Расширенный поиск
Методика выделения трещин на основе данных микроимиджера с использованием методов машинного обучения
Московский физико-технический институт национальный исследовательский университет
Журнал: Сейсмические приборы
Том: 60
Номер: 2
Год: 2024
Страницы: 53-66
УДК: 550.8.053
DOI: 10.21455/si2024.2-4
Показать библиографическую ссылку
Архипов Н.Д. Методика выделения трещин на основе данных микроимиджера с использованием методов машинного обучения
// Сейсмические приборы. 2024. Т. 60. № 2. С. 53-66. DOI: 10.21455/si2024.2-4
@article{АрхиповМетодика2024,
author = "Архипов, Н. Д.",
title = "Методика выделения трещин на основе данных микроимиджера с использованием методов машинного обучения
",
journal = "Сейсмические приборы",
year = 2024,
volume = "60",
number = "2",
pages = "53-66",
doi = "10.21455/si2024.2-4",
language = "Russian"
}
Скопировать ссылку в формате ГОСТ
Скопировать ссылку BibTex
Файлы:
Ключевые слова: компьютерное зрение, обнаружение границ, нейросети, машинное обучение, электрический микроимиджер, ГИС, глубокое обучение
Аннотация: Рассматривается разработка методики автоматического выделения естественной слоисто-сти и трещиноватости при помощи методов машинного обучения. Предложенная методика включает в себя процедуры предобработки, выделения границ и постобработки. Эффектив-ность работы алгоритма была количественно показана на тестовых данных, а предложен-ный алгоритм был оценен на качественном уровне на реальных данных.
Список литературы: Дубиня Н.В. Обзор скважинных методов изучения напряженного состояния верхних слоев земной коры // Физика Земли. 2019. № 2. С.137–155. https://doi.org/10.31857/S0002-333720192137-155
Дубиня Н.В., Тихоцкий С.А. О методе решения обратной задачи восстановления напряжён-но-деформированного состояния массива горных пород по данным о естественной трещиноватости // Физика Земли. 2022. № 4. С.113–134. https://doi.org/10.31857/S0002333722040020
Amari S. Backpropagation and stochastic gradient descent method // Neurocomputing. 1993. V. 5, Iss. 4–5. P.185–196. https://doi.org/10.1016/0925-2312(93)90006-O
Assous S., Elkington P., Whetton J. Microresistivity borehole image inpainting // Geophysics. 2014. V. 79, Iss. 2. P.D31–D39. https://doi.org/10.1190/geo2013-0188.1
Dias L.O., Bom C.R., Faria E.L., Blanco Valentín M., Duarte Correia M., de Albuquerque Már-cio P., de Albuquerque Marcelo P., Coelho J.M. Automatic detection of fractures and breakouts patterns in acoustic borehole image logs using fast-region convolutional neural networks // J. Petrol. Sci. Eng. 2020. V. 191. Art. 107099. 11 p. https://doi.org/10.1016/j.petrol.2020.107099
Eaton B.A. The equation for geopressure prediction from well logs // Fall Meeting of the Society of Petroleum Engineers of AIME, Dallas, TX, 28 September – 1 October 1975. Paper No. SPE-5544-MS. https://doi.org/10.2118/5544-MS
Gaillot Ph., Brewer T., Pezard Ph.A., Yeh E.-Ch. Borehole imaging tools – Principles and appli-cations // Scientific Drilling. 2007. V. 5. P.1–4. https://doi.org/10.2204/iodp.sd.5.07S1.2007
Hilpert M., Miller C.T. Pore-morphology-based simulation of drainage in totally wetting porous media // Adv. Water Resources. 2001. V. 24, Iss. 3–4. P.243–255. https://doi.org/10.1016/S0309-1708(00)00056-7
Kingma D.P., Ba J.L. Adam: A method for stochastic optimization // arXiv. 2014. Paper No. 1412.6980. https://doi.org/10.48550/arXiv.1412.6980
Lagae A. Lefebvre S., Cook R., DeRose T., Drettakis G., Ebert D.S., Lewis J.P., Perlin K., Zwick-er M. A survey of procedural noise functions // Computer Graphics Forum. 2010. V. 29, Iss. 8. P.2579–2600. https://doi.org/10.1111/j.1467-8659.2010.01827.x
Li X.-N., Shen J.-S., Yang W.-Y., Li Zh.-L. Automatic fracture-vug identification and extraction from electric imaging logging data based on path morphology // Petrol. Sci. 2019. V. 16, Iss. 1. P.58–76. https://doi.org/10.1007/s12182-018-0282-6
Li X., Shen J., Wei J., Li J., Yang X., Wang K. Electric imaging fusion technique combining sin-gular spectrum interpolation with mathematical morphology in Amu Darya Basin // 82nd EAGE Annual Conference & Exhibition, Amsterdam, 18–21 October 2021. EAGE, 2021. P.1–5. https://doi.org/10.3997/2214-4609.202112438
Lorensen W.E., Cline H.E. Marching cubes: A high resolution 3D surface construction algorithm // ACM SIGGRAPH Computer Graphics. 1987. V. 21, Iss. 4. P.163–169. https://doi.org/10.1145/37402.37422
Martin M.A., Wakefield M., MacPhail M.K., Pearce T., Edwards H.E. Sedimentology and stratig-raphy of an intra-cratonic basin coal seam gas play: Walloon Subgroup of the Surat Basin, eastern Australia // Petrol. Geosci. 2013. V. 19, N 1. P.21–38. https://doi.org/10.1144/petgeo2011-043
Shafiabadi M., Kamkar-Rouhani A., Ghavami-Riabi S.R., Kahoo A.R., Tokhmechi B. Identifica-tion of reservoir fractures on FMI image logs using Canny and Sobel edge detection algo-rithms // Oil & Gas Science and Technology – Rev. IFP Energies nouvelles. 2021. V. 76, N 10. P.1–11. https://doi.org/10.2516/ogst/2020086
Shreyamsha Kumar B.K. Image denoising based on non-local means filter and its method noise thresholding // Signal Image Video Proc. 2013. V. 7, Iss. 6. P.1211–1227. https://doi.org/10.1007/s11760-012-0389-y
Soria X., Riba E., Sappa A. Dense extreme inception network: Towards a robust CNN model for edge detection // Proc. IEEE/CVF winter conference on applications of computer vision, Snowmass, CO, 01–05 March 2020. P.1923–1932. https://doi.org/10.1109/WACV45572.2020.9093290
Sun Q., Su N., Gong F., Du Q. Blank strip filling for logging electrical imaging based on mul-tiscale generative adversarial network // Processes. 2023. V. 11, Iss. 6. Art. 1709. 17 p. https://doi.org/10.3390/pr11061709
Well Completion Report PL 276, QGC ROSS 19. URL: https://geoscience.data.qld.gov.au/data/report/cr075532 [Access date: 30.07.2024].
Zajac B.J., Stock J.M. Using borehole breakouts to constrain the complete stress tensor: Results from the Sijan Deep Drilling Project and offshore Santa Maria Basin, California // J. Ge-ophys. Res. Solid Earth. 1997. V. 102, Iss. B5. P.10083–10100. https://doi.org/10.1029/96JB03914
Дубиня Н.В., Тихоцкий С.А. О методе решения обратной задачи восстановления напряжён-но-деформированного состояния массива горных пород по данным о естественной трещиноватости // Физика Земли. 2022. № 4. С.113–134. https://doi.org/10.31857/S0002333722040020
Amari S. Backpropagation and stochastic gradient descent method // Neurocomputing. 1993. V. 5, Iss. 4–5. P.185–196. https://doi.org/10.1016/0925-2312(93)90006-O
Assous S., Elkington P., Whetton J. Microresistivity borehole image inpainting // Geophysics. 2014. V. 79, Iss. 2. P.D31–D39. https://doi.org/10.1190/geo2013-0188.1
Dias L.O., Bom C.R., Faria E.L., Blanco Valentín M., Duarte Correia M., de Albuquerque Már-cio P., de Albuquerque Marcelo P., Coelho J.M. Automatic detection of fractures and breakouts patterns in acoustic borehole image logs using fast-region convolutional neural networks // J. Petrol. Sci. Eng. 2020. V. 191. Art. 107099. 11 p. https://doi.org/10.1016/j.petrol.2020.107099
Eaton B.A. The equation for geopressure prediction from well logs // Fall Meeting of the Society of Petroleum Engineers of AIME, Dallas, TX, 28 September – 1 October 1975. Paper No. SPE-5544-MS. https://doi.org/10.2118/5544-MS
Gaillot Ph., Brewer T., Pezard Ph.A., Yeh E.-Ch. Borehole imaging tools – Principles and appli-cations // Scientific Drilling. 2007. V. 5. P.1–4. https://doi.org/10.2204/iodp.sd.5.07S1.2007
Hilpert M., Miller C.T. Pore-morphology-based simulation of drainage in totally wetting porous media // Adv. Water Resources. 2001. V. 24, Iss. 3–4. P.243–255. https://doi.org/10.1016/S0309-1708(00)00056-7
Kingma D.P., Ba J.L. Adam: A method for stochastic optimization // arXiv. 2014. Paper No. 1412.6980. https://doi.org/10.48550/arXiv.1412.6980
Lagae A. Lefebvre S., Cook R., DeRose T., Drettakis G., Ebert D.S., Lewis J.P., Perlin K., Zwick-er M. A survey of procedural noise functions // Computer Graphics Forum. 2010. V. 29, Iss. 8. P.2579–2600. https://doi.org/10.1111/j.1467-8659.2010.01827.x
Li X.-N., Shen J.-S., Yang W.-Y., Li Zh.-L. Automatic fracture-vug identification and extraction from electric imaging logging data based on path morphology // Petrol. Sci. 2019. V. 16, Iss. 1. P.58–76. https://doi.org/10.1007/s12182-018-0282-6
Li X., Shen J., Wei J., Li J., Yang X., Wang K. Electric imaging fusion technique combining sin-gular spectrum interpolation with mathematical morphology in Amu Darya Basin // 82nd EAGE Annual Conference & Exhibition, Amsterdam, 18–21 October 2021. EAGE, 2021. P.1–5. https://doi.org/10.3997/2214-4609.202112438
Lorensen W.E., Cline H.E. Marching cubes: A high resolution 3D surface construction algorithm // ACM SIGGRAPH Computer Graphics. 1987. V. 21, Iss. 4. P.163–169. https://doi.org/10.1145/37402.37422
Martin M.A., Wakefield M., MacPhail M.K., Pearce T., Edwards H.E. Sedimentology and stratig-raphy of an intra-cratonic basin coal seam gas play: Walloon Subgroup of the Surat Basin, eastern Australia // Petrol. Geosci. 2013. V. 19, N 1. P.21–38. https://doi.org/10.1144/petgeo2011-043
Shafiabadi M., Kamkar-Rouhani A., Ghavami-Riabi S.R., Kahoo A.R., Tokhmechi B. Identifica-tion of reservoir fractures on FMI image logs using Canny and Sobel edge detection algo-rithms // Oil & Gas Science and Technology – Rev. IFP Energies nouvelles. 2021. V. 76, N 10. P.1–11. https://doi.org/10.2516/ogst/2020086
Shreyamsha Kumar B.K. Image denoising based on non-local means filter and its method noise thresholding // Signal Image Video Proc. 2013. V. 7, Iss. 6. P.1211–1227. https://doi.org/10.1007/s11760-012-0389-y
Soria X., Riba E., Sappa A. Dense extreme inception network: Towards a robust CNN model for edge detection // Proc. IEEE/CVF winter conference on applications of computer vision, Snowmass, CO, 01–05 March 2020. P.1923–1932. https://doi.org/10.1109/WACV45572.2020.9093290
Sun Q., Su N., Gong F., Du Q. Blank strip filling for logging electrical imaging based on mul-tiscale generative adversarial network // Processes. 2023. V. 11, Iss. 6. Art. 1709. 17 p. https://doi.org/10.3390/pr11061709
Well Completion Report PL 276, QGC ROSS 19. URL: https://geoscience.data.qld.gov.au/data/report/cr075532 [Access date: 30.07.2024].
Zajac B.J., Stock J.M. Using borehole breakouts to constrain the complete stress tensor: Results from the Sijan Deep Drilling Project and offshore Santa Maria Basin, California // J. Ge-ophys. Res. Solid Earth. 1997. V. 102, Iss. B5. P.10083–10100. https://doi.org/10.1029/96JB03914
