far less than 10 s, which can meet the requirements of coal and rock identification in terms of recognition speed; and (4) according to 20 groups of data, the range, variance, and standard deviation of the same coal gangue sample meet the accuracy requirements of coal and rock identification. The identification method provides an effective method to improve the efficiency of coal separation, effectively determine the distribution of coal and rock, and timely adjust the cutting height of shearer drum and the operation parameters of various fully mechanized mining equipment, so as to improve the recovery rate of coal resources.
13
Sengupta, Mita, and Shannon L. Eichmann. "Computing elastic properties of organic-rich source rocks using digital images." Leading Edge 40, no. 9 (September 2021): 662–66. http://dx.doi.org/10.1190/tle40090662.1.
Full textAbstract:
Digital rocks are 3D image-based representations of pore-scale geometries that reside in virtual laboratories. High-resolution 3D images that capture microstructural details of the real rock are used to build a digital rock. The digital rock, which is a data-driven model, is used to simulate physical processes such as fluid flow, heat flow, electricity, and elastic deformation through basic laws of physics and numerical simulations. Unconventional reservoirs are chemically heterogeneous where the rock matrix is composed of inorganic minerals, and hydrocarbons are held in the pores of thermally matured organic matter, all of which vary spatially at the nanoscale. This nanoscale heterogeneity poses challenges in measuring the petrophysical properties of source rocks and interpreting the data with reference to the changing rock structure. Focused ion beam scanning electron microscopy is a powerful 3D imaging technique used to study source rock structure where significant micro- and nanoscale heterogeneity exists. Compared to conventional rocks, the imaging resolution required to image source rocks is much higher due to the nanoscale pores, while the field of view becomes smaller. Moreover, pore connectivity and resulting permeability are extremely low, making flow property computations much more challenging than in conventional rocks. Elastic properties of source rocks are significantly more anisotropic than those of conventional reservoirs. However, one advantage of unconventional rocks is that the soft organic matter can be captured at the same imaging resolution as the stiff inorganic matrix, making digital elasticity computations feasible. Physical measurement of kerogen elastic properties is difficult because of the tiny sample size. Digital rock physics provides a unique and powerful tool in the elastic characterization of kerogen.
14
Kuang, Hong Hai. "Pattern Recognition of Carbonate Rocks in Rs Image." Key Engineering Materials 500 (January 2012): 37–39. http://dx.doi.org/10.4028/www.scientific.net/kem.500.37.
Full textAbstract:
Pattern recognition of carbonate rocks in RS image have been studied in the paper. Samples of carbonate rocks were scanned into rock images.By analysing these samples of carbonate rocks,a new arithmetic was chosed and a standard curve of carbonate rocks by the arithmetic can be gotten.Rs images were divided into grids.There are curves by the arithmetic in grids. The standard curve of carbonate rocks and curves in grids were compared.If both of curves look very similar,the grid is carbonate rocks area.
15
Yao, Kouame, Biswajeet Pradhan, and Mohammed Oludare Idrees. "Identification of Rocks and Their Quartz Content in Gua Musang Goldfield Using Advanced Spaceborne Thermal Emission and Reflection Radiometer Imagery." Journal of Sensors 2017 (2017): 1–8. http://dx.doi.org/10.1155/2017/6794095.
Full textAbstract:
Quartz is an important mineral element and the most abundant rock-forming mineral that controls the mineralogy of a reservoir. At the surface, quartz is more stable than most other rock minerals because it is made up of interlocking silica that makes it quite resistant to mechanical weathering. Quartz abundance is an indication of mineralization in many metal deposits; therefore, identification and mapping of quartz in rocks are of great value for exploration and resource potential assessments. In this study, thermal infrared (TIR) bands of the Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) imagery were used to identify quartz contained rocks in Gua Musang. First, the image was corrected for atmospheric effect and the study area subset for further processing. Thereafter, spectral transformation (principal component analysis (PCA)) was implemented on the TIR bands and the resulting principal component (PC) images were analysed. The three optimal PCs were selected using the strength of spectral interaction and the eigenvalues of each band. To discriminate between quartz-rich and quartz-poor rocks, RGB false colour composite and greyscale image of one of the PCs were analysed. The result shows that volcanogenic igneous rock and carbonate sedimentary rocks of Permian formation are quartz-poor while Triassic sedimentary rock made up of organic particles and sandstone is quartz-rich. On the contrary, the quartz content in the metamorphic rock varies across the area but is richer in quartz content than the igneous and carbonate rocks. Classification of the composite image classified using maximum likelihood (ML) supervised classification method produced overall accuracy and Kappa coefficient of 96.53%, and 0.95, respectively.
16
Sidiq, Irsyad Nuruzzaman, and Thaqibul Fikri Niyartama. "Porosity Identification of Carbonate Core Reservoir Using Digital Rock Physics Method." Proceeding International Conference on Science and Engineering 1 (October 31, 2017): 175–81. http://dx.doi.org/10.14421/icse.v1.297.
Full textAbstract:
Indonesia is an archipelago country so rich with coral reefs that are a major component of the carbonate rock constituents. Where as much as 40% of carbonate rocks in Indonesia is a hydrocarbon reservoir is still rarely done exploration. This is because conventional hydrocarbon exploration technology has not been able to provide detailed information about the physical quantities. Hydrocarbon exploration technologies currently leads on digital technology to know the physical quantities of a reservoir of more detail such as porosity. Porosity which is physical quantities related to the presence of hydrocarbons in the pores of rocks. Digital Rock Physics (DRP) is a digital image-based method as an alternative method to find the physical quantities of rock samples to make it more effective and efficient. This study aims to identify the physical quantity using the method of porosity of the DRP until obtaining porosity of rock core carbonate reservoir by analyzing the binary image of the two rock cores from the same reservoir but has different dimensions to find out the exact core rocks to analyze the value of porosity. Binary image obtained from a scanned image of a projection of rock that has been reconstructed to become the greyscale image and have gone through the process of thresholding. The results of this study showed that the method can identify the physical quantities of DRP porosity and non-damaging rock pore structure (non-destructive). Analysis of the porosity of the rock core with histogram variations performed (by adjustingting the histogram), using the otsu method of thresholding and pixel size of the image has high (5.343750 μm) used to analyze the value of porosity. The porosity values acquired for 18.040 and has precision 96.20%.
17
Carpenter, Chris. "Machine-Learning Techniques Characterize Source-Rock Images at the Pore Scale." Journal of Petroleum Technology 74, no. 01 (January 1, 2022): 92–95. http://dx.doi.org/10.2118/0122-0092-jpt.
Full textAbstract:
This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 208632, “Reconstruction and Synthesis of Source-Rock Images at the Pore Scale,” by Timothy Anderson, SPE, Stanford University. The paper has not been peer reviewed. Nanoimaging techniques for characterizing pore-scale structure of shales trade off between high-resolution/high-contrast sample-destructive imaging modalities and low-contrast/low-resolution sample-preserving modalities. Acquisition of nanoscale images also is often time-consuming and expensive. In the complete paper, the author introduces methods for overcoming these challenges in image-based characterization of the fabric of shale source rocks using deep-learning models. Introduction A promising application of data-driven scale-translation techniques is nanoscale imaging. This application is important for studying shales because of the importance of nanoporosity in shale gas storage. Nanoimaging techniques, however, present specific challenges and can result in small image data sets that do not allow for accurate quantification of petrophysical or morphological properties. Consequently, data translation and generation both offer many opportunities to assimilate multiple nano- and microscale modalities and to overcome limitations of nanoimaging systems. The author proposes an image-based characterization work flow (Fig. 1) for data-driven scale translation that uses deep-learning image synthesis and translation models to assimilate multimodal, multiscale, and data-scarce source-rock images for predicting petrophysical and morphological properties. A central challenge in source-rock characterization addressed in this work is the reconstruction of 3D volumes when only 2D training images are available. Image-translation models are presented for reconstruction of 3D image volumes from 2D training data and a porous media image-synthesis algorithm that generalizes to 3D grayscale and multimodal volume generation from 2D training data. The complete paper describes the translation and synthesis models, applies these models to source-rock image data sets, and discusses extensions and future directions for the introduced work flow.
18
Zou, Yongning, Gongjie Yao, and Jue Wang. "Research on 3D crack segmentation of CT images of oil rock core." PLOS ONE 16, no. 10 (October 14, 2021): e0258463. http://dx.doi.org/10.1371/journal.pone.0258463.
Full textAbstract:
In this paper, we propose a framework for CT image segmentation of oil rock core. According to the characteristics of CT image of oil rock core, the existing level set segmentation algorithm is improved. Firstly, an algorithm of Chan-Vese (C-V) model is carried out to segment rock core from image background. Secondly the gray level of image background region is replaced by the average gray level of rock core, so that image background does not affect the binary segmentation. Next, median filtering processing is carried out. Finally, an algorithm of local binary fitting (LBF) model is executed to obtain the crack region. The proposed algorithm has been applied to oil rock core CT images with promising results.
19
Wang, Xiufang, Jingyuan Li, Ming Bai, and Yan Pei. "Quantitative Identification Cracks of Heritage Rock Based on Digital Image Technology." Journal of Physics: Conference Series 2148, no. 1 (January 1, 2022): 012048. http://dx.doi.org/10.1088/1742-6596/2148/1/012048.
Full textAbstract:
Abstract Digital image processing technologies are used to extract and evaluate the cracks of heritage rock in this paper. Firstly, the image needs to go through a series of image preprocessing operations such as graying, enhancement, filtering and binaryzation to filter out a large part of the noise. Then, in order to achieve the requirements of accurately extracting the crack area, the image is again divided into the crack area and morphological filtering. After evaluation, the obtained fracture area can provide data support for the restoration and protection of heritage rock. In this paper, the cracks of heritage rock are extracted in three different locations.The results show that the three groups of rock fractures have different effects on the rocks, but they all need to be repaired to maintain the appearance of the heritage rock.
20
Wei, Xin Shan, Chun Long Rong, Jun Xiang Nan, Guo Jian Cheng, and Ye Liu. "Rock Classification Based on Image Processing and Neural Networks." Applied Mechanics and Materials 568-570 (June 2014): 685–90. http://dx.doi.org/10.4028/www.scientific.net/amm.568-570.685.
Full textAbstract:
For the identification complexity of rock microstructure, based on numerical analysis of rock section images, an automatic rock texture classification method and identification system is proposed in this paper. Digital grey image processing of rock thin section is used for features extraction, the features are then as inputs to the neural network model, the model output is the rock microstructure classification. 100 pieces of rock section images from Sulige region in Changqing Oilfield are used for the experiment; the whole dataset is randomly divided into 70 images for training datasets, 15 images for validation datasets and 15 images for testing datasets. It is shown that the correct classification rate for automatic identification of rock microstructure is about 93.3%. Therefore, the proposed method for solving geological problem is effective and can get a good identification performance for rock microstructure classification quickly and accurately.
21
Miquel-González, Lisset, Gilbert Ortiz-Rabell, and Olga Castro-Castiñeira. "Tomography axial computerized technique application to improve Cuban oil fields seal and reservoir rocks characterization." Boletín de Ciencias de la Tierra, no. 41 (January 1, 2017): 73–80. http://dx.doi.org/10.15446/rbct.n41.55046.
Full textAbstract:
This investigation pretend to obtain improve on seal and reservoir rocks composition studies in oil fields, more certain in the formations characterization, and to prove the necessity of analytical nuclear techniques’ incorporation to petrophysical methods’ complex used in the Cuban oil prospection. This investigation used computer axial tomography method in consolidated cores’ rock and free software Image J as tomography interpretation support, resulting in novel improvement to the petrophysical laboratory. The following results were obtained: the computer axial tomography on cores’ rock were carried out; the resulted images were analyzed in quantitative and qualitative way, using Image J software, obtaining a good correlation with expert’s description of those cores’ rock. A methodology which permit to find average porosity and density values per pixel using tomography images were obtained, with the necessary corrections per lithology. This methodology is now in the initial phase of its development.
22
Anderson, Timothy I., Kelly M. Guan, Bolivia Vega, Saman A. Aryana, and Anthony R. Kovscek. "RockFlow: Fast Generation of Synthetic Source Rock Images Using Generative Flow Models." Energies 13, no. 24 (December 13, 2020): 6571. http://dx.doi.org/10.3390/en13246571.
Full textAbstract:
Image-based evaluation methods are a valuable tool for source rock characterization. The time and resources needed to obtain images has spurred development of machine-learning generative models to create synthetic images of pore structure and rock fabric from limited image data. While generative models have shown success, existing methods for generating 3D volumes from 2D training images are restricted to binary images and grayscale volume generation requires 3D training data. Shale characterization relies on 2D imaging techniques such as scanning electron microscopy (SEM), and grayscale values carry important information about porosity, kerogen content, and mineral composition of the shale. Here, we introduce RockFlow, a method based on generative flow models that creates grayscale volumes from 2D training data. We apply RockFlow to baseline binary micro-CT image volumes and compare performance to a previously proposed model. We also show the extension of our model to 2D grayscale data by generating grayscale image volumes from 2D SEM and dual modality nanoscale shale images. The results show that our method underestimates the porosity and surface area on the binary baseline datasets but is able to generate realistic grayscale image volumes for shales. With improved binary data preprocessing, we believe that our model is capable of generating synthetic porous media volumes for a very broad class of rocks from shale to carbonates to sandstone.
23
Malik, Owais A., Idrus Puasa, and Daphne Teck Ching Lai. "Segmentation for Multi-Rock Types on Digital Outcrop Photographs Using Deep Learning Techniques." Sensors 22, no. 21 (October 22, 2022): 8086. http://dx.doi.org/10.3390/s22218086.
Full textAbstract:
The basic identification and classification of sedimentary rocks into sandstone and mudstone are important in the study of sedimentology and they are executed by a sedimentologist. However, such manual activity involves countless hours of observation and data collection prior to any interpretation. When such activity is conducted in the field as part of an outcrop study, the sedimentologist is likely to be exposed to challenging conditions such as the weather and their accessibility to the outcrops. This study uses high-resolution photographs which are acquired from a sedimentological study to test an alternative basic multi-rock identification through machine learning. While existing studies have effectively applied deep learning techniques to classify the rock types in field rock images, their approaches only handle a single rock-type classification per image. One study applied deep learning techniques to classify multi-rock types in each image; however, the test was performed on artificially overlaid images of different rock types in a test sample and not of naturally occurring rock surfaces of multiple rock types. To the best of our knowledge, no study has applied semantic segmentation to solve the multi-rock classification problem using digital photographs of multiple rock types. This paper presents the application of two state-of-the-art segmentation models, namely U-Net and LinkNet, to identify multiple rock types in digital photographs by segmenting the sandstone, mudstone, and background classes in a self-collected dataset of 102 images from a field in Brunei Darussalam. Four pre-trained networks, including Resnet34, Inceptionv3, VGG16, and Efficientnetb7 were used as a backbone for both models, and the performances of the individual models and their ensembles were compared. We also investigated the impact of image enhancement and different color representations on the performances of these segmentation models. The experiment results of this study show that among the individual models, LinkNet with Efficientnetb7 as a backbone had the best performance with a mean over intersection (MIoU) value of 0.8135 for all of the classes. While the ensemble of U-Net models (with all four backbones) performed slightly better than the LinkNet with Efficientnetb7 did with an MIoU of 0.8201. When different color representations and image enhancements were explored, the best performance (MIoU = 0.8178) was noticed for the L*a*b* color representation with Efficientnetb7 using U-Net segmentation. For the individual classes of interest (sandstone and mudstone), U-Net with Efficientnetb7 was found to be the best model for the segmentation. Thus, this study presents the potential of semantic segmentation in automating the reservoir characterization process whereby we can extract the patches of interest from the rocks for much deeper study and modeling to be conducted.
24
Bénard, Antoine, Sabine Palle, Luc Serge Doucet, and Dmitri A. Ionov. "Three-Dimensional Imaging of Sulfides in Silicate Rocks at Submicron Resolution with Multiphoton Microscopy." Microscopy and Microanalysis 17, no. 6 (November 18, 2011): 937–43. http://dx.doi.org/10.1017/s1431927611011883.
Full textAbstract:
AbstractWe report the first application of multiphoton microscopy (MPM) to generate three-dimensional (3D) images of natural minerals (micron-sized sulfides) in thick (∼120 μm) rock sections. First, reflection mode (RM) using confocal laser scanning microscopy (CLSM), combined with differential interference contrast (DIC), was tested on polished sections. Second, two-photon fluorescence (TPF) and second harmonic signal (SHG) images were generated using a femtosecond-laser on the same rock section without impregnation by a fluorescent dye. CSLM results show that the silicate matrix is revealed with DIC and RM, while sulfides can be imaged in 3D at low resolution by RM. Sulfides yield strong autofluorescence from 392 to 715 nm with TPF, while SHG is only produced by the embedding medium. Simultaneous recording of TPF and SHG images enables efficient discrimination between different components of silicate rocks. Image stacks obtained with MPM enable complete reconstruction of the 3D structure of a rock slice and of sulfide morphology at submicron resolution, which has not been previously reported for 3D imaging of minerals. Our work suggests that MPM is a highly efficient tool for 3D studies of microstructures and morphologies of minerals in silicate rocks, which may find other applications in geosciences.
25
Gonçalves, Laercio B., and Fabiana R. Leta. "Macroscopic Rock Texture Image Classification Using a Hierarchical Neuro-Fuzzy Class Method." Mathematical Problems in Engineering 2010 (2010): 1–23. http://dx.doi.org/10.1155/2010/163635.
Full textAbstract:
We used a Hierarchical Neuro-Fuzzy Class Method based on binary space partitioning (NFHB-Class Method) for macroscopic rock texture classification. The relevance of this study is in helping Geologists in the diagnosis and planning of oil reservoir exploration. The proposed method is capable of generating its own decision structure, with automatic extraction of fuzzy rules. These rules are linguistically interpretable, thus explaining the obtained data structure. The presented image classification for macroscopic rocks is based on texture descriptors, such as spatial variation coefficient, Hurst coefficient, entropy, and cooccurrence matrix. Four rock classes have been evaluated by the NFHB-Class Method: gneiss (two subclasses), basalt (four subclasses), diabase (five subclasses), and rhyolite (five subclasses). These four rock classes are of great interest in the evaluation of oil boreholes, which is considered a complex task by geologists. We present a computer method to solve this problem. In order to evaluate system performance, we used 50 RGB images for each rock classes and subclasses, thus producing a total of 800 images. For all rock classes, the NFHB-Class Method achieved a percentage of correct hits over 73%. The proposed method converged for all tests presented in the case study.
26
Wadge, G., and N. Quarmby. "Geological remote sensing of rocky coasts." Geological Magazine 125, no. 5 (September 1988): 495–505. http://dx.doi.org/10.1017/s0016756800013236.
Full textAbstract:
AbstractFrom remotely sensed images of rock surfaces at coasts it is possible to map some characteristics of different rock types. To do this a selection must be made of those parts of the image that correspond to the rock surfaces prior to interrogation of their geological information content. A comparative study of satellite-acquired multispectral Thematic Mapper data and aircraft-acquired multispectral scanner data at four test sites on the Pembrokeshire coast was made. The spatial resolution of the Thematic Mapper data (30 m) proved to be too coarse to provide any continuity of mapping over several kilometres of rock exposures, whereas the 10 m resolution of the aircraft data was adequate to do this. Using the aircraft scanner data, neighbouring Old Red Sandstone and Carboniferous (mainly carbonate) rocks could be discriminated in both three-band and principal components images. Furthermore, it proved possible to distinguish between limestone and dolomite lithologies in the Carboniferous succession and between some of the mudstones and sandstones in the Old Red Sandstone. Airborne multispectral scanning of rocky coasts is a new potential tool for geological mapping in exploration projects in which it would be best integrated with the acquisition of airborne geophysical and field geological data.
27
Li, Diyuan, Junjie Zhao, and Jinyin Ma. "Experimental Studies on Rock Thin-Section Image Classification by Deep Learning-Based Approaches." Mathematics 10, no. 13 (July 2, 2022): 2317. http://dx.doi.org/10.3390/math10132317.
Full textAbstract:
Experimental studies were carried out to analyze the impact of optimizers and learning rate on the performance of deep learning-based algorithms for rock thin-section image classification. A total of 2634 rock thin-section images including three rock types—metamorphic, sedimentary, and volcanic rocks—were acquired from an online open-source science data bank. Four CNNs using three different optimizer algorithms (Adam, SGD, RMSprop) under two learning-rate decay schedules (lambda and cosine decay modes) were trained and validated. Then, a systematic comparison was conducted based on the performance of the trained model. Precision, f1-scores, and confusion matrix were adopted as the evaluation indicators. Trials revealed that deep learning-based approaches for rock thin-section image classification were highly effective and stable. Meanwhile, the experimental results showed that the cosine learning-rate decay mode was the better option for learning-rate adjustment during the training process. In addition, the performance of the four neural networks was confirmed and ranked as VGG16, GoogLeNet, MobileNetV2, and ShuffleNetV2. In the last step, the influence of optimization algorithms was evaluated based on VGG16 and GoogLeNet, and the results demonstrated that the capabilities of the model using Adam and RMSprop optimizers were more robust than that of SGD. The experimental study in this paper provides important practical value for training a high-precision rock thin-section image classification model, which can also be transferred to other similar image classification tasks.
28
Peng, Rui Dong, Yan Cong Yang, Peng Wang, and Yu Jun Zhang. "Developments in Detection of Rock Damage." Applied Mechanics and Materials 152-154 (January 2012): 1018–23. http://dx.doi.org/10.4028/www.scientific.net/amm.152-154.1018.
Full textAbstract:
How to quantificationally detect the damage of rocks is a key problem in damage mechanics for rocks, and it determined whether the damage theory of rocks could be brought into action in rock engineering. Detection techniques of rock damage were summarized and grouped into structural analysis approaches and feature measurement approaches, which include SEM analysis, CT detection, stress-strain measurement, wave detection, acoustic emission monitoring, infrared radiation detection, etc. Image processing and fractal theory were introduced to calculate damage variable directly based on images. All kinds of damage variables resulted from different methods are equipollent in thermodynamics, and they are an internal variable to characterize damage state. The difference of each kind of damage variable is that different formations of state equations and dynamic equations would be derived from different variables. It was suggested that the favorable rock damage variables should be selected according to the thermodynamics principle and those convenient to detect and easy to analysis should be adopted preferably.
29
Zhang, Yong Jun, Li Qian An, and Nian Jie Ma. "Study on Infrared Characteristics in the Progressive Failure of Bolted Rocks under Uniaxial Compression." Advanced Materials Research 332-334 (September 2011): 1227–31. http://dx.doi.org/10.4028/www.scientific.net/amr.332-334.1227.
Full textAbstract:
For the demands of thermal infrared (TIR) radiation change regularity for TIR radiation detection experiments of interaction between bolt and rock, TIR image information extracting and quantitative analysis of bolts action zones were carried out. The IR isothermal fringes of the bolted bocks were obtained through thermal infrared image subtraction of bolted bocks and data fitting. The interaction ranges between bolts and rock were obtained and the bolted ranges of lateral directions were determined. The quantitative treatment methods were applied to analyze infrared images of bolted roadway also. The common acting zones of several bolts in the surrounding rocks are determined. The theoretical guides have been provided for the bolt supporting parameters design of spacing interval and array pitch.
30
Mohamed, Mohamed Taha AlMakki, Latifa Shaheen Al-Naimi, Tochukwu Innocent Mgbeojedo, and Chidiebere Charles Agoha. "Geological mapping and mineral prospectivity using remote sensing and GIS in parts of Hamissana, Northeast Sudan." Journal of Petroleum Exploration and Production Technology 11, no. 3 (March 2021): 1123–38. http://dx.doi.org/10.1007/s13202-021-01115-3.
Full textAbstract:
AbstractIn recent years, various geological activities and different mineral prospecting and exploration programs have been intensified along the Red Sea hills in order to elucidate the geological maps and to evaluate the mineral potentials. This study is therefore aimed at testing the viability of using remote sensing and geographic information system (GIS) techniques for geological mapping and prospecting for gold mineralization in the area. The study area is located in northeast Sudan and covers an area of about 1379 km2. Different digital image processing techniques were applied to Landsat 8 Operational Land Imager image in order to increase the discrimination between various lithological units and to delineate wall rock alteration which represents target zones for gold mineralization. Image sharpening was performed to enhance the spatial resolution of the images for more detailed information. Contrast stretching was applied after the various digital processing procedures to produce more interpretable images. The principal component analysis transformations yielded saturated images and resulted in more interpretable images than the original data. Several ratio images were prepared, combined together and displayed in RGB color composite ratio images. This process revealed the existence of alteration zones in the study area. These zones extend from the northeast to the southwest in the acid meta-volcanic and silica barite rocks. The enhanced satellite images were implemented in the GIS environment to facilitate the final production of the geological map at scale 1:400,000. X-ray fluorescence analyses prove that selected samples taken from the wall rock alteration zones are gold-bearing.
31
Popescu, Sorin, and Ovidiu-Bogdan Tomuş. "Determination of the rock mass resistance index (GSI) based on image processing." MATEC Web of Conferences 342 (2021): 02012. http://dx.doi.org/10.1051/matecconf/202134202012.
Full textAbstract:
More and more often, and on an increasingly large scale, the geological resistance index (GSI) system is used for the design and practice of the mining process. The GSI, is a unique system for classifying the mass of rocks, linked to the parameters of rock strength and mass distortion, based on the generalized criteria of Hoek-Brown and MohrCoulomb. The GSI can be estimated using standard and in situ tables by direct surface observations in underground or surface mining. The GSI value provides a numerical representation of the overall Geotechnical quality of the rock mass. The method for determining GSI using photographic images of the in situ rock mass, with image processing technology, fractal theory and artificial neuronal network (ANN), is already known and successfully applied in several projects.
32
Callender, C. A., Wm C. Dawson, and J. J. Funk. "Correlation of Pore Structure and Permeability by SEM-Image Analysis." Proceedings, annual meeting, Electron Microscopy Society of America 48, no. 1 (August 12, 1990): 428–29. http://dx.doi.org/10.1017/s0424820100180896.
Full textAbstract:
The geometric structure of pore space in some carbonate rocks can be correlated with petrophysical measurements by quantitatively analyzing binaries generated from SEM images. Reservoirs with similar porosities can have markedly different permeabilities. Image analysis identifies which characteristics of a rock are responsible for the permeability differences. Imaging data can explain unusual fluid flow patterns which, in turn, can improve production simulation models.Analytical SchemeOur sample suite consists of 30 Middle East carbonates having porosities ranging from 21 to 28% and permeabilities from 92 to 2153 md. Engineering tests reveal the lack of a consistent (predictable) relationship between porosity and permeability (Fig. 1). Finely polished thin sections were studied petrographically to determine rock texture. The studied thin sections represent four petrographically distinct carbonate rock types ranging from compacted, poorly-sorted, dolomitized, intraclastic grainstones to well-sorted, foraminiferal,ooid, peloidal grainstones. The samples were analyzed for pore structure by a Tracor Northern 5500 IPP 5B/80 image analyzer and a 80386 microprocessor-based imaging system. Between 30 and 50 SEM-generated backscattered electron images (frames) were collected per thin section. Binaries were created from the gray level that represents the pore space. Calculated values were averaged and the data analyzed to determine which geological pore structure characteristics actually affect permeability.
33
Wei, Xin Shan, Xiao Hua Qin, Chun Long Rong, Jun Xiang Nan, and Guo Jian Cheng. "Image Classification Recognition for Rock Micro-Thin Section Based on Probabilistic Neural Networks." Applied Mechanics and Materials 602-605 (August 2014): 2147–52. http://dx.doi.org/10.4028/www.scientific.net/amm.602-605.2147.
Full textAbstract:
In order to implement the recognition automation of rock section pore images, a method combined K-means clustering with probabilistic neural network is proposed and applied to rock thin section images. Firstly, K-means clustering is used as segmentation algorithm, the rock images are divided into two types and extracted enough features and it is shown good classification recognition effect on testing dataset. Secondly, 100 pieces of rock image section are used as validation dataset, including 20 groups, each group has 5 images and 200 data samplings. Experiments show that the probabilistic neural network can be used as rock texture classifier, the average correct classification rate is around 95.12%, which can meet the practical application needs.
34
Handoyo, Handoyo, Fatkhan Fatkhan, Fourier D. E. Latief, and Harnanti Y. Putri. "Estimation of Rock Physical Parameters Based on Digital Rock Physics Image, Case Study: Blok Cepu Oil Field, Central Java, Indonesia." Jurnal Geofisika 16, no. 1 (March 22, 2018): 21. http://dx.doi.org/10.36435/jgf.v16i1.53.
Full textAbstract:
Modern technique to estimate of the physical properties of rocks can be done by means of digital imagingand numerical simulation, an approach known as digital rock physics (DRP: Digital Rock Physics). Digital rockphysics modeling is useful to understand microstructural parameters of rocks (pores and rock matrks), quite quickly and in detail. In this paper a study was conducted on sandstone reservoir samples in a rock formation. The core of sandstone samples were calculated porosity, permeability, and elasticity parameters in the laboratory. Then performed digital image processing using CT-Scan that utilizes X-ray tomography. The result of digital image is processed and done by calculation of digital simulation to calculate porosity, permeability, and elastic parameter of sandstones. In addition, there are also predictions of p-wave velocity and wave -S using the empirical equations given by Han (1986), Raymer (1990), and Nur (1998). The results of digital simulation (DRP) in this study provide a higher than the calculations in the laboratory. The digital rock physicsmethod (DRP) combined with rock physics modeling can be a practical and rapid method for determining the rock properties of tiny (microscopic) rock fragments
35
Tan, Yunliang, Dongmei Huang, and Ze Zhang. "Rock Mechanical Property Influenced by Inhomogeneity." Advances in Materials Science and Engineering 2012 (2012): 1–9. http://dx.doi.org/10.1155/2012/418729.
Full textAbstract:
In order to identify the microstructure inhomogeneity influence on rock mechanical property, SEM scanning test and fractal dimension estimation were adopted. The investigations showed that the self-similarity of rock microstructure markedly changes with the scanned microscale. Different rocks behave in different fractal dimension variation patterns with the scanned magnification, so it is conditional to adopt fractal dimension to describe rock material. Grey diabase and black diabase have high suitability; red sandstone has low suitability. The suitability of fractal-dimension-describing method for rocks depends on both investigating scale and rock type. The homogeneities of grey diabase, black diabase, grey sandstone, and red sandstone are 7.8, 5.7, 4.4, and 3.4, separately; their average fractal dimensions of microstructure are 2.06, 2.03, 1.72, and 1.40 correspondingly, so the homogeneity is well consistent with fractal dimension. For rock material, the stronger brittleness is, the less profile fractal dimension is. In a sense, brittleness is an image of rock inhomogeneity in macroscale, while profile fractal dimension is an image of rock inhomogeneity in microscale. To combine the test of brittleness with the estimation of fractal dimension with condition will be an effective approach for understanding rock failure mechanism, patterns, and behaviours.
36
Junning, Xie, Liu Bolong, and Zeng Nianchang. "Study on the breaking process of jointed rock mass by disc cutters based on digital image correlation and infrared thermography." E3S Web of Conferences 233 (2021): 03006. http://dx.doi.org/10.1051/e3sconf/202123303006.
Full textAbstract:
Jointed rock masses are frequently encountered during the TBM excavation. To investigate the rock breakage mechanism of jointed rock mass by disc cutter and precursory information before rock failure, a series of indentation tests were performed on shear rheological test system. During the test, breaking process of specimens were recorded by digital image correlation system and thermal infrared imager simultaneously. Therefore, the strain fields and thermal infrared images of jointed rock mass by disc cutters were obtain. The experimental results show that the failure process of jointed rock mass can be divided into four stages: compaction stage, linear elastic stage, residual failure transition stage and post-failure stage. Besides, the characteristic of strain fields shows a good accordance with that of infrared radiation temperature fields at each stage. The failure of rock samples is dominated by shear failure, and the localized temperature rise is an important infrared precursor of rock fracture and instability. The experimental results are of great significance to the deep understanding of the breaking mechanism of jointed rock mass and warnings of engineering disasters.
37
Cai, Weibo, Juncan Deng, Qirong Lu, Kengdong Lu, and Kaiqing Luo. "Automated Classification of High-resolution Rock Image Based on Residual Neural Network." Journal of Physics: Conference Series 2095, no. 1 (November 1, 2021): 012051. http://dx.doi.org/10.1088/1742-6596/2095/1/012051.
Full textAbstract:
Abstract The identification and classification of high-resolution rock images are significant for oil and gas exploration. In recent years, deep learning has been applied in various fields and achieved satisfactory results. This paper presents a rock classification method based on deep learning. Firstly, the high-resolution rock images are randomly divided into several small images as a training set. According to the characteristics of the datasets, the ResNet (Residual Neural Network) is optimized and trained. The local images obtained by random segmentation are predicted by using the model obtained by training. Finally, all probability values corresponding to each category of the local image are combined for statistics and voting. The maximum probability value and the corresponding category are taken as the final classification result of the classified image. Experimental results show that the classification accuracy of this method is 99.6%, which proves the algorithm’s effectiveness in high-resolution rock images classification.
38
Wang, Wei, Jing Hong Liu, and Pan Fei Shi. "Analyses on CT Image of Gray Rock Uniaxial Compressive Failure Process Based on MATLAB." Applied Mechanics and Materials 577 (July 2014): 1083–86. http://dx.doi.org/10.4028/www.scientific.net/amm.577.1083.
Full textAbstract:
The uniaxial compressive failure process CT images of gray rock were analysised based on Matlab. Matlab is used to transfer gray rock CT images into gray histogram which can be observed directly so as to see clearly the damage evolution process of gray rock under loading. By comparison, gray histogram is consistent with the result presented by original CT image. The gray histogram equalized by Matlab can show clearly the change trend and process of gray rock internal defects and micro cracks. Gray histogram is a good method to observe and analyses CT images.
39
Liu, Jinzi, Wenying Du, Chong Zhou, and Zhiqing Qin. "Rock Image Intelligent Classification and Recognition Based on Resnet-50 Model." Journal of Physics: Conference Series 2076, no. 1 (November 1, 2021): 012011. http://dx.doi.org/10.1088/1742-6596/2076/1/012011.
Full textAbstract:
Abstract Machine learning algorithms becomes popular for intelligent classification of rock images. In this paper, it selects Resnet 50 neural network model to divide the data sets based on the rock pictures taken under the white light lamp. By continuously adjusting the parameters of each layer, the intelligent classification of rocks is carries out. The training final validates accuracy reached 94.12%.
40
Botero García, Manuela, Sara Paulina Marín López, and Javier Vinasco Vallejo. "Shape Preferred Orientation (SPO) methodology for oriented hand specimens of rock and outcrops through digital image processing." Boletín de Ciencias de la Tierra, no. 38 (July 1, 2015): 5–13. http://dx.doi.org/10.15446/rbct.n38.44724.
Full textAbstract:
The shape-preferred orientation (SPO) is a technique, which allows the study of the fabric of deformed rocks and understanding its dominant deformational style and partitioning. This work presents SPO results and methodological aspects for one hand specimen of rock and a high-resolution composed image of an outcrop through digital image processing. The technique involves imaging of three semi-orthogonal oriented sections for digital processing and subsequent implementation in structural software. The image processing consists of digital separation of a phase of interest, i.e. defining the deformational fabric. The processed images are then implemented in the SPO2003® software for acquisition of sectional ellipses and finally implemented in the Ellipsoid2003® software to obtain the characteristic ellipsoid of deformational fabric. For outcrops, due to the difficulty to finding three appropriate sections for photography, it was only obtained a sectional ellipse, characteristic of the rock fabric based on contrasting deformed quartz segregates in mylonitic schists.
41
Liu, Xin, Zhengzhao Liang, Siwei Meng, Chunan Tang, and Jiaping Tao. "Numerical Simulation Study of Brittle Rock Materials from Micro to Macro Scales Using Digital Image Processing and Parallel Computing." Applied Sciences 12, no. 8 (April 11, 2022): 3864. http://dx.doi.org/10.3390/app12083864.
Full textAbstract:
The multi-scale, high-resolution and accurate structural modeling of rocks is a powerful means to reveal the complex failure mechanisms of rocks and evaluate rock engineering safety. Due to the non-uniformity and opacity of rocks, describing their internal microstructure, mesostructure and macro joints accurately, and how to model their progressive fracture process, is a significant challenge. This paper aims to build a numerical method that can take into account real spatial structures of rocks and be applied to the study of crack propagation and failure in different scales of rocks. By combining the failure process analysis (RFPA) simulator with digital image processing technology, large-scale finite element models of multi-scale rocks, considering microstructure, mesostructure, and macro joints, were created to study mechanical and fracture behaviors on a cloud computing platform. The Windows-Linux interactive method was used for digital image processing and parallel computing. The simulation results show that the combination of a parallel RFPA solver and digital image modeling technology can achieve high-resolution structural modeling and high-efficiency calculation. In microscopic simulations, the influence of shale fractures and mineral spatial distribution on the fracture formation process can be revealed. In the mesostructure simulation, it can be seen that the spatial distribution of minerals has an impact on the splitting mode of the Brazilian splitting model. In the simulation of a joined rock mass, the progressive failure process can be effectively simulated. According to the results, it seems that the finite element parallel computing simulation method based on digital images can simulate the multi-scale failure process of brittle materials from micro to macro scales. Primarily, efficient parallel computing based on a cloud platform allows for the multi-scale, high-resolution and realistic modeling and analysis of rock materials.
42
Li, Ang, Guo-jian Shao, Tian-tang Yu, Jing-bo Su, and Sheng-yong Ding. "Mesoscopic Numerical Simulation of Stratified Rock Failure Using Digital Image Processing." Advances in Mechanical Engineering 6 (January 1, 2014): 106073. http://dx.doi.org/10.1155/2014/106073.
Full textAbstract:
This paper presents a digital image processing (DIP) based finite difference method (FDM) and makes the first attempt to apply the new method to the failure process of stratified rocks from Chinese Jinping underground carves. In the method, the two-dimensional (2D) inhomogeneity and mesostructures of rock materials are first identified with the DIP technique. And then the binarization image information is used to generate the finite difference grids. Finally, the failure process of stratified rock samples under uniaxial compression condition is simulated by using the FDM. In the DIP, an image segmentation algorithm based on seeded region growing (SRG) is proposed, instead of the traditional threshold value method. And with the new method, we can fully acquire the inhomogeneous distributions and mesostructures of stratified rocks. The simulated macroscopic mechanical behaviors are in good agreement with the laboratory experimental observation. Numerical results show that the proposed DIP based FDM is suitable for the failure analysis of stratified rocks because it can fully take into account the material heterogeneity, and the anisotropy of stratified rocks is also disposed to some extent.
43
Qin, Qiu Ju, Xin Jian Qiang, Ye Liu, and Jing Yang. "Rock Image Pore Identification Based on Fuzzy C-Means Clustering and Neural Networks." Applied Mechanics and Materials 571-572 (June 2014): 803–6. http://dx.doi.org/10.4028/www.scientific.net/amm.571-572.803.
Full textAbstract:
In order to realize the recognition automation of rock section pore images, a method combined Fuzzy C-Means clustering with BP neural network is proposed to recognize the pore of rock images. Firstly, Fuzzy C-Means clustering as segmentation algorithm are applied to the rock images and they are divided into two types, then using the BP neural network training and classification recognition. It is shown that the trained BP neural network can accurately identify the effective porosity in the casting image, and lay a good foundation for practical applications.
44
Hébert, Vanessa, Thierry Porcher, Valentin Planes, Marie Léger, Anna Alperovich, Bastian Goldluecke, Olivier Rodriguez, and Souhail Youssef. "Digital core repository coupled with machine learning as a tool to classify and assess petrophysical rock properties." E3S Web of Conferences 146 (2020): 01003. http://dx.doi.org/10.1051/e3sconf/202014601003.
Full textAbstract:
To make efficient use of image-based rock physics workflow, it is necessary to optimize different criteria, among which: quantity, representativeness, size and resolution. Advances in artificial intelligence give insights of databases potential. Deep learning methods not only enable to classify rock images, but could also help to estimate their petrophysical properties. In this study we prepare a set of thousands high-resolution 3D images captured in a set of four reservoir rock samples as a base for learning and training. The Voxilon software computes numerical petrophysical analysis. We identify different descriptors directly from 3D images used as inputs. We use convolutional neural network modelling with supervised training using TensorFlow framework. Using approximately fifteen thousand 2D images to drive the classification network, the test on thousand unseen images shows any error of rock type misclassification. The porosity trend provides good fit between digital benchmark datasets and machine learning tests. In a few minutes, database screening classifies carbonates and sandstones images and associates the porosity values and distribution. This work aims at conveying the potential of deep learning method in reservoir characterization to petroleum research, to illustrate how a smart image-based rock physics database at industrial scale can swiftly give access to rock properties.
45
Dormishi, Alireza, Mohammad Ataei, Reza Mikaeil, and Reza Khalo Kakaei. "Relations between Texture Coefficient and Energy Consumption of Gang Saws in Carbonate Rock Cutting Process." Civil Engineering Journal 4, no. 2 (March 6, 2018): 413. http://dx.doi.org/10.28991/cej-0309101.
Full textAbstract:
Texture coefficient is one of the most influential parameters in rock engineering specifications in various projects including drilling, cutting, permeability of all-section drilling devices, etc. Meanwhile, investigating and forecasting the energy consumption of saw cutters are one of the most important factors in estimating the cutting costs. The present study aims to investigate the relationship between rock texture characteristics and the amount of energy consumption of the gang saw machine in the process of cutting carbonate rocks. To evaluate the effects of texture on the rocks' engineering specifications, 14 carbonate rock samples were studied. A microscopic thin section was made from each rock specimen. Then, five digital images were taken from each section under a microscope and the values of area, environment, the largest diameter and the smallest diameter of all grains in each image were determined. Using these specifications, the coefficient of texture of all rock samples was calculated and the relationship between the texture coefficient and the rate of energy consumption of the gang saw machine was investigated for the studied samples. The study results indicated that there was a significant relation between the texture coefficient and energy consumption rate in the three groups of carbonate rocks.
46
Shan, Pengfei, Chengwei Yan, Xingping Lai, Haoqiang Sun, Chao Li, and Xingzhou Chen. "Evaluation of Real-Time Perception of Deformation State of Host Rocks in Coal Mine Roadways in Dusty Environment." Sustainability 15, no. 3 (February 3, 2023): 2816. http://dx.doi.org/10.3390/su15032816.
Full textAbstract:
Intelligent mining needs to achieve real-time acquisition of surrounding rock deformation data of roadways and analysis and provide technical support for intelligent mining construction. To solve problems such as significant error, information lag, and low acquisition frequency of surrounding rock monitoring technology at the current stage, a perception method, RSBV of roadway deformation situation, based on binocular vision is proposed, which realizes the dynamic, accurate real-time acquisition of host rocks’ relative deformation in a dusky environment. The low illumination image enhancement method is used to preprocess original images, which reduces the impact of low illumination and high dust; the K-medoids algorithm segments the target image, and the SIFT algorithm extracts feature points from the ROI (region of interest). The influence of eliminating background images on the feature point extraction is revealed, and the efficiency of feature extraction is improved; the method of SIFT feature-matching with epipolar constraints is studied, which improves the accuracy and speed of feature points. The roadway deformation characteristics are analyzed, and the reflective target is used as the monitoring point. A roadway deformation acquisition and analysis platform based on binocular vision is built in a dim environment. Zhang’s method is selected to calibrate the camera parameters, and stereo rectification is carried out for the target motion image. The adaptability of the RSBV method to different surrounding rock deformation scales is studied and compared with the measurement results of the SGBM algorithm. The results show that the error of the RSBV method is controlled within 1.6%, which is 2.88% lower than the average error of the SGBM algorithm. The average time for processing a group of binocular images is 1.87 s, which is only 20% of the SGBM algorithm. The research result provides a reliable theoretical basis for the real-time and accurate evaluation of the surrounding rock deformation mechanism.
47
Dementieva, Alisa V. "RAVEN IMAGE IN ROCK POETRY AND THE INFLUENCE OF THE POEM “THE RAVEN” BY E.A. POE." Practices & Interpretations: A Journal of Philology, Teaching and Cultural Studies 7, no. 4 (December 22, 2022): 140–60. http://dx.doi.org/10.18522/2415-8852-2022-4-140-160.
Full textAbstract:
The article analyzes the image of raven in rock poetry of the XX–XXI centuries in selected song lyrics. The author gives a brief review of the research works that studied the image of raven in poetry, including song texts. The article presents the samples of songs of both Russian and foreign rock bands. The features of raven images created by them are described. The article provides examples of raven images dating back to mythological and folklore sources. Special attention is paid to rock texts referring directly to fragments and imagery of “The Raven” by E.A. Poe. The degree and particulars of borrowings from the E.A. Poe’s poem are specified. The author determines the variety of raven interpretations by different authors, as well as semantic and expressive similarities and differences of this image in the studied works.
48
Huang, Zhihao, Lumei Su, Jiajun Wu, and Yuhan Chen. "Rock Image Classification Based on EfficientNet and Triplet Attention Mechanism." Applied Sciences 13, no. 5 (March 1, 2023): 3180. http://dx.doi.org/10.3390/app13053180.
Full textAbstract:
Rock image classification is a fundamental and crucial task in the creation of geological surveys. Traditional rock image classification methods mainly rely on manual operation, resulting in high costs and unstable accuracy. While existing methods based on deep learning models have overcome the limitations of traditional methods and achieved intelligent image classification, they still suffer from low accuracy due to suboptimal network structures. In this study, a rock image classification model based on EfficientNet and a triplet attention mechanism is proposed to achieve accurate end-to-end classification. The model was built on EfficientNet, which boasts an efficient network structure thanks to NAS technology and a compound model scaling method, thus achieving high accuracy for rock image classification. Additionally, the triplet attention mechanism was introduced to address the shortcoming of EfficientNet in feature expression and enable the model to fully capture the channel and spatial attention information of rock images, further improving accuracy. During network training, transfer learning was employed by loading pre-trained model parameters into the classification model, which accelerated convergence and reduced training time. The results show that the classification model with transfer learning achieved 92.6% accuracy in the training set and 93.2% Top-1 accuracy in the test set, outperforming other mainstream models and demonstrating strong robustness and generalization ability.
49
Yang, Hai Qing, and Xiao Ping Zhou. "Experimental Investigation on the Damage Localization of Limestone under Triaxial Compression Condition." Advanced Materials Research 168-170 (December 2010): 1524–30. http://dx.doi.org/10.4028/www.scientific.net/amr.168-170.1524.
Full textAbstract:
The phenomena of Damage localization, which characterized as the rock mass suddenly enter into the deformation localization stage after a period of uniform deformation, is the beginning of rock failure. Damage localization is also the precursor of rock failure. Utilizing the image enhancement and segmentation technology, the rule of damage evolution of limestone under triaxial compression is analyzed. Moreover, The computerized tomography images are analyzed by the method of digital image processing, which includes threshold partition and edge detection, and then the relationship between computerized tomography image and damage evolution is discussed. Meanwhile, the dependence of fractal dimensions of rock section on the axial stress is determined by the method of box-counting dimension. It is concluded that the fractal dimension may reach a minimum value at the point of damage localization, and after that damage become more severe.
50
Tian, Xiao, and Hugh Daigle. "Machine-learning-based object detection in images for reservoir characterization: A case study of fracture detection in shales." Leading Edge 37, no. 6 (June 2018): 435–42. http://dx.doi.org/10.1190/tle37060435.1.
Full textAbstract:
Imaging tools are widely used in the petroleum industry to investigate structural features of reservoir rocks directly at multiple scales. Quantitative image analysis is often used to determine various rock properties, but it requires significant time and effort, particularly to analyze a large number of samples. Automated object detection represents a potential solution to this efficiency problem. This method uses computers to efficiently provide quantitative information for thousands of images. Automated fracture detection in scanning electron microscope (SEM) images is presented as an example to show the workflow of using advanced deep-learning tools for quantitative rock characterization. First, an automatic object-detection method is presented for fast identification and characterization of microfractures in shales. Using this approach, we analyzed 100 SEM images obtained from deformed and intact samples of a carbonate-rich shale and a siliceous shale with the goal of analyzing the abundance and characteristics of microfractures generated during hydraulic fracturing. Most of the fractures are detected with about 90% success rate relative to manual picking. Second, we obtained statistics of length and areal porosities of these fractures. The experimentally deformed samples had slightly more detectable microfractures (1.8 fractures/image on average compared to 1.6 fractures/image), and the microfractures induced by shear deformation tend to be short (<50 μm) in the Eagle Ford and long in the siliceous samples, presumably because of differences in rock fabric. In future work, this approach will be applied to characterize the shape and size of mineral grains and to analyze relationships between fractures and minerals.