{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T04:49:11Z","timestamp":1748580551665,"version":"3.40.5"},"reference-count":76,"publisher":"IOP Publishing","issue":"2","license":[{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"},{"start":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T00:00:00Z","timestamp":1747008000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Mach. Learn.: Sci. Technol."],"published-print":{"date-parts":[[2025,6,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Understanding the microstructure of porous media is crucial in various fields\u2014particularly in petroleum engineering, hydrogeology, and materials science\u2014because it directly influences the properties of porous materials and the behavior of fluids within their pores. Traditional characterization methods often struggle to capture the complex, heterogeneous micro-scale features of rock structures. To address this challenge, this study presents a novel approach for the classification and visualization of rock microstructure from micro-computed tomography images, leveraging pre-trained convolutional neural network (CNN) models (AlexNet, GoogLeNet, Inception v3 Net, ResNet, and DenseNet) combined with unsupervised machine learning (USML) techniques principal component analysis, multidimensional scaling, isometric mapping, t-distributed stochastic neighbor embedding (t-SNE), and uniform manifold approximation projection (UMAP)). Using pre-trained CNNs allows us to extract rich feature representations without the need for large, specialized training datasets, effectively capturing intricate patterns in the microstructures. The application of USML methods enables us to reduce dimensionality and uncover latent structures in the data without supervision. We tested the effectiveness of our method through three distinct case studies that include a wide variety of porous structures and found high classification accuracy using DenseNet and t-SNE or UMAP. Our approach successfully distinguishes similar rock samples that have been difficult to classify using conventional features such as porosity, specific surface area, and Euler characteristics, as demonstrated by silhouette score, Davies\u2013Bouldin Index, and Cali\u0144ski\u2013Harabasz Index. To enhance the interpretability of the machine learning approach, we proposed a patch-based analysis to identify local characteristic textural patterns that contribute significantly to the classification of individual rock samples. By visualizing the spatial distribution of these patterns and quantifying their characteristics, we gained insights into the microstructural differences between rock samples, providing an effective tool for interpreting the classification results and understanding the underlying factors that differentiate various rock types.<\/jats:p>","DOI":"10.1088\/2632-2153\/adcf71","type":"journal-article","created":{"date-parts":[[2025,4,22]],"date-time":"2025-04-22T22:54:39Z","timestamp":1745362479000},"page":"025033","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Feature extraction and classification of digital rock images via pre-trained convolutional neural network and unsupervised machine learning"],"prefix":"10.1088","volume":"6","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8577-3402","authenticated-orcid":true,"given":"Masashige","family":"Shiga","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0742-707X","authenticated-orcid":false,"given":"Masao","family":"Sorai","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8308-6211","authenticated-orcid":false,"given":"Tetsuya","family":"Morishita","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9777-5974","authenticated-orcid":true,"given":"Masaatsu","family":"Aichi","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4607-2355","authenticated-orcid":false,"given":"Naoki","family":"Nishiyama","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1837-775X","authenticated-orcid":false,"given":"Takashi","family":"Fujii","sequence":"additional","affiliation":[]}],"member":"266","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"mlstadcf71bib1","doi-asserted-by":"publisher","first-page":"ipj260424","DOI":"10.69631\/ipj.v1i1nr14","article-title":"Research needs in porous media for the energy transition","volume":"1","author":"Blunt","year":"2024","journal-title":"InterPore J."},{"key":"mlstadcf71bib2","doi-asserted-by":"publisher","first-page":"B62","DOI":"10.1115\/1.1483342","article-title":"Random heterogeneous materials: microstructure and macroscopic properties","volume":"55","author":"Torquato","year":"2002","journal-title":"Appl. Mech. Rev."},{"year":"1980","author":"Folk","key":"mlstadcf71bib3"},{"key":"mlstadcf71bib4","doi-asserted-by":"crossref","first-page":"217","DOI":"10.1016\/j.advwatres.2012.07.018","article-title":"x-ray imaging and analysis techniques for quantifying pore-scale structure and processes in subsurface porous medium systems","volume":"51","author":"Wildenschild","year":"2013","journal-title":"Adv. Water Resour."},{"key":"mlstadcf71bib5","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/j.flowmeasinst.2010.05.002","article-title":"Pore-scale visualization of gas trapping in porous media by x-ray CT scanning","volume":"21","author":"Zhou","year":"2010","journal-title":"Flow Meas. Instrum."},{"key":"mlstadcf71bib6","first-page":"304","article-title":"Multiphase flow in porous rock imaged under dynamic flow conditions with fast x-ray computed microtomography","volume":"55","author":"Berg","year":"2014","journal-title":"Petrophysics"},{"key":"mlstadcf71bib7","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1016\/j.ijggc.2019.04.024","article-title":"Predicting CO2 residual trapping ability based on experimental petrophysical properties for different sandstone types","volume":"86","author":"Ni","year":"2019","journal-title":"Int. J. Greenhouse Gas Control"},{"key":"mlstadcf71bib8","doi-asserted-by":"crossref","DOI":"10.1088\/2632-2153\/acf117","article-title":"A study of transfer learning in digital rock properties measurement","volume":"4","author":"Haq","year":"2023","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstadcf71bib9","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevE.96.043309","article-title":"Reconstruction of three-dimensional porous media using generative adversarial neural networks","volume":"96","author":"Mosser","year":"2017","journal-title":"Phys. Rev. E"},{"key":"mlstadcf71bib10","first-page":"1","article-title":"A Wasserstein GAN with gradient penalty for 3D porous media generation","volume":"vol 2022","author":"Corrales","year":"2022"},{"key":"mlstadcf71bib11","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1007\/s11242-023-02008-1","article-title":"Scale-independent rock heterogeneity classification algorithm applied to microtomography images","volume":"150","author":"Mohamed","year":"2023","journal-title":"Transp. Porous Media"},{"article-title":"Rock typing using the complete set of additive morphological descriptors","year":"2014","author":"Ismail","key":"mlstadcf71bib12"},{"key":"mlstadcf71bib13","doi-asserted-by":"publisher","DOI":"10.1088\/1751-8121\/ac72d7","article-title":"Local order metrics for two-phase media across length scales","volume":"55","author":"Torquato","year":"2022","journal-title":"J. Phys. A"},{"key":"mlstadcf71bib14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2023.105455","article-title":"Deep learning in image segmentation for mineral production: a review","volume":"180","author":"Liu","year":"2023","journal-title":"Comput. Geosci."},{"key":"mlstadcf71bib15","doi-asserted-by":"publisher","DOI":"10.1029\/2019WR026597","article-title":"Digital rock segmentation for petrophysical analysis with reduced user bias using convolutional neural networks","volume":"56","author":"Niu","year":"2020","journal-title":"Water Resour. Res."},{"key":"mlstadcf71bib16","doi-asserted-by":"publisher","DOI":"10.1029\/2023EA002845","article-title":"Exploring the Influence of Input Feature Space on CNN\u2010Based Geomorphic Feature Extraction From Digital Terrain Data","volume":"10","author":"Maxwell","year":"2023","journal-title":"Earth Space Sci."},{"key":"mlstadcf71bib17","doi-asserted-by":"publisher","DOI":"10.1016\/j.advwatres.2020.103539","article-title":"PoreFlow-Net: a 3D convolutional neural network to predict fluid flow through porous media","volume":"138","author":"Santos","year":"2020","journal-title":"Adv. Water Resour."},{"key":"mlstadcf71bib18","doi-asserted-by":"publisher","DOI":"10.1029\/2023WR035521","article-title":"Predicting 3D physical properties from a single 2D slice based on convolutional neural networks: 2D\u2010Slice\u2010To\u20103D\u2010Properties for porous rocks","volume":"59","author":"Chen","year":"2023","journal-title":"Water Resour. Res."},{"key":"mlstadcf71bib19","doi-asserted-by":"publisher","DOI":"10.1029\/2022WR033267","article-title":"Upscaling permeability using multiscale X\u2010ray\u2010CT images with digital rock modeling and deep learning techniques","volume":"59","author":"Jiang","year":"2023","journal-title":"Water Resour. Res."},{"key":"mlstadcf71bib20","doi-asserted-by":"crossref","DOI":"10.1088\/2632-2153\/ad45af","article-title":"Learning a general model of single phase flow in complex 3D porous media","volume":"5","author":"Santos","year":"2024","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstadcf71bib21","doi-asserted-by":"publisher","DOI":"10.1029\/2024WR037124","article-title":"Knowledge extraction via machine learning guides a topology\u2010based permeability prediction model","volume":"60","author":"Zhang","year":"2024","journal-title":"Water Resour. Res."},{"key":"mlstadcf71bib22","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2021.104799","article-title":"Deep learning of rock images for intelligent lithology identification","volume":"154","author":"Xu","year":"2021","journal-title":"Comput. Geosci."},{"key":"mlstadcf71bib23","first-page":"248","article-title":"Imagenet: a large-scale hierarchical image database","author":"Deng","year":"2009"},{"article-title":"Learning multiple layers of features from tiny images","year":"2009","author":"Krizhevsky","key":"mlstadcf71bib24"},{"key":"mlstadcf71bib25","doi-asserted-by":"publisher","DOI":"10.3389\/feart.2022.1079447","article-title":"Rock image classification using deep residual neural network with transfer learning","volume":"10","author":"Chen","year":"2023","journal-title":"Front. Earth Sci."},{"key":"mlstadcf71bib26","doi-asserted-by":"publisher","first-page":"SF27","DOI":"10.1190\/INT-2018-0245.1","article-title":"Convolutional neural networks as aid in core lithofacies classification","volume":"7","author":"Pires de Lima","year":"2019","journal-title":"Interpretation"},{"key":"mlstadcf71bib27","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/1022\/1\/012086","article-title":"Automatic plant identification using transfer learning","volume":"1022","author":"Sachar","year":"2021","journal-title":"IOP Conf. Ser.: Mater. Sci. Eng."},{"key":"mlstadcf71bib28","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2402\/1\/012009","article-title":"Galaxy morphology classification with densenet","volume":"2402","author":"Hui","year":"2022","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadcf71bib29","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/2571\/1\/012006","article-title":"Comparative analysis of pre-trained resnet and densenet models for the detection of diabetic macular Edema","volume":"2571","author":"Pavithra","year":"2023","journal-title":"J. Phys.: Conf. Ser."},{"key":"mlstadcf71bib30","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/BF02289694","article-title":"Nonmetric multidimensional scaling: a numerical method","volume":"29","author":"Kruskal","year":"1964","journal-title":"Psychometrika"},{"key":"mlstadcf71bib31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/BF02289565","article-title":"Multidimensional scaling by optimizing goodness of fit to a nonmetric hypothesis","volume":"29","author":"Kruskal","year":"1964","journal-title":"Psychometrika"},{"year":"2005","author":"Borg","key":"mlstadcf71bib32"},{"key":"mlstadcf71bib33","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","article-title":"A global geometric framework for nonlinear dimensionality reduction","volume":"290","author":"Tenenbaum","year":"2000","journal-title":"science"},{"key":"mlstadcf71bib34","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"article-title":"Umap: uniform manifold approximation and projection for dimension reduction","year":"2018","author":"McInnes","key":"mlstadcf71bib35"},{"key":"mlstadcf71bib36","doi-asserted-by":"publisher","first-page":"9","DOI":"10.3389\/fninf.2016.00009","article-title":"A tool for interactive data visualization: application to over 10,000 brain imaging and phantom MRI data sets","volume":"10","author":"Panta","year":"2016","journal-title":"Front. Neuroinform."},{"key":"mlstadcf71bib37","doi-asserted-by":"publisher","DOI":"10.3389\/fmed.2021.595077","article-title":"Unsupervised clustering reveals sarcoidosis phenotypes marked by a reduction in lymphocytes relate to increased inflammatory activity on 18FDG-PET\/CT","volume":"8","author":"Vagts","year":"2021","journal-title":"Front. Med."},{"key":"mlstadcf71bib38","doi-asserted-by":"publisher","DOI":"10.1063\/1.5091842","article-title":"Unsupervised machine learning in atomistic simulations, between predictions and understanding","volume":"150","author":"Ceriotti","year":"2019","journal-title":"J. Chem. Phys."},{"key":"mlstadcf71bib39","doi-asserted-by":"publisher","DOI":"10.1063\/5.0061874","article-title":"Time-dependent principal component analysis: a unified approach to high-dimensional data reduction using adiabatic dynamics","volume":"155","author":"Morishita","year":"2021","journal-title":"J. Chem. Phys."},{"key":"mlstadcf71bib40","doi-asserted-by":"publisher","DOI":"10.1088\/2632-2153\/ace81a","article-title":"Manifold learning in atomistic simulations: a conceptual review","volume":"4","author":"Rydzewski","year":"2023","journal-title":"Mach. Learn. Sci. Technol."},{"key":"mlstadcf71bib41","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.105.075107","article-title":"Structural analysis based on unsupervised learning: search for a characteristic low-dimensional space by local structures in atomistic simulations","volume":"105","author":"Tamura","year":"2022","journal-title":"Phys. Rev. B"},{"key":"mlstadcf71bib42","doi-asserted-by":"publisher","first-page":"5781","DOI":"10.1021\/acs.jpcb.4c01526","article-title":"Ab initio characterization of the CO2\u2013water interface using unsupervised machine learning for dimensionality reduction","volume":"128","author":"Morishita","year":"2024","journal-title":"J. Phys. Chem. A"},{"key":"mlstadcf71bib43","doi-asserted-by":"publisher","DOI":"10.1063\/5.0224230","article-title":"The wetting of H2O by CO2","volume":"161","author":"Brookes","year":"2024","journal-title":"J. Chem. Phys."},{"key":"mlstadcf71bib44","doi-asserted-by":"publisher","first-page":"1251","DOI":"10.1007\/s10596-021-10059-w","article-title":"Geological facies modeling based on progressive growing of generative adversarial networks (GANs)","volume":"25","author":"Song","year":"2021","journal-title":"Comput. Geosci."},{"key":"mlstadcf71bib45","doi-asserted-by":"publisher","first-page":"1","DOI":"10.2113\/2024\/lithosphere_2023_233","article-title":"Stochastic reconstruction of 3D heterogeneous microstructure using a column-oriented multiple-point statistics program","volume":"2024","author":"Zuo","year":"2024","journal-title":"Lithosphere"},{"key":"mlstadcf71bib46","first-page":"p 25","article-title":"Imagenet classification with deep convolutional neural networks","author":"Krizhevsky","year":"2012"},{"key":"mlstadcf71bib47","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"mlstadcf71bib48","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"mlstadcf71bib49","first-page":"2818","article-title":"Rethinking the inception architecture for computer vision","author":"Szegedy","year":"2016"},{"key":"mlstadcf71bib50","first-page":"4700","article-title":"Densely connected convolutional networks","author":"Huang","year":"2017"},{"key":"mlstadcf71bib51","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.21105\/joss.01296","article-title":"PoreSpy: a python toolkit for quantitative analysis of porous media images","volume":"4","author":"Gostick","year":"2019","journal-title":"J. Open Source Softw."},{"article-title":"Automatic differentiation in pytorch","year":"2017","author":"Paszke","key":"mlstadcf71bib52"},{"article-title":"Network in network","year":"2013","author":"Lin","key":"mlstadcf71bib53"},{"author":"Digital Rocks Portal","key":"mlstadcf71bib54"},{"article-title":"Blobbiness: a measure of how blobby an image is","year":"n.d.","author":"PoreSpy","key":"mlstadcf71bib55"},{"key":"mlstadcf71bib56","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-021-90090-0","article-title":"High accuracy capillary network representation in digital rock reveals permeability scaling functions","volume":"11","author":"Neumann","year":"2021","journal-title":"Sci. Rep."},{"key":"mlstadcf71bib57","doi-asserted-by":"publisher","first-page":"6955","DOI":"10.1002\/2016JB013793","article-title":"Permeability of porous media: role of the critical pore size","volume":"122","author":"Nishiyama","year":"2017","journal-title":"J. Geophys. Res."},{"key":"mlstadcf71bib58","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","article-title":"A cluster separation measure","volume":"2","author":"Davies","year":"1979","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"mlstadcf71bib59","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","article-title":"A dendrite method for cluster analysis","volume":"3","author":"Cali\u0144ski","year":"1974","journal-title":"Commun. Stat. Theory Methods"},{"key":"mlstadcf71bib60","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1186\/s12859-022-04675-1","article-title":"Statistical power for cluster analysis","volume":"23","author":"Dalmaijer","year":"2022","journal-title":"BMC Bioinf."},{"article-title":"Very deep convolutional networks for large-scale image recognition","year":"2014","author":"Simonyan","key":"mlstadcf71bib61"},{"article-title":"Mobilenets: efficient convolutional neural networks for mobile vision applications","year":"2017","author":"Howard","key":"mlstadcf71bib62"},{"key":"mlstadcf71bib63","first-page":"1251","article-title":"Xception: deep learning with depthwise separable convolutions","author":"Chollet","year":"2017"},{"key":"mlstadcf71bib64","first-page":"6105","article-title":"Efficientnet: rethinking model scaling for convolutional neural networks","author":"Tan","year":"2019"},{"key":"mlstadcf71bib65","article-title":"A unified approach to interpreting model predictions","volume":"vol 30","author":"Lundberg","year":"2017"},{"key":"mlstadcf71bib66","first-page":"1135","article-title":"Why should i trust you? Explaining the predictions of any classifier","author":"Ribeiro","year":"2016"},{"article-title":"Captum: a unified and generic model interpretability library for PyTorch","year":"2020","author":"Kokhlikyan","key":"mlstadcf71bib67"},{"key":"mlstadcf71bib68","doi-asserted-by":"publisher","DOI":"10.1016\/j.cageo.2023.105511","article-title":"Explainable deep learning for automatic rock classification","volume":"184","author":"Zheng","year":"2024","journal-title":"Comput. Geosci"},{"key":"mlstadcf71bib69","doi-asserted-by":"publisher","first-page":"1358","DOI":"10.1039\/D2LC00020B","article-title":"Lab chip for a low-carbon future","volume":"23","author":"Datta","year":"2023","journal-title":"Lab on a Chip"},{"key":"mlstadcf71bib70","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41467-016-0009-6","article-title":"Quantifying similarity of pore-geometry in nanoporous materials","volume":"8","author":"Lee","year":"2017","journal-title":"Nat. Commun."},{"key":"mlstadcf71bib71","doi-asserted-by":"publisher","first-page":"3203","DOI":"10.1021\/acs.energyfuels.4c05413","article-title":"Experimental study of CO2 injection in sandstone aquifer for sequestration purposes using x-ray computed tomography","volume":"39","author":"Shi","year":"2025","journal-title":"Energy Fuels"},{"key":"mlstadcf71bib72","doi-asserted-by":"publisher","DOI":"10.1016\/j.cma.2025.117784","article-title":"History-matching of imbibition flow in fractured porous media Using Physics-Informed Neural Networks (PINNs)","volume":"437","author":"Abbasi","year":"2025","journal-title":"Comput. Methods Appl. Mech. Eng."},{"key":"mlstadcf71bib73","doi-asserted-by":"publisher","first-page":"143","DOI":"10.46690\/ager.2025.02.06","article-title":"Impact of micro-scale characteristics of shale reservoirs on gas depletion behavior: a microscale discrete model","volume":"15","author":"Cheng","year":"2025","journal-title":"Adv. Geo-Energy Res."},{"article-title":"Simulating carbon mineralization at pore scale in capillary networks of digital rock","year":"2024","author":"Vasquez","key":"mlstadcf71bib74"},{"key":"mlstadcf71bib75","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevApplied.13.024043","article-title":"Nanometer-scale deformations of Berea sandstone under moisture-content variations","volume":"13","author":"Ilin","year":"2020","journal-title":"Phys. Rev. Appl."},{"year":"2025","author":"Shiga","key":"mlstadcf71bib76","doi-asserted-by":"publisher","DOI":"10.5281\/zenodo.14859377"}],"container-title":["Machine Learning: Science and Technology"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,12]],"date-time":"2025-05-12T10:50:00Z","timestamp":1747047000000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2632-2153\/adcf71"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,12]]},"references-count":76,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2025,5,12]]},"published-print":{"date-parts":[[2025,6,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2632-2153\/adcf71","relation":{},"ISSN":["2632-2153"],"issn-type":[{"type":"electronic","value":"2632-2153"}],"subject":[],"published":{"date-parts":[[2025,5,12]]},"assertion":[{"value":"Feature extraction and classification of digital rock images via pre-trained convolutional neural network and unsupervised machine learning","name":"article_title","label":"Article Title"},{"value":"Machine Learning: Science and Technology","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 The Author(s). Published by IOP Publishing Ltd","name":"copyright_information","label":"Copyright Information"},{"value":"2024-11-03","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-04-22","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-05-12","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}