Multimodal imaging and machine learning to enhance microscope images of shale

Anderson, Timothy I.; Vega, Bolivia; Kovscek, Anthony R.

doi:10.1016/j.cageo.2020.104593

Multimodal imaging and machine learning to enhance microscope images of shale

Journal Article · Sun Sep 06 00:00:00 EDT 2020 · Computers and Geosciences

DOI:https://doi.org/10.1016/j.cageo.2020.104593· OSTI ID:1759011

Anderson, Timothy I. ^[1]; ^[2]; Kovscek, Anthony R. ^[2]

Stanford Univ., CA (United States); Stanford University
Stanford Univ., CA (United States)

A machine learning based image processing workflow is presented to enhance shale source rock microscopic images obtained using diverse imaging platforms. Images were acquired from a 30 μm diameter cylindrical Vaca Muerta shale sample using both nondestructive Transmission X-Ray Microscopy (TXM, alternately referred to as nano computed tomography) and destructive Focused Ion Beam-Scanning Electron Microscopy (FIB-SEM). Output cross-sectional images from each modality were aligned using a combination of manual and automated registration techniques to create a registered image dataset. We then apply this dataset for two image processing tasks: prediction of image cross sections with SEM-like resolution from nondestructive TXM data and repair of charged region artifacts (localized accumulation of electrons) within SEM images. The image processing algorithms for both tasks use deep learning models, specifically image-to-image Convolutional Neural Networks (CNNs) and conditional Generative Adversarial Networks (cGANs). In the image enhancement tasks, we are able to achieve significant qualitative and quantitative improvement in TXM images. Here, the best model reaches an average Peak Signal to Noise Ratio (PSNR) of 15.8 dB. Conditioning on TXM data is also shown to reduce artifacts from SEM charging, achieving an average PSNR of 25.8 dB. Furthermore, our results suggest that properly trained and validated networks are capable of significant enhancement of images obtained using nondestructive techniques, thereby improving interpretation of two- and three-dimensional images while preserving samples for future use.

View Accepted Manuscript (DOE)

Research Organization:: Stanford Univ., CA (United States)

Sponsoring Organization:: USDOE Office of Science (SC), Basic Energy Sciences (BES)

Grant/Contract Number:: SC0019165; AC02-76SF00515

OSTI ID:: 1759011

Journal Information:: Computers and Geosciences, Journal Name: Computers and Geosciences Vol. 145; ISSN 0098-3004

Publisher:: ElsevierCopyright Statement

Country of Publication:: United States

Language:: English

References (26)

Perceptual Losses for Real-Time Style Transfer and Super-Resolution Johnson, Justin; Alahi, Alexandre; Fei-Fei, Li Computer Vision – ECCV 2016 https://doi.org/10.1007/978-3-319-46475-6_43	book	September 2016
Quantifying the heterogeneity of shale through statistical combination of imaging across scales Semnani, Shabnam J.; Borja, Ronaldo I. Acta Geotechnica, Vol. 12, Issue 6 https://doi.org/10.1007/s11440-017-0576-7	journal	August 2017
The application of pattern recognition in the automatic classification of microscopic rock images Młynarczuk, Mariusz; Górszczyk, Andrzej; Ślipek, Bartłomiej Computers & Geosciences, Vol. 60 https://doi.org/10.1016/j.cageo.2013.07.015	journal	October 2013
Application of Decision Tree Algorithm for classification and identification of natural minerals using SEM–EDS Akkaş, Efe; Akin, Lutfiye; Evren Çubukçu, H. Computers & Geosciences, Vol. 80 https://doi.org/10.1016/j.cageo.2015.03.015	journal	July 2015
A novel method for extracting information on pores from cast thin-section images Dong, Shaoqun; Zeng, Lianbo; Xu, Chaoshui Computers & Geosciences, Vol. 130 https://doi.org/10.1016/j.cageo.2019.05.003	journal	September 2019
Mineral grains recognition using computer vision and machine learning Maitre, Julien; Bouchard, Kévin; Bédard, L. Paul Computers & Geosciences, Vol. 130 https://doi.org/10.1016/j.cageo.2019.05.009	journal	September 2019
Deep learning-based method for SEM image segmentation in mineral characterization, an example from Duvernay Shale samples in Western Canada Sedimentary Basin Chen, Zhuoheng; Liu, Xiaojun; Yang, Jijin Computers & Geosciences, Vol. 138 https://doi.org/10.1016/j.cageo.2020.104450	journal	May 2020
Enhancing images of shale formations by a hybrid stochastic and deep learning algorithm Kamrava, Serveh; Tahmasebi, Pejman; Sahimi, Muhammad Neural Networks, Vol. 118 https://doi.org/10.1016/j.neunet.2019.07.009	journal	October 2019
Fiji: an open-source platform for biological-image analysis Schindelin, Johannes; Arganda-Carreras, Ignacio; Frise, Erwin Nature Methods, Vol. 9, Issue 7 https://doi.org/10.1038/nmeth.2019	journal	June 2012
Reconstruction of porous media from extremely limited information using conditional generative adversarial networks Feng, Junxi; He, Xiaohai; Teng, Qizhi Physical Review E, Vol. 100, Issue 3 https://doi.org/10.1103/PhysRevE.100.033308	journal	September 2019
Reconstruction of three-dimensional porous media using generative adversarial neural networks Mosser, Lukas; Dubrule, Olivier; Blunt, Martin J. Physical Review E, Vol. 96, Issue 4 https://doi.org/10.1103/PhysRevE.96.043309	journal	October 2017
TXM-Wizard : a program for advanced data collection and evaluation in full-field transmission X-ray microscopy Liu, Yijin; Meirer, Florian; Williams, Phillip A. Journal of Synchrotron Radiation, Vol. 19, Issue 2 https://doi.org/10.1107/S0909049511049144	journal	January 2012
Automatic projection image registration for nanoscale X-ray tomographic reconstruction Yu, Haiyan; Xia, Sihao; Wei, Chenxi Journal of Synchrotron Radiation, Vol. 25, Issue 6 https://doi.org/10.1107/S1600577518013929	journal	October 2018
Morphometric analysis of white matter lesions in MR images: method and validation Zijdenbos, A. P.; Dawant, B. M.; Margolin, R. A. IEEE Transactions on Medical Imaging, Vol. 13, Issue 4 https://doi.org/10.1109/42.363096	journal	January 1994
Semantic Image Inpainting with Deep Generative Models Yeh, Raymond A.; Chen, Chen; Lim, Teck Yian 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) https://doi.org/10.1109/CVPR.2017.728	conference	July 2017
Image Quality Assessment: From Error Visibility to Structural Similarity Wang, Z.; Bovik, A. C.; Sheikh, H. R. IEEE Transactions on Image Processing, Vol. 13, Issue 4 https://doi.org/10.1109/TIP.2003.819861	journal	April 2004
Coupled Dictionary Training for Image Super-Resolution Yang, Jianchao; Wang, Zhaowen; Lin, Zhe IEEE Transactions on Image Processing, Vol. 21, Issue 8, p. 3467-3478 https://doi.org/10.1109/TIP.2012.2192127	journal	August 2012
Visual pattern recognition by moment invariants Hu, Ming-Kuei IEEE Transactions on Information Theory, Vol. 8, Issue 2, p. 179-187 https://doi.org/10.1109/TIT.1962.1057692	journal	February 1962
Image Super-Resolution Using Deep Convolutional Networks Dong, Chao; Loy, Chen Change; He, Kaiming IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol. 38, Issue 2 https://doi.org/10.1109/TPAMI.2015.2439281	journal	February 2016
Three-Dimensional Mapping of Soil Chemical Characteristics at Micrometric Scale by Combining 2D SEM-EDX Data and 3D X-Ray CT Images Hapca, Simona; Baveye, Philippe C.; Wilson, Clare PLOS ONE, Vol. 10, Issue 9 https://doi.org/10.1371/journal.pone.0137205	journal	September 2015
Morphology, Genesis, and Distribution of Nanometer-Scale Pores in Siliceous Mudstones of the Mississippian Barnett Shale Loucks, R. G.; Reed, R. M.; Ruppel, S. C. Journal of Sedimentary Research, Vol. 79, Issue 12 https://doi.org/10.2110/jsr.2009.092	journal	November 2009
Multiscale Gas Transport in Shales With Local Kerogen Heterogeneities Akkutlu, I. Yucel; Fathi, Ebrahim SPE Journal, Vol. 17, Issue 04 https://doi.org/10.2118/146422-PA	journal	December 2012
Multiscale Imaging of Gas Storage in Shales Aljamaan, Hamza; Ross, Cynthia M.; Kovscek, Anthony R. SPE Journal, Vol. 22, Issue 06 https://doi.org/10.2118/185054-PA	journal	August 2017
Imaging-Based Characterization of Calcite-Filled Fractures and Porosity in Shales Vega, Bolivia; Ross, Cynthia M.; Kovscek, Anthony R. SPE Journal, Vol. 20, Issue 04 https://doi.org/10.2118/2014-1922521-PA	journal	August 2015
Fast Patch-Based Pseudo-CT Synthesis from T1-Weighted MR Images for PET/MR Attenuation Correction in Brain Studies Torrado-Carvajal, A.; Herraiz, J. L.; Alcain, E. Journal of Nuclear Medicine, Vol. 57, Issue 1 https://doi.org/10.2967/jnumed.115.156299	journal	October 2015
Deep Learning in Neuroradiology Zaharchuk, G.; Gong, E.; Wintermark, M. American Journal of Neuroradiology, Vol. 39, Issue 10 https://doi.org/10.3174/ajnr.A5543	journal	February 2018

Similar Records

2D-to-3D image translation of complex nanoporous volumes using generative networks

Journal Article · Thu Oct 21 00:00:00 EDT 2021 · Scientific Reports · OSTI ID:1835602

Pore system characterization of organic-rich shales using nanoscale-resolution 3D imaging

Journal Article · Fri Sep 20 00:00:00 EDT 2019 · Fuel · OSTI ID:1594054

Related Subjects

58 GEOSCIENCES
Data Processing
Data assimilation
Deep learning
Image analysis
Machine learning
Shale

Multimodal imaging and machine learning to enhance microscope images of shale

Citation Formats

References (26)

Similar Records

Related Subjects