본문 바로가기
KERD
논문KCI 등재

A study on estimating the interlayer boundary of the subsurface using a artificial neural network with electrical impedance tomography

김경연|Anil Kumar Khambampati|Sunam Kumar Sharma
한국전기전자학회 (Institute of Korean Electrical and Electronics Engineers)|2021.12|전기전자학회논문지 (Journal of IKEEE)|제25권 제4호|pp. 650-663|DOI 10.7471/ikeee.2021.25.4.650

0

조회

0

다운로드

0

인용

0

참고문헌

키워드

artificial neural networkElectrical impedance tomographyfront pointssubsurfaceinterlayer estimation
주제분류전자/정보통신공학

초록

Subsurface topology estimation is an important factor in the geophysical survey. Electrical impedancetomography is one of the popular methods used for subsurface imaging. The EIT inverse problem is highlynonlinear and ill-posed; therefore, reconstructed conductivity distribution suffers from low spatial resolution. Thesubsurface region can be approximated as piece-wise separate regions with constant conductivity in each region;therefore, the conductivity estimation problem is transformed to estimate the shape and location of the layerboundary interface. Each layer interface boundary is treated as an open boundary that is described using frontpoints. The subsurface domain contains multi-layers with very complex configurations, and, in such situations,conventional methods such as the modified Newton Raphson method fail to provide the desired solution. Therefore, in this work, we have implemented a 7-layer artificial neural network (ANN) as an inverse problemalgorithm to estimate the front points that describe the multi-layer interface boundaries. An ANN model consistingof input, output, and five fully connected hidden layers are trained for interlayer boundary reconstruction usingtraining data that consists of pairs of voltage measurements of the subsurface domain with three-layerconfiguration and the corresponding front points of interface boundaries. The results from the proposed ANNmodel are compared with the gravitational search algorithm (GSA) for interlayer boundary estimation, and theresults show that ANN is successful in estimating the layer boundaries with good accuracy.

Abstract

Subsurface topology estimation is an important factor in the geophysical survey. Electrical impedancetomography is one of the popular methods used for subsurface imaging. The EIT inverse problem is highlynonlinear and ill-posed; therefore, reconstructed conductivity distribution suffers from low spatial resolution. Thesubsurface region can be approximated as piece-wise separate regions with constant conductivity in each region;therefore, the conductivity estimation problem is transformed to estimate the shape and location of the layerboundary interface. Each layer interface boundary is treated as an open boundary that is described using frontpoints. The subsurface domain contains multi-layers with very complex configurations, and, in such situations,conventional methods such as the modified Newton Raphson method fail to provide the desired solution. Therefore, in this work, we have implemented a 7-layer artificial neural network (ANN) as an inverse problemalgorithm to estimate the front points that describe the multi-layer interface boundaries. An ANN model consistingof input, output, and five fully connected hidden layers are trained for interlayer boundary reconstruction usingtraining data that consists of pairs of voltage measurements of the subsurface domain with three-layerconfiguration and the corresponding front points of interface boundaries. The results from the proposed ANNmodel are compared with the gravitational search algorithm (GSA) for interlayer boundary estimation, and theresults show that ANN is successful in estimating the layer boundaries with good accuracy.

참고문헌 (51)

  1. P. Kearey, "An introduction to geophysical exploration" (2002), John Wiley & Sons
  2. R. Philp, "Surface geochemical methods used for oil and gas prospecting—a review", Journal of Geochemical Exploration, 17(1), pp.1~34 (1982)[DOI]
  3. R. Saad, "Groundwater detection in alluvium using 2-d electrical resistivity tomography (ert)", Electronic Journal of Geotechnical Engineering, 17, pp.369~376 (2012)
  4. D. B. Hoover, "Geophysical methods in exploration and mineral environmental investigations", Preliminary compilation of descriptive geoenvironmental mineral deposit models: USGS Open-File Report, 95(831), pp.1~27 (1995)
  5. N. Abdullahi, "Application of integrated geophysical techniques in the investigation of groundwater contamination:A case study of municipal solid waste leachate", Ozean Journal of applied sciences, 4(1), pp.7~25 (2011)
  6. G. S. Baker, "An introduction to ground penetrating radar (gpr)", Special Papers-Geological Society of America, 432(1) (2007)[DOI]
  7. W. Daily, "Electrical resistivity tomography of vadose water movement", Water Resources Research, 28(5), pp.1429~1442 (1992)[DOI]
  8. K. Sudha, "Soil characterization using electrical resistivity tomography and geotechnical investigations", Journal of Applied Geophysics, 67(1), pp.74~79 (2009)[DOI]
  9. T. J. Katsube, "Detection and Remediation Technologies for Mines and Minelike Targets IX, vol. 5415", pp.691~704 (2004), International Society for Optics and Photonics
  10. T. J. Katsube, "Detection and Remediation Technologies for Mines and Minelike Targets VIII, vol.5089", pp.1219~1230 (2003), International Society for Optics and Photonics
  11. W. Menke, "The resolving power of crossborehole tomography", Geophysical Research Letters, 11(2), pp.105~108 (1984)[DOI]
  12. M. Perri, "A saline tracer test monitored via both surface and cross-borehole electrical resistivity tomography : Comparison of time-lapse results", Journal of Applied Geophysics, 79, pp.6~16 (2012)[DOI]
  13. J. G. Webster, "Electrical impedance tomography" (1990), Taylor & Francis Group
  14. M. Cheney, "Electrical impedance tomography", SIAM review, 41(1), pp.85~101 (1999)[DOI]
  15. G. D’Antona, "Active monitoring apparatus for underground pollutant detection based on electrical impedance tomography", IMTC, 2002, pp.1 (2002), 577~579
  16. R. Stacey, "Electrical impedance tomography (eit) technique for real-time saturation monitoring", SPE Annual Technical Conference and Exhibition. Society of Petroleum Engineers (2006)
  17. A. Adler, "Greit: a unifed approach to 2d linear eit reconstruction of lung images", Physiological measurement, 30(6), pp.S35~ (2009)[DOI]
  18. D. Holder, "Electrical impedance tomography(eit)of brain function", Brain Topography, 5(2), pp.87~93 (1992)[DOI]
  19. E. K. Murphy, "Phantom experiments using soft-prior regularization eit for breast cancer imaging", Physiological measurement, 38(6), pp.1262~ (2017)[DOI]
  20. A. P. Bagshaw, "Electrical impedance tomography of human brain function using reconstruction algorithms based on the fnite element method", NeuroImage, 20(2), pp.752~764 (2003)[DOI]
  21. G. Xu, "3-d electrical impedance tomography forward problem with fnite element method", IEEE transactions on magnetics, 41(5), pp.1832~1835 (2005)[DOI]
  22. E. Woo, "Finite-element method in electrical impedance tomography", Medical and Biological Engineering and Computing, 32(5), pp.530~536 (1994)[DOI]
  23. J. C. de Munck, "The boundary element method in the forward and inverse problem of electrical impedance tomography", IEEE transactions on Biomedical Engineering, 47(6), pp.792~800 (2000)[DOI]
  24. M. Tarvainen, "Boundary element method and internal electrodes in electrical impedance tomography", International journal for numerical methods in engineering, 50(4), pp.809~824 (2001)
  25. R. Duraiswami, "Boundary element techniques for effcient 2-d and 3-d electrical impedance tomography", Chemical engineering science, 52(13), pp.2185~2196 (1997)
  26. R. G. Aykroyd, "A boundaryelement approach for the complete-electrode model of eit illustrated using simulated and real data", Inverse Problems in Science and Engineering, 15(5), pp.441~461 (2007)[DOI]
  27. A. K. Khambampati, "An analytical boundary element integral approach to track the boundary of a moving cavity using electrical impedance tomography", Measurement Science and Technology, 23(3), pp.035401~ (2012)[DOI]
  28. W. R. Lionheart, "Eit reconstruction algorithms : pitfalls, challenges and recent developments", Physiological measurement, 25(1), pp.125~[DOI]
  29. E. Beretta, "Reconstruction of a piecewise constant conductivity on a polygonal partition via shape optimization in eit", Journal of Computational Physics, 353, pp.264~280 (2018)
  30. S. Kim, "Moving interfacial boundary estimation in stratifed ?ow of two immiscible liquids using electrical resistance tomography", Measurement Science and Technology, 18(5), pp.1257~ (2007)
  31. A. K. Khambampati, "An effcient method to determine the size of bladder using electrical impedance tomography", TENCON 2018～2018IEEE Region 10 Conference. IEEE, pp.1933~1936 (2018)
  32. D. Liu, "A parametric level set method for electrical impedance tomography", IEEE transactions on medical imaging, 37(2), pp.451~460 (2017)
  33. D. Liu, "B-spline-based sharp feature preserving shape reconstruction approach for electrical impedance tomography", IEEE transactions on medical imaging, 38(11), pp.2533~2544 (2019)
  34. S. K. Sharma, "Bladder boundary estimation by gravitational search algorithm using electrical impedance tomography", IEEE Transactions on Instrumentation and Measurement, 69(12), pp.9657~9667 (2020)
  35. W. Liu, "A survey of deep neural network architectures and their applications", Neurocomputing, 234, pp.11~26 (2017)[DOI]
  36. S. K. Konki, "A deep neural network for estimating the bladder boundary using electrical impedance tomography", Physiological Measurement, 41(11), pp.115003~ (2020)[DOI]
  37. Sunam Kumar Sharma, "Estimating aquifer location using deep neural network with electrical impedance tomography", 전기전자학회논문지, 24(4), pp.982~990 (2020), 한국전기전자학회[DOI]
  38. H. Park, "Deep neural network based electrical impedance tomographic sensing methodology for large-area robotic tactile sensing", IEEE Transactions on Robotics (2021)[DOI]
  39. M. Vauhkonen, "Electrical impedance tomography and prior information", ph. d, pp.1997
  40. O. C. Zienkiewicz, "Finite Element Method: Vol. 3: Fluid Dynamics" (2000), Elsevier Science & Technology Books
  41. K.-S. Cheng, "Electrode models for electric current computed tomography", IEEE Transactions on Biomedical Engineering, 36(9), pp.918~924 (1989)[DOI]
  42. E. Somersalo, "Existence and uniqueness for electrode models for electric current computed tomography", SIAM Journal on Applied Mathematics, 52(4), pp.1023~1040 (1992)[DOI]
  43. S. Brenner, "The mathematical theory of fnite element methods", Springer Science & Business Media, 15 (2007)
  44. A. Adler, "Uses and abuses of eidors: an extensible software base for eit", Physiological measurement, 27(5), pp.S25~ (2006)[DOI]
  45. A. K. Khambampati, "A boundary element method to estimate the interfacial boundary of two immiscible stratifed liquids using electrical resistance tomography", Chemical Engineering Science, 95, pp.161~173 (2013)[DOI]
  46. E. Rashedi, "Gsa : a gravitational search algorithm", Information sciences, 179(13), pp.2232~2248 (2009)[DOI]
  47. M. M. Lau, "Review of adaptive activation function in deep neural network", 2018 IEEE-EMBS Conference on Biomedical Engineering and Sciences (IECBES), pp.686~690 (2018), IEEE
  48. D. P. Kingma, "Adam: A method for stochastic optimization" (2014)
  49. J. McNeill, "Electrical conductivity of soils and rocks. geonics limited" (1980)
  50. M. Abadi, "Tensor?ow: A system for large-scale machine learning", 2th {USENIX}symposium on operating systems design and implementation ({OSDI} 16), 265283, pp.265283~ (2016)
  51. J. Lee Rodgers, "Thirteen ways to look at the correlation coeffcient", The American Statistician, 42(1), pp.59~66 (1988)[DOI]

관련 논문AI추천

Estimating aquifer location using deep neural network with electrical impedance tomography김경연, Anil Kumar Khambampati, Sunam Kumar Sharma한국전기전자학회 · 전기전자학회논문지2020 · 제24권 제4호전기전자탐사에 적용되는 심층 학습 연구 동향 및 적용 사례 분석남명진, 윤대웅, 장한나, 정인석, 정주연, 조아현, Caesary Desy한국자원공학회 · 한국자원공학회지2022 · 제59권 제4호Cuckoo search optimization algorithm for boundary estimation problems in electrical impedance tomography김경연, 전민호, Anil Kumar Khambampati, Sravan Kumar Konki한국전기전자학회 · 전기전자학회논문지2024 · 제28권 제2호상호작용 이중-모드 조정방법을 이용한 저항률 영상 복원강숙인, 김경연한국전기전자학회 · 전기전자학회논문지2016 · 제20권 제2호A Study on Two-Dimensional Variational Mode Decomposition Applied to Electrical Resistivity Tomography김경연, Anil Kumar Khambampati, Felipe Alberto Solano Sanchez한국전기전자학회 · 전기전자학회논문지2022 · 제26권 제3호수직 다층구조의 대지저항률 영상복원을 위한 전극배열법의 비교강민제, 김호찬, 부창진한국전기전자학회 · 전기전자학회논문지2018 · 제22권 제1호

이 간행물의 다른 논문 (29건)

초음파 센서 간 신호 간섭 제거 방법이성수, 임형철pp. 584-590차량용 블루투스 스피커를 위한 EMC를고려한 4층 PCB 설계윤기영, 이성수, 김부균pp. 591-597상황인지 기반 IoT-MEC 서비스를 위한계층적 서비스 바인딩 및 자원관리 구조 설계노원종pp. 598-606CPW 급전 UWB 모노폴 종이 안테나박동국pp. 607-612얼굴 랜드마크 거리 특징을 이용한 표정 분류에 대한 연구배진희, 왕보현, 임준식pp. 613-618
원문 보기