Machine Learning Guided 3D Image Recognition for Carbonate Pore and Mineral Volumes Determination

Automated image processing algorithms can improve the quality, efficiency, and consistency of classifying the morphology of heterogeneous carbonate rock and can deal with a massive amount of data and images seamlessly. Geoscientists and petroleum engineers face difficulties in setting the direction of the optimum method for determining petrophysical properties from core plug images of optical thin-sections, Micro-Computed Tomography (μCT), or Magnetic Resonance Imaging (MRI). Most of the successful work is from the homogeneous and clastic rocks focusing on 2D images with less focus on 3D and requiring numerical simulation. Currently, image analysis methods converge to three approaches: image processing, artificial intelligence, and combined image processing with artificial intelligence. In this work, we propose two methods to determine the porosity from 3D μCT and MRI images: an image processing method with Image Resolution Optimized Gaussian Algorithm (IROGA); advanced image recognition method enabled by Machine Learning Difference of Gaussian Random Forest (MLDGRF).Meanwhile, we have built reference 3D micro models and collected images for calibration of the IROGA and MLDGRF methods. To evaluate the predictive capability of these calibrated approaches, we ran them on 3D μCT and MRI images of natural heterogeneous carbonate rock. We also measured the porosity and lithology of the carbonate rock using three and two industry-standard ways, respectively, as reference values. Notably, IROGA and MLDGRF have produced porosity results with an accuracy of 96.2% and 97.1% on the training set and 91.7% and 94.4% on blind test validation, respectively, in comparison with the three experimental measurements. We measured limestone and pyrite reference values using two methods, X-ray powder diffraction, and grain density measurements. MLDGRF has produced lithology (limestone and pyrite) volume fractions with an accuracy of 97.7% in comparison to reference measurements.

[1]  Dirk Mallants,et al.  Universal Stochastic Multiscale Image Fusion: An Example Application for Shale Rock , 2015, Scientific Reports.

[2]  John C. Russ,et al.  The Image Processing Handbook , 2015 .

[3]  J. Fujimoto,et al.  Ultrahigh-resolution ophthalmic optical coherence tomography , 2001, Nature Medicine.

[4]  Christopher. Simons,et al.  Machine learning with Python , 2017 .

[5]  Michael D. Abràmoff,et al.  Image processing with ImageJ , 2004 .

[6]  Christoph H. Arns,et al.  Archie's exponents in complex lithologies derived from 3D digital core analysis , 2007 .

[7]  Christoph H. Arns,et al.  Digital Core Laboratory: Properties of reservoir core derived from 3D images , 2004 .

[8]  Johannes E. Schindelin,et al.  Fiji: an open-source platform for biological-image analysis , 2012, Nature Methods.

[9]  J. Affeldt,et al.  The feasibility study , 2019, The Information System Consultant’s Handbook.

[10]  Tony J Collins,et al.  ImageJ for microscopy. , 2007, BioTechniques.

[11]  Hao Xu,et al.  A precise measurement method for shale porosity with low-field nuclear magnetic resonance: A case study of the Carboniferous-Permian strata in the Linxing area, eastern Ordos Basin, China , 2015 .

[12]  Bingyu Ji,et al.  Measurement and Visualization of Tight Rock Exposed to CO2 Using NMR Relaxometry and MRI , 2017, Scientific Reports.

[13]  Huiqi Li,et al.  Automated feature extraction in color retinal images by a model based approach , 2004, IEEE Transactions on Biomedical Engineering.

[14]  John Thurmond,et al.  Hyperspectral image analysis of different carbonate lithologies (limestone, karst and hydrothermal dolomites): the Pozalagua Quarry case study (Cantabria, North‐west Spain) , 2012 .

[15]  Ang Li,et al.  Quantitative microporosity evaluation using mercury injection and digital image analysis in tight carbonate rocks: A case study from the Ordovician in the Tazhong Palaeouplift, Tarim Basin, NW China , 2016 .

[16]  Jean-Michel Morel,et al.  A non-local algorithm for image denoising , 2005, 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05).

[17]  Jiaming Zhang,et al.  Analogue signal and image processing with large memristor crossbars , 2017, Nature Electronics.

[18]  G. Padmaja,et al.  An Automatic Diagnostic System for CT Brain Image Classification , 2012 .

[19]  R. Leahy,et al.  Magnetic Resonance Image Tissue Classification Using a Partial Volume Model , 2001, NeuroImage.

[20]  Andrew Zisserman,et al.  Very Deep Convolutional Networks for Large-Scale Image Recognition , 2014, ICLR.

[21]  Jian Sun,et al.  Deep Residual Learning for Image Recognition , 2015, 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[22]  S. Chough,et al.  Technical Note— Bulk Density, Void Ratio, and Porosity Determined From Average Grain Density and Water Content: An Evaluation of Errors , 1987 .

[23]  Jean-Pierre Leduc,et al.  Electrofacies and permeability modeling in carbonate reservoirs using image texture analysis and clustering tools , 2004 .

[24]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[25]  Yiqiang Li,et al.  Pore-scale investigation of residual oil displacement in surfactant–polymer flooding using nuclear magnetic resonance experiments , 2016, Petroleum Science.

[26]  Thomas S. Huang,et al.  Image Super-Resolution Via Sparse Representation , 2010, IEEE Transactions on Image Processing.

[27]  Guangjie Han,et al.  RAQ–A Random Forest Approach for Predicting Air Quality in Urban Sensing Systems , 2016, Sensors.

[28]  Gary Mavko,et al.  Estimating elastic moduli of rocks from thin sections: Digital rock study of 3D properties from 2D images , 2016, Comput. Geosci..

[29]  Tony Lindeberg,et al.  Image Matching Using Generalized Scale-Space Interest Points , 2013, Journal of Mathematical Imaging and Vision.

[30]  Anne-Laure Boulesteix,et al.  Overview of random forest methodology and practical guidance with emphasis on computational biology and bioinformatics , 2012, WIREs Data Mining Knowl. Discov..

[31]  David A. Budd,et al.  Quantification of Porosity and Permeability Reduction Due to Calcite Cementation Using Computer-Assisted Petrographic Image Analysis Techniques , 1996 .

[32]  Yan Zhang,et al.  Visualization and Post-processing of 5D Brain Images , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[33]  Peyman Mostaghimi,et al.  Deep Learning Convolutional Neural Networks to Predict Porous Media Properties , 2018, Day 1 Tue, October 23, 2018.

[34]  E-Liang Chen,et al.  An automatic diagnostic system for CT liver image classification , 1998, IEEE Transactions on Biomedical Engineering.

[35]  Christoph Rau,et al.  Dynamics of snap-off and pore-filling events during two-phase fluid flow in permeable media , 2017, Scientific Reports.

[36]  R. Ehrlich,et al.  Petrographic Image Analysis, I. Analysis of Reservoir Pore Complexes , 1984 .

[37]  Yuan Yu,et al.  TensorFlow: A system for large-scale machine learning , 2016, OSDI.

[38]  Guy Cazuguel,et al.  TeleOphta: Machine learning and image processing methods for teleophthalmology , 2013 .

[39]  Gaël Varoquaux,et al.  Scikit-learn: Machine Learning in Python , 2011, J. Mach. Learn. Res..

[40]  Martin P. DeSimio,et al.  Computer-aided breast cancer detection and diagnosis of masses using difference of Gaussians and derivative-based feature saliency , 1997, IEEE Transactions on Medical Imaging.

[41]  Bin Zheng,et al.  Computer-aided classification of mammographic masses using visually sensitive image features. , 2017, Journal of X-ray science and technology.

[42]  Roberto Hornero,et al.  A novel automatic image processing algorithm for detection of hard exudates based on retinal image analysis. , 2008, Medical engineering & physics.

[43]  Jan-P. Calliess,et al.  On the computational benefit of tensor separation for high-dimensional discrete convolutions , 2012, Multidimens. Syst. Signal Process..

[44]  Omar Al-Farisi,et al.  Revelation of Carbonate Rock Typing—The Resolved Gap , 2009 .

[45]  N. Hurley,et al.  Pore-Size Distributions in Vuggy Carbonates From Core Images, NMR, and Capillary Pressure , 1999 .

[46]  Travis E. Oliphant,et al.  Python for Scientific Computing , 2007, Computing in Science & Engineering.

[47]  Charles R. Thomas,et al.  Artificial Intelligence in Oncology: Current Applications and Future Directions. , 2019, Oncology.

[48]  Ramón Díaz-Uriarte,et al.  Gene selection and classification of microarray data using random forest , 2006, BMC Bioinformatics.

[49]  W. B. Lindquist,et al.  Medial axis analysis of void structure in three-dimensional tomographic images of porous media , 1996 .

[50]  Jonathan W. Peirce,et al.  PsychoPy—Psychophysics software in Python , 2007, Journal of Neuroscience Methods.

[51]  Zakariya Yahya Algamal,et al.  Gene selection and classification of microarray gene expression data based on a new adaptive L1-norm elastic net penalty , 2021 .

[52]  Alice J. O'Toole,et al.  Comparison of human and computer performance across face recognition experiments , 2014, Image and Vision Computing.

[53]  M F Sanner,et al.  Python: a programming language for software integration and development. , 1999, Journal of molecular graphics & modelling.

[54]  G LoweDavid,et al.  Distinctive Image Features from Scale-Invariant Keypoints , 2004 .

[55]  A. C. Spowage,et al.  Image segmentation and analysis for porosity measurement , 2007 .

[56]  Daniel F Polan,et al.  Tissue segmentation of computed tomography images using a Random Forest algorithm: a feasibility study , 2016, Physics in medicine and biology.

[57]  Alan C. Bovik,et al.  The Essential Guide to Image Processing , 2009, J. Electronic Imaging.

[58]  Mark Bates,et al.  Three-Dimensional Super-Resolution Imaging by Stochastic Optical Reconstruction Microscopy , 2008, Science.

[59]  Ullrich Köthe,et al.  Ilastik: Interactive learning and segmentation toolkit , 2011, 2011 IEEE International Symposium on Biomedical Imaging: From Nano to Macro.

[60]  D. L. Luffel,et al.  New Core Analysis Methods for Measuring Reservoir Rock Properties of Devonian Shale , 1992 .

[61]  G. Collewet,et al.  Influence of MRI acquisition protocols and image intensity normalization methods on texture classification. , 2004, Magnetic resonance imaging.

[62]  Gary Mavko,et al.  Estimating permeability from thin sections without reconstruction: Digital rock study of 3D properties from 2D images , 2017, Comput. Geosci..

[63]  Rafael C. González,et al.  Digital image processing, 3rd Edition , 2008 .

[64]  Martin J Blunt,et al.  Pore-network extraction from micro-computerized-tomography images. , 2009, Physical review. E, Statistical, nonlinear, and soft matter physics.

[65]  Rachid Deriche,et al.  Using Canny's criteria to derive a recursively implemented optimal edge detector , 1987, International Journal of Computer Vision.

[66]  Richard A. Ketcham,et al.  Nondestructive high-resolution visualization and measurement of anisotropic effective porosity in complex lithologies using high-resolution X-ray computed tomography , 2005 .

[67]  W. B. Lindquist,et al.  Investigating 3D geometry of porous media from high resolution images , 1999 .

[68]  Andreas Müller,et al.  Introduction to Machine Learning with Python: A Guide for Data Scientists , 2016 .

[69]  Tamara G. Kolda,et al.  Tensor Decompositions for Analyzing Multi-link Graphs. , 2008 .

[70]  Carl E. Rasmussen,et al.  Gaussian processes for machine learning , 2005, Adaptive computation and machine learning.

[71]  H. Sebastian Seung,et al.  Trainable Weka Segmentation: a machine learning tool for microscopy pixel classification , 2017, Bioinform..

[72]  Iron Cove Solutions,et al.  Microsoft Office 365 , 2014 .

[73]  A. Sato,et al.  Three‐dimensional spatial and temporal monitoring of soil water content using electrical resistivity tomography , 2001 .