Machine learning and fractal attributes applied to automatic detection and classification of geologic planes in resistivity image logs

dc.contributor.advisorOchoa Gutiérrez, Luis Hernán
dc.contributor.authorLeal Freitez, Jorge Alberto
dc.date.accessioned2021-11-24T20:07:06Z
dc.date.available2021-11-24T20:07:06Z
dc.date.issued2021-11
dc.descriptionilustraciones, fotografías color, fotografías blanco y negro, tablasspa
dc.description.abstractThe purpose of this research is to develop a methodology for automatic detection and classification of geologic planes in wireline acquired resistivity imaging. The methodology involves the application of bioinspired image filters, machine learning, and elements of fractal theory. In upstream activities of hydrocarbon reservoirs, the analysis and interpretation of resistivity imaging is a time-consuming and repetitive task, usually manually performed by specialized geologists. Delay in this task may result in operational problems, causing economic losses during field operations. In order to solve this issue, the present research proposes automatic extraction of geologic features in borehole resistivity imaging shortly after the image log is acquired. Features are initially extracted from pixels analysis of the dynamic-normalized images, employing a set of computer vision techniques to detect edges and sinusoids. Afterward, these sinusoids are classified using statistical measures and machine learning. During training and classification stages, machines employ fractal dimension, lacunarity, and their derived statistic parameters (fractal attributes); the fractal information is complemented with resistivity, gamma rays, and photoelectric factor logs to improve the accuracy during classification. In both clastic and carbonate environments, the outcome consists of a set of classified geologic planes, precise enough to recognize patterns in the structural and stratigraphic dips of the drilled sequence. Academically, the main novelty of this research is the integration of fractal theory and machine learning, aiming at automatizing interpretation of resistivity imaging in hydrocarbon producer wells. (Text taken from source)eng
dc.description.abstractEl propósito de esta investigación es desarrollar una metodología para la detección y clasificación automática de planos geológicos en imágenes resistivas adquirida con cable. La metodología involucra aplicación de filtros bioinspirados, aprendizaje automático y elementos de la teoría fractal. En las actividades aguas arriba de yacimientos de hidrocarburos, el análisis e interpretación de imágenes resistivas es una tarea repetitiva, que requiere mucho tiempo y generalmente realizada manualmente por geólogos especializados. La demora en esta tarea puede resultar en problemas operativos, causando pérdidas económicas durante las operaciones de campo. Para resolver este problema, la presente investigación propone la extracción automática de características geológicas en las imágenes de resistividad del pozo poco después de que se adquiere el registro de imágenes. Las características se extraen inicialmente del análisis de píxeles de las imágenes dinámicas normalizadas, empleando un conjunto de técnicas de visión por computadora para detectar bordes y sinusoides. Posteriormente, estas sinusoides se clasifican utilizando medidas estadísticas y aprendizaje automático. Durante las etapas de entrenamiento y clasificación, las máquinas emplean la dimensión fractal, lagunaridad y sus parámetros estadísticos derivados (atributos fractales); la información fractal se complementa con registros de resistividad, rayos gamma y factor fotoeléctrico para mejorar la precisión durante la clasificación. Tanto en ambientes clásticos como en carbonatos, el resultado consiste en un conjunto de planos geológicos clasificados, lo suficientemente precisos como para reconocer patrones en los buzamientos estructurales y estratigráficos de la secuencia perforada. Académicamente, la principal novedad de esta investigación es la integración de la teoría fractal y aprendizaje automático, con el objetivo de automatizar la interpretación de imágenes resistivas en pozos productores de hidrocarburosspa
dc.description.degreelevelDoctoradospa
dc.description.degreenameDoctor en Geocienciasspa
dc.description.researchareaSistemas Inteligentes Aplicados a las Geocienciasspa
dc.format.extent136 páginasspa
dc.format.mimetypeapplication/pdfspa
dc.identifier.instnameUniversidad Nacional de Colombiaspa
dc.identifier.reponameRepositorio Institucional Universidad Nacional de Colombiaspa
dc.identifier.repourlhttps://repositorio.unal.edu.co/spa
dc.identifier.urihttps://repositorio.unal.edu.co/handle/unal/80725
dc.language.isoengspa
dc.publisherUniversidad Nacional de Colombiaspa
dc.publisher.branchUniversidad Nacional de Colombia - Sede Bogotáspa
dc.publisher.departmentDepartamento de Geocienciasspa
dc.publisher.facultyFacultad de Cienciasspa
dc.publisher.programBogotá - Ciencias - Doctorado en Geocienciasspa
dc.relation.referencesAggarwal, C., 2015, Data mining. The textbook, first edition. Springer, New York, 181-488pp.spa
dc.relation.referencesAllain, C., Cloitre, M., 1991, Characterizing the lacunarity of random and deterministic fractal sets. Physical Review A, 44(6), 3552 - 3553. https://doi.org/10.1103/PhysRevA.44.3552spa
dc.relation.referencesAlpaydin, E., 2014, Introduction to machine learning, third edition. The MIT Press, Cambridge, 27-238pp.spa
dc.relation.referencesAl-Sit, W., Al-Nuaimy, W., Marelli, M., Al- Ataby, A., 2015, Visual texture for automated characterization of geological features in borehole televiewer imagery. Journal of Applied Geophysics, 119, 39-146pp. http://dx.doi.org/10.1016/j.jappgeo.2015.05.015spa
dc.relation.referencesArizabalo, R., Oleschko, K., Gabor, K., Lozada, M., Castrejón, R., Ronquillo, G., 2006, Lacunarity of geophysical well logs in the Cantarell oil field, Gulf of Mexico. Geofísica International, 45(2), 99-105pp.spa
dc.relation.referencesAssous, S., Elkington, P., Clark, S., Whetton, J., 2013, Automated detection of planar geological feature in borehole image. Society of Exploration Geophysicists, 79 (1). D11-D19pp. https://doi.org/10.1190/geo2013-0189.1spa
dc.relation.referencesAsquith, G., Krygowski, D., 2004, Basic well log analysis, second edition. The American Association of Petroleum Geologist, Tulsa, 31pp.spa
dc.relation.referencesArora, N., Sarvani, G., 2017, A review paper on Gabor filter algorithm & its application. IJARECE, 6 (9), 1003-1007pp. doi:10.17148/IJARCCE.2017.6492spa
dc.relation.referencesAwad, M., Khanna, R., 2015, Efficient learning machines, second edition. Apress Open, Berkeley, 14-17pp.spa
dc.relation.referencesAyad, A., Amrani, M., Bakkali, S., 2019, Quantification of the disturbances of phosphate series using the box-counting method on geoelectrical images (Sidi Chennane, Morocco). International Journal of Geophysics, 2019(12), 1-12. https://doi.org/10.1155/2019/2565430spa
dc.relation.referencesBarnsley, M., 1993, Fractals Everywhere, second edition. Morgan Kaufmann, Atlanta, 171pp.spa
dc.relation.referencesBloem, P., 2010, Machine learning and fractal geometry. M.Sc. Thesis, University of Amsterdam. iii-8pp.spa
dc.relation.referencesBoggs, S., 2009, Petrology of sedimentary rocks, second edition. Cambridge University Press, Cambridge, 194-314pp.spa
dc.relation.referencesBoggs, S., 2014, Principles of sedimentology and stratigraphy, fifth edition. Pearson Educational Limited, Edinburgh, 76-135pp.spa
dc.relation.referencesBrownlee, J., 2016, What is a Confusion Matrix in Machine Learning. Machine Learning Mastery, 18 November 2016, https://machinelearningmastery.com/confusion-matrix-machine-learning/ (accessed 6 June 2020).spa
dc.relation.referencesBurger, W., Burge, M., 2009, Principles of digital image processing. Fundamental techniques, first edition. Springer, Hagenberg, 57-122pp.spa
dc.relation.referencesBurger, W., Burge, M., 2009, Principles of digital image processing. Core algorithms, first edition. Springer, Hagenberg, 110pp.spa
dc.relation.referencesChangchun, Z., Ge, S., 2002, A Hough transform-based method for fast detection of fixed period sinusoidal curves in images. Signal Processing 6th International Conference, 909-912pp. DOI: 10.1109/ICOSP.2002.1181204spa
dc.relation.referencesCheng, G., Guo, W., 2017, Rock images classification by using deep convolutional neural network. Journal of Physiscs, 887, 1-7pp. DOI: 10.1088/1742-6596/887/1/012089spa
dc.relation.referencesConway, D., Myles, J., 2012, Machine learning for hackers, first edition. O’Reilly, Sebastopol, 17pp.spa
dc.relation.referencesDavis, G., Reynolds, S., Kluth, C., 2012, Structural geology of rocks and regions, third edition. John Wiley and Sons, Hoboken, 786pp.spa
dc.relation.referencesDesarda, A., 2019, Understanding AdaBoost. Towards Data Science, 17 January 2019, https://towardsdatascience.com/understanding-adaboost-2f94f22d5bfe (accessed 7 June 2020).spa
dc.relation.referencesEllis, D., Singer, J., 2008, Well logging for earth scientists, second edition. Springer, Ridgefield, 20pp.spa
dc.relation.referencesGeron, A., 2019, Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow, second edition. O’Reilly Media Inc., Sebastopol, 177pp.spa
dc.relation.referencesGlander, S., 2018, Machine Learning Basics - Gradient Boosting & XGBoost. Shirin's playgRound, 29 November 2018, https://www.shirin-glander.de/2018/11/ml_basics_gbm/ (accessed 8 June 2020).spa
dc.relation.referencesHan, J., Kamber, M., Pei, J., 2012, Data mining. Concepts and techniques, third edition. Morgan Kaufmann, Waltham, 254-460pp.spa
dc.relation.referencesHarvey, A., Fotopoulos, G., 2016, Geological mapping using machine learning algorithms. The international Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLI (B8), 423-430pp. DOI:10.5194/ISPRS-ARCHIVES-XLI-B8-423-2016spa
dc.relation.referencesHe, C., Wang, W., 2010, A PCNN-Based Edge Detection Algorithm for Rock Fracture Images, 2010 Symposium on Photonics and Optoelectronics, 2010, 1-4pp. 10.1109/SOPO.2010.5504347.spa
dc.relation.referencesJoseph, R., 2018, Grid Search for model tuning. Towards Data Science, 29 December 2018, https://towardsdatascience.com/grid-search-for-model-tuning-3319b259367e (accessed 8 June 2020).spa
dc.relation.referencesKhan, J., 2019, Guide to image inpainting: using machine learning to edit and correct defects in photos. Medium Heartbeat, 7 August 2019, https://heartbeat.fritz.ai/guide-to-image-inpainting-using-machine-learning-to-edit-and-correct-defects-in-photos-3c1b0e13bbd0 (accessed 5 June 2019).spa
dc.relation.referencesKoehrsen, W., 2018, Improving the Random Forest in Python Part 1. Towards Data Science, 6 January 2018. https://towardsdatascience.com/improving-random-forest-in-python-part-1-893916666cd (accessed 10 January 2020).spa
dc.relation.referencesLeal, J., Ochoa, L., Contreras, C., 2018, Automatic identification of calcareous lithologies using support vector machines, borehole logs and fractal dimension of borehole electrical imaging. Earth Sciences Research Journal, 22(2), 75-82pp. https://doi.org/10.15446/esrj.v22n2.68320spa
dc.relation.referencesLeal, J., Ochoa, L., Garcia, G., 2016, Identification of natural fractures using resistive image logs, fractal dimension and support vector machines. Ingeniería e Investigación, 36(3), 125-132pp. https://doi.org/10.15446/ing.investig.v36n3.56198spa
dc.relation.referencesLi, J., Sun, C., Du, Q., 2006, A new box-counting method for estimation of image fractal dimension. International Conference on Image Processing, 2006, 3029-3032. DOI: 10.1109/ICIP.2006.313005.spa
dc.relation.referencesLisle, R., 2004, Geological structures and maps. A practical guide, third edition. Elsevier, Oxford, 2pp.spa
dc.relation.referencesLuthi, S., 2001, Geological well logs. Their use in reservoir modeling, first edition. Springer, Berlin, 53pp.spa
dc.relation.referencesMandelbrot, B., 1983, The fractal geometry of nature, second edition. W. H. Freeman and Company, New York, 14pp.spa
dc.relation.referencesMaynberg, O., Kush, G., 2013, Airborne crown density estimation. International Society For Photogrammetry And Remote Sensing, 2 (49), 49-54pp. https://doi.org/10.5194/isprsannals-II-3-W3-49-2013spa
dc.relation.referencesMoreno, G., García, O., 2006, Quantitative characterization of fracture patterns with circular windows and fractal analysis., Geología Colombiana, (31), 73-74pp.spa
dc.relation.referencesMorton, D., Woods, A., 1992, Development geology reference manual. AAPG Methods in exploration V10., Tulsa, 174pp.spa
dc.relation.referencesNeer, K., Mathur, S., 2015, An improved method of edge detection based on Gabor wavelet transform. Recent Advances in Electrical Engineering and Electronic Devices, 184-191pp.spa
dc.relation.referencesNelson, R., 2001, Geologic analysis of naturally fractured reservoirs, second edition. Gulf Professional Publishing, Woburn, 23pp.spa
dc.relation.referencesNichols, G., 2009, Sedimentology and stratigraphy, second edition. Willey-Blackwell, Chichester, 66-88pp.spa
dc.relation.referencesOchoa, L., Niño, L., Vargas, C., 2018, Fast estimation of earthquake epicenter distance using a single seismological station with machine learning techniques. DYNA, 85 (204), 161-168pp. https://doi.org/10.15446/dyna.v85n204.68408spa
dc.relation.referencesOppenheimer, A., 2018, ¡Sálvese quien pueda! EL trabajo del futuro en la era de la automatización, primera edición. Penguin Random House Group Editorial, Ciudad de México, 6pp.spa
dc.relation.referencesPark, S., Kim, Y., Ryoo, C. Sanderson, D., 2010, Fractal analysis of the evolution of a fracture network in a granite outcrop, SE Korea. Geosciences Journal, 14(1), 201-215pp. https://doi.org/10.1007/s12303-010-0019-zspa
dc.relation.referencesParker, J., 2011, Algorithms for image processing and computer vision, second edition. John Wiley and Sons, Indianapolis, 85pp.spa
dc.relation.referencesPlotnick, R., Garner, R., Hargrove, W., Prestegaard, K., Perlmutter, M., 1996, Lacunarity analysis: A general technique for the analysis of spatial patterns. Physical Review E, 53(5461), 5461-5468. https://doi.org/10.1103/PhysRevE.53.5461spa
dc.relation.referencesPratt, W., 2007, Digital image processing, fourth edition. John Wiley and Sons, Los Altos, 421pp.spa
dc.relation.referencesQuan, Y., Xu, Y., Sun, Y., Luo, Y., 2014, Lacunarity analysis on image patterns for texture classification, in 2014 IEEE Conference on Computer Vision and Pattern Recognition, The United States Of America, 23-28 June. DOI: 10.1109/CVPR.2014.28spa
dc.relation.referencesQuintanilla, C., Cacau, D., Dos Santos, R., Ribeiro, E., Leta, F., Gonzalez, E., 2017, Improving accuracy of automatic fracture detection in borehole images with deep learning and GPUs. 30th SIBGRAPI Conference on Graphics, Patterns and Images (SIBGRAPI), 345-350pp. DOI: 10.1109/SIBGRAPI.2017.52.spa
dc.relation.referencesRaghupathy, K., 2004, Curve tracing and curve detection in images. M.Sc. Thesis, Cornell University. pp. ii.spa
dc.relation.referencesRanjay, K., 2017, Computer vision: Foundation and Applications, first edition. Stanford University, Stanford, 17pp.spa
dc.relation.referencesRider, M., 2000, The geological interpretation of well logs, second edition. Rider – French Consulting Ltd., Sutherland, 67pp.spa
dc.relation.referencesRoy, A., Perfect, E., Dunne, W., Mackay, L., 2007, Fractal characterization of fracture networks. An improved box-counting technique. Journal of Geophysical Research, (112), 1-2pp. https://doi.org/10.1029/2006JB004582spa
dc.relation.referencesRussell, S., Norvig, P., 2010, Artificial intelligence a modern approach, third edition. Prentice Hall, Upper Saddle River, 698-764pp.spa
dc.relation.referencesSadeghi, B., Madeni, N., Carranza, E., 2014, Combination of geostatistical simulation and fractal modeling for mineral resource classification. Journal of Geochemical Exploration, 149(10), 59-73pp. http://dx.doi.org/10.1016/j.gexplo.2014.11.007spa
dc.relation.referencesSchlager, W., 2004, Fractal nature of stratigraphic sequences. GeoScience World, 32(3), 185-188pp. https://doi.org/10.1130/G20253.1spa
dc.relation.referencesSchlumberger, 2013, FMI-HD High-definition formation microimager. Schlumberger brochure, 4pp.spa
dc.relation.referencesSchlumberger, 1999, Geologic Applications of Dipmeter and Borehole Images. Schlumberger Educational Services, 31-322pp.spa
dc.relation.referencesSchott, M., 2019, Random forest algorithm for machine learning. Medium, 25 April 2019, https://medium.com/capital-one-tech/random-forest-algorithm-for-machine-learning-c4b2c8cc9feb (accessed 10 April 2020).spa
dc.relation.referencesShapiro, L., Stockman, G., 2001, Computer Vision. The University of Washington, 107-332pp.spa
dc.relation.referencesSingh, H., 2018, Understanding Gradient Boosting Machines. Towards Data Science, 3 November 2018, https://towardsdatascience.com/understanding-gradient-boosting-machines-9be756fe76ab (accessed 8 June 2020).spa
dc.relation.referencesSingh, V., 2019, Model-based feature importance. Towards data sciences, 3 January 2019, https://towardsdatascience.com/model-based-feature-importance-d4f6fb2ad403 (accessed 31 July 2020).spa
dc.relation.referencesTan, T., Stainbach M., Kumar, V., 2006, Introduction to data mining, first edition. Pearson Addison-Wesley, Boston, 297-598pp.spa
dc.relation.referencesTelea, A., 2004, An image inpainting technique based on the fast marching method. Journal of Graphic Tools, 9 (1), 25-36pp. https://doi.org/10.1080/10867651.2004.10487596spa
dc.relation.referencesTurcotte, D., 1997, Fractal and chaos in geology and geophysics, second edition. Cambridge University, Cambridge, 166pp.spa
dc.relation.referencesTwiss, R., Moores, E., 2006, Structural geology, second edition. W. H. Freeman and Company, New York, 50pp.spa
dc.relation.referencesVasiloudis, T., 2019, Block-distributed Gradient Boosted Trees. Theodore Vasiloudis, 26 August 2019, http://tvas.me/articles/2019/08/26/Block-Distributed-Gradient-Boosted-Trees.html (accessed 15 November 2020).spa
dc.relation.referencesVivas, M., 1992, A techniques for inter well description by applying geostatistic and fractal geometry methods to well logs and core data. Doctoral dissertation, University of Oklahoma, 16pp.spa
dc.relation.referencesWang, W., Liao, H., Huang, Y., 2007, Rock fractured tracing based on image processing and SVM. Third International Conference of Natural Computation, 1, 632-635pp. 10.1109/ICNC.2007.643spa
dc.relation.referencesWeatherford, 2014, Compact microimager. Weatherford brochure, 1-4pp.spa
dc.rights.accessrightsinfo:eu-repo/semantics/openAccessspa
dc.rights.licenseReconocimiento 4.0 Internacionalspa
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/spa
dc.subject.ddc550 - Ciencias de la tierraspa
dc.subject.ddc500 - Ciencias naturales y matemáticasspa
dc.subject.ddc000 - Ciencias de la computación, información y obras generalesspa
dc.subject.proposalOil and gas wellseng
dc.subject.proposalMachine learningeng
dc.subject.proposalFractal dimensioneng
dc.subject.proposalLacunarityeng
dc.subject.proposalBorehole resistivity imagingeng
dc.subject.proposalGeologic planeseng
dc.subject.proposalautomatic pickingeng
dc.subject.proposalAutomatic dip classificationeng
dc.subject.proposalHydrocarbon reservoirseng
dc.subject.proposalAprendizaje automáticospa
dc.subject.proposalDimensión fractalspa
dc.subject.proposalLagunaridadspa
dc.subject.proposalImágenes resistivas de pozospa
dc.subject.proposalPlanos geológicosspa
dc.subject.proposalClasificación automática de buzamientosspa
dc.subject.proposalYacimientos de hidrocarburosspa
dc.titleMachine learning and fractal attributes applied to automatic detection and classification of geologic planes in resistivity image logseng
dc.title.translatedAprendizaje automático y atributos fractales aplicados a la detección y clasificación automática de planos geológicos en registros de imágenes resistivasspa
dc.typeTrabajo de grado - Doctoradospa
dc.type.coarhttp://purl.org/coar/resource_type/c_db06spa
dc.type.coarversionhttp://purl.org/coar/version/c_ab4af688f83e57aaspa
dc.type.contentTextspa
dc.type.driverinfo:eu-repo/semantics/doctoralThesisspa
dc.type.redcolhttp://purl.org/redcol/resource_type/TDspa
dc.type.versioninfo:eu-repo/semantics/acceptedVersionspa
dcterms.audience.professionaldevelopmentAdministradoresspa
dcterms.audience.professionaldevelopmentBibliotecariosspa
dcterms.audience.professionaldevelopmentConsejerosspa
dcterms.audience.professionaldevelopmentEstudiantesspa
dcterms.audience.professionaldevelopmentGrupos comunitariosspa
dcterms.audience.professionaldevelopmentInvestigadoresspa
dcterms.audience.professionaldevelopmentMaestrosspa
dcterms.audience.professionaldevelopmentMedios de comunicaciónspa
dcterms.audience.professionaldevelopmentPadres y familiasspa
dcterms.audience.professionaldevelopmentPersonal de apoyo escolarspa
dcterms.audience.professionaldevelopmentProveedores de ayuda financiera para estudiantesspa
dcterms.audience.professionaldevelopmentPúblico generalspa
dcterms.audience.professionaldevelopmentReceptores de fondos federales y solicitantesspa
dcterms.audience.professionaldevelopmentResponsables políticosspa
oaire.accessrightshttp://purl.org/coar/access_right/c_abf2spa

Archivos

Bloque original

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
389194.2021.pdf
Tamaño:
7.3 MB
Formato:
Adobe Portable Document Format
Descripción:
Tesis de Doctorado en Geociencias

Bloque de licencias

Mostrando 1 - 1 de 1
Cargando...
Miniatura
Nombre:
license.txt
Tamaño:
3.98 KB
Formato:
Item-specific license agreed upon to submission
Descripción: