Published

2018-04-01

Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging

Identificación Automática de Litologías Calcáreas Utilizando Máquinas de Vector de Soporte, Registros de Pozo y Dimensión Fractal de Imágenes Eléctricas de Pozo

DOI:

https://doi.org/10.15446/esrj.v22n2.68320

Keywords:

machine learning, support vector machines, borehole logs, image logs, fractal dimension, calcareous lithologies, Catatumbo Basin. (en)
aprendizaje de máquinas, máquinas de soporte vectorial, registros de pozo, registro de imágenes, dimensión fractal, litologías calcáreas, Cuenca de Catatumbo. (es)

Downloads

Authors

  • Jorge Alberto Leal Universidad Nacional de Colombia
  • Luis Hernan Ochoa Ph.D. Professor, Geosciences Department, Science Faculty, Universidad Nacional de Colombia, Bogota.
  • Carmen Cecilia Contreras Principal Geologist, PTS-DFW. Schlumberger Technology

In this research algorithms of support vector machine (SVM) and a logic function were applied to identify automatically sections of carbonate rocks in wells located in the former Barco Concession, Catatumbo Basin - Colombia. During training stages the SVMs use neutron, photoelectric factor and gamma ray logs as input; also mean and variance of resistivity acquired for image tool and fractal dimension of resistive images. The first SVM employs in the training stage intervals manually interpreted of fossiliferous limestone, performed by a specialized geologist integrating information of core-logs correlation of a pilot well; afterwards, in classification stages, this SVM automatically recognizes intervals with fossiliferous limestone only using logs data of any well of the field. The second SVM was also trained with nuclear logs, resistivity and fractal dimension, but in this case, with information of intervals composed of calcareous shales interbedded with limestone, recognizing automatically these rock associations during classification stage without interpretations of a geologist as input data. Additionally, a logic function was applied to intervals with photoelectric factor ≥ 4 and all sections not classified by the SVMs were grouped as laminated calcareous rocks. The SVMs and logic function show accuracy of 98.76 %, 94.02 % and 94.60 % respectively in six evaluated wells and might be applied to other wells in the field that have the same dataset. This methodology is highly dependent of the data quality and all intervals affected by bad borehole condition have to be removed prior its application in order to avoid wrong interpretations. Finally, the whole model has to be recalibrated to be applied in other fields of the basin.

En esta investigación algoritmos de máquinas de vector de soporte (MVS) y una función lógica fueron aplicados para identificar automáticamente secciones con rocas carbonáticas en pozos ubicados en la antigua Concesión Barco, Cuenca de Catatumbo - Colombia. Durante las etapas de clasificación las MVS utilizan registros de neutrón, factor fotoeléctrico y rayos gamma como entrada; también media y varianza de la resistividad adquirida por herramientas de imágenes y dimensión fractal de imágenes resistivas. La primera MVS emplea en la etapa de entrenamiento intervalos manualmente interpretados de calizas fosilíferas, realizado por un geólogo especialista integrando información de correlación núcleo-registro de un pozo piloto; posteriormente, en etapas de clasificación, esta MVS automáticamente reconoce intervalos con calizas fosilíferas utilizando solamente datos de registros de cualquier pozo del campo. La segunda MVS fue también entrenada con registros nucleares, resistivos y dimensión fractal, pero en este caso, con información de intervalos compuestos de lutitas calcáreas intercaladas con calizas, reconociendo automáticamente estas asociaciones de rocas durante la etapa de clasificación sin requerir interpretaciones de un geólogo como dato de entrada. Adicionalmente, se aplicó una función lógica a intervalos con factor fotoeléctrico ≥ 4 y todas las secciones no clasificados por las MVS fueron agrupadas como rocas calcáreas laminadas. Las MVS y la función lógica mostraron precisiones de 98.76%, 94.02% y 94.60% respectivamente en seis pozos evaluados y podrían ser aplicado a otros pozos del campo que tengan el mismo conjunto de datos. Esta metodología es altamente dependiente de la calidad de los datos, por consiguiente, todos los intervalos afectados por malas condiciones del pozo tienen que ser removidos antes de ser aplicados para evitar interpretaciones erróneas. Finalmente, todo el modelo debe ser recalibrado para ser aplicado en otros campos de la cuenca.

References

AIP-Asesoría en Ingeniería de Petróleos. (2009). Caracterización de Yacimientos, Cuenca de Catatumbo-Colombia. Bogotá, Colombia. 6-18.

Asquith, G., & Krygowski, D. (2004). Basic Well Log Analysis. AAPG methods in exploration Series 16, Tulsa. The United States of America. 30-40.

Barrero, D., Pardo, A., Vargas. C, & Martinez, J. (2007). Colombian Sedimentary Basins: Nomenclature, Boundaries and Petroleum Geology, a New Proposal. Agencia Nacional de Hidrocarburos, Bogotá, Colombia, 32-60. http://www.anh.gov.co/Informacion- Geologica-y-Geofisica/Cuencas-sedimentarias/Documents/ colombian_sedimentary_basins.pdf

Branquet, Y., Cheilletz, A., Cobbold, P. R., Baby, P., Laumonier, B., & Giuliani, G. (2002). Andean deformation and rift inversion, eastern edge of Cordillera Oriental (Guateque-Medina area), Colombia. Journal of South America Earth Sciences, 15(4) 391-407. https://doi.org/10.1016/S0895-9811(02)00063-9

Ecopetrol. (2012). Informe Técnico Anual Contractual Año 2012. Gerencia Catatumbo Orinoquia, Vicepresidencia de Producción, Bogotá, Colombia. 5-20.

Gonzales, M., Mier, R., Cruz, L., & Vásquez, M. (2009). Informe ejecutivo evaluación del potencial hidrocarburífero de las cuencas colombianas. Contrato administrativo No. 2081941, Fondo Financiero de Proyectos de Desarrollo – Universidad Industrial de Santander – Agencia Nacional de Hidrocarburos, Bucaramanga, Colombia. 5-6.

KNIME 2.7.4 (2013). The Konstanz Information Miner. http://www. kanime.com (last accessed October 2017).

Leal, J. (2014). Identificación y modelado de fracturas naturales en pozos de un yacimiento de hidrocarburos ubicado en la Cuenca de Catatumbo, Departamento Norte de Santander – Colombia, utilizando registros de imagénes resistivas y datos de dimensión fractal. M.Sc. Thesis, Department of Geoscience, Universidad Nacional de Colombia, Bogotá, Colombia. http://www.bdigital. unal.edu.co/12849/

Leal, J., Ochoa, L. & García, J. (2016). Identification of natural fractures using resistive image logs, fractal dimension and support vector machines. Ingeniería e Investigación, 36(3), 125-132. https://doi.org/10.15446/ing.investig.v36n3.56198

Mandelbrot, B. (1983). The fractal geometry of nature. W. H. Freeman and Company, New York, The United States of America. 14-15.

Notestein, F., Hubman, C., & Bowler, J. (1944). Geology of The Barco Concession, Republic of Colombia, South America. Bulletin of The Geological Society of America, (55)1173-1183.

Ochoa, L. Niño, L. & Vargas, C. (2017). Fast magnitude determination using a single seismological station record implementing machine learning techniques. Geodesy and Geodynamics, 1-8. https://doi.org/10.1016/j.geog.2017.03.010

Rider, M. (2000). The geological interpretation of well logs second edition. Rider – French Consulting Ltd, Sutherland, The United Kingdom. 126-128.

SGC-Servicio Geológico Colombiano. (2015). Plancha 78 - Puerto Santander. Memoria Explicativa. Medellín, Colombia.

Taylor, J., & Cristianini, N. (2004). Kernel methods for pattern analysis. Cambridge University Press, New York, The United States of America. 25-26.

Tan, P., Steinbach, M., & Kumar, V. (2006). Introduction to data mining. Pearson Addison-Wesley, Boston, The United States of America. 256-276.

Toussaint, J. F. (1995). Evolución geológica de Colombia–Triásico y Jurásico. Universidad Nacional de Colombia, Medellín, Colombia. (1) 94.

How to Cite

APA

Leal, J. A., Ochoa, L. H. and Contreras, C. 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), 75–82. https://doi.org/10.15446/esrj.v22n2.68320

ACM

[1]
Leal, J.A., Ochoa, L.H. and Contreras, C.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 (Apr. 2018), 75–82. DOI:https://doi.org/10.15446/esrj.v22n2.68320.

ACS

(1)
Leal, J. A.; Ochoa, L. H.; Contreras, C. C. Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging. Earth sci. res. j. 2018, 22, 75-82.

ABNT

LEAL, J. A.; OCHOA, L. H.; CONTRERAS, C. C. Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging. Earth Sciences Research Journal, [S. l.], v. 22, n. 2, p. 75–82, 2018. DOI: 10.15446/esrj.v22n2.68320. Disponível em: https://revistas.unal.edu.co/index.php/esrj/article/view/68320. Acesso em: 21 nov. 2024.

Chicago

Leal, Jorge Alberto, Luis Hernan Ochoa, and Carmen Cecilia Contreras. 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):75-82. https://doi.org/10.15446/esrj.v22n2.68320.

Harvard

Leal, J. A., Ochoa, L. H. and Contreras, C. 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), pp. 75–82. doi: 10.15446/esrj.v22n2.68320.

IEEE

[1]
J. A. Leal, L. H. Ochoa, and C. C. Contreras, “Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging”, Earth sci. res. j., vol. 22, no. 2, pp. 75–82, Apr. 2018.

MLA

Leal, J. A., L. H. Ochoa, and C. C. Contreras. “Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging”. Earth Sciences Research Journal, vol. 22, no. 2, Apr. 2018, pp. 75-82, doi:10.15446/esrj.v22n2.68320.

Turabian

Leal, Jorge Alberto, Luis Hernan Ochoa, and Carmen Cecilia Contreras. “Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging”. Earth Sciences Research Journal 22, no. 2 (April 1, 2018): 75–82. Accessed November 21, 2024. https://revistas.unal.edu.co/index.php/esrj/article/view/68320.

Vancouver

1.
Leal JA, Ochoa LH, Contreras CC. Automatic Identification of Calcareous Lithologies Using Support Vector Machines, Borehole Logs and Fractal Dimension of Borehole Electrical Imaging. Earth sci. res. j. [Internet]. 2018 Apr. 1 [cited 2024 Nov. 21];22(2):75-82. Available from: https://revistas.unal.edu.co/index.php/esrj/article/view/68320

Download Citation

CrossRef Cited-by

CrossRef citations8

1. Luis Hernán Ochoa Gutierrez, Carlos Alberto Vargas Jiménez, Luis Fernando Niño Vásquez. (2019). Fast estimation of earthquake arrival azimuth using a single seismological station and machine learning techniques. Earth Sciences Research Journal, 23(2), p.103. https://doi.org/10.15446/esrj.v23n2.70581.

2. Anas Mohamed Abaker Babai, Olugbenga Ajayi Ehinola, Omer Ibrahim Fadul Abul Gebbayin, Mohammed Abdalla Elsharif Ibrahim. (2024). Clastic facies classification using machine learning-based algorithms: A case study from Rawat Basin, Sudan. Energy Geoscience, , p.100353. https://doi.org/10.1016/j.engeos.2024.100353.

3. Cancan Liu, Xigui Zheng, Lu Yang, Peng Li, Niaz Muhammad Shahani, Cong Wang, Xiaowei Guo. (2024). Automatic identification of rock formation interface based on borehole imaging. Energy Sources, Part A: Recovery, Utilization, and Environmental Effects, 46(1), p.493. https://doi.org/10.1080/15567036.2021.1903121.

4. Hao Leng, Huoyin Lv, Fenglei Han, Fabo Liu, Tao Liu. (2021). Permanent magnet treatment technology for crystal blockage of tunnel drainage pipes. Desalination and Water Treatment, 243, p.211. https://doi.org/10.5004/dwt.2021.27795.

5. Tie Yan, Rui Xu, Shi-Hui Sun, Zhao-Kai Hou, Jin-Yu Feng. (2024). A real-time intelligent lithology identification method based on a dynamic felling strategy weighted random forest algorithm. Petroleum Science, 21(2), p.1135. https://doi.org/10.1016/j.petsci.2023.09.011.

6. Pedro Ribeiro Mendes, Soroor Salavati, Oscar Linares, Maiara Moreira Gonçalves, Marcelo Ferreira Zampieri, Vitor Hugo de Sousa Ferreira, Manuel Castro, Rafael de Oliveira Werneck, Renato Moura, Elayne Morais, Ahmed Esmin, Leopoldo Lusquino, Denis José Schiozer, Alexandre Ferreira, Alessandra Davólio, Anderson Rocha. (2024). Rock-type classification: A (critical) machine-learning perspective. Computers & Geosciences, 193, p.105730. https://doi.org/10.1016/j.cageo.2024.105730.

7. Jorge Alberto Leal, Luis Hernan Ochoa Gutierrez, Sergio Francisco Acosta Lenis. (2023). Computer vision techniques applied to automatic detection of sinusoids in borehole resistivity imaging – A comparison with the MSD method. Earth Sciences Research Journal, 27(2), p.139. https://doi.org/10.15446/esrj.v27n2.101556.

8. Aiting Wang, Shuyu Zhao, Kai Xie, Chang Wen, Hong-ling Tian, Jian-Biao He, Wei Zhang. (2024). Attention mechanism-enhanced graph convolutional neural network for unbalanced lithology identification. Scientific Reports, 14(1) https://doi.org/10.1038/s41598-024-64871-2.

Dimensions

PlumX

Article abstract page views

709

Downloads

Download data is not yet available.