지구물리와물리탐사 (Geophysics and Geophysical Exploration)

  • 제23권4호
  • /
  • Pages.230-242
  • /
  • 2020
  • /
  • 1229-1064(pISSN)
  • /
  • 2384-051X(eISSN)
한국지구물리·물리탐사학회 (Korean Society of Earth and Exploration Geophysicists)
권호 표지
DOI QR코드

DOI QR Code

Random Forest 기법을 이용한 도심지 MT 시계열 자료의 차량 잡음 분류

Classification of Transport Vehicle Noise Events in Magnetotelluric Time Series Data in an Urban area Using Random Forest Techniques

  • 권형석 (강원대학교 지구자원연구소) ;
  • 류경호 (강원대학교 에너지자원공학과) ;
  • 심익현 ((주)에이에이티) ;
  • 이춘기 (극지연구소 빙하환경연구본부) ;
  • 오석훈 (강원대학교 에너지자원공학과)
  • Kwon, Hyoung-Seok (Research Research Institute for Earth Resources, Kangwon National University) ;
  • Ryu, Kyeongho (Department of Energy and Resources Engineering, Kangwon National University) ;
  • Sim, Ickhyeon (AAT Co. Ltd.) ;
  • Lee, Choon-Ki (Division of Glacial Environment Research, Korea Polar Research Institute) ;
  • Oh, Seokhoon (Department of Energy and Resources Engineering, Kangwon National University)
  • 투고 : 2020.06.12
  • 심사 : 2020.11.10
  • 발행 : 2020.11.30
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

201 6년 9월에 발생한 경주지진원 구역에 대한 정밀 지질구조 규명을 위해 MT 탐사를 적용하였다. 경주지역의 MT 측정자료는 조사지역 인근의 지하철, 전력선, 공장, 주택, 농경지에서 발생된 전기적 잡음과 철도, 도로에서의 차량잡음 등으로 인해 측정자료 왜곡이 심하게 발생되었다. 이 연구에서는 고속철도 및 고속도로와 인접한 4개소의 MT 탐사자료에 기계학습 기법을 적용하여 차량잡음이 포함된 시계열을 분류하였다. 고속열차 잡음이 포함된 시계열에 대해서는 확률적 경사 하강법, 서포트 벡터 머신과 랜덤 포레스트 3가지의 분류모델을 적용하여 그 결과를 비교하였다. 대형트럭 잡음이 포함된 시계열 자료에 대해서는 Hx 성분, Hy 성분과 Hx & Hy 합성성분 크기에 대한 3가지의 샘플 자료를 준비하였으며 랜덤 포레스트 분류모델을 구성하여 그 성능을 평가하였다. 마지막으로 차량잡음 제거 효과 분석을 위하여 차량잡음 제거 전후의 시계열, 진폭 스펙트럼과 겉보기비저항 곡선을 비교하였으며, 이를 통해 차량잡음이 영향을 미치는 주파수 대역과 차량잡음 제거 시 발생될 수 있는 문제점에 대해 고찰하였다.

We performed a magnetotelluric (MT) survey to delineate the geological structures below the depth of 20 km in the Gyeongju area where an earthquake with a magnitude of 5.8 occurred in September 2016. The measured MT data were severely distorted by electrical noise caused by subways, power lines, factories, houses, and farmlands, and by vehicle noise from passing trains and large trucks. Using machine-learning methods, we classified the MT time series data obtained near the railway and highway into two groups according to the inclusion of traffic noise. We applied three schemes, stochastic gradient descent, support vector machine, and random forest, to the time series data for the highspeed train noise. We formulated three datasets, Hx, Hy, and Hx & Hy, for the time series data of the large truck noise and applied the random forest method to each dataset. To evaluate the effect of removing the traffic noise, we compared the time series data, amplitude spectra, and apparent resistivity curves before and after removing the traffic noise from the time series data. We also examined the frequency range affected by traffic noise and whether artifact noise occurred during the traffic noise removal process as a result of the residual difference.

키워드

참고문헌

  1. Carbonari, R., Maio, R. D., Piegari, E., D'Auria, L., Esposito, A., and Petrillo, Z., 2018, Filtering of noisy magnetotelluric signals by SOM neural netoworks, Phys. Earth Planet. Inter., 258, 12-22, doi: 10.1016/j.pepi.2018.10.004.
  2. Chave, A. D. and Jones, A. G., 2012, The magnetotelluric method-Theory and practice, Cambridge Univ. Press, 454-457, doi: 10.1017/CBO9781139020138.
  3. Chave, A. D. and Thomson, D. J., 2004, Bounded inluence magnetotelluric response function estimation, Geophys. J. Int., 157(3), 998-1006, doi: 10.1111/j.1365-246X.2004.02203.x.
  4. Chave, A. D., Thomson, D. J., and Ander M. E., 1987, On the Robust estimation of power spectra, coherences, and transfer functions, J. Geophys. Res. Solid Earth, 92(B1), 633-648, doi:0.1029/JB092iB01p00633. https://doi.org/10.1029/JB092iB01p00633
  5. Daubaras, A., and Zilys, M., 2012, Vehicle detection based on magneto-resistive magnetic field sensor, Elektronika ir Elektrotechnika, 118(2), 27-32, doi: 10.5755/j01.eee.118.2.1169.
  6. Geron, A., 2017, Hands-on machine learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O'Reilly media. Sebastopol, CA, 54-56.
  7. Han, K., 2012, Geophysical study fors tructural characteristics and changes of Yangsan fault zone in the Eonyang-Gyeongju area, Ph.D. thesis, Andong Nat'l University.
  8. Kim, K., and Oh, S., 2013, A geophysical survey of an iron mine site, Jour. Korean Earth Science Society, 34(6), 575-587 (in Korean with English abstract), doi: 10.5467/JKESS.2013.34.6.575.
  9. Kwon, H. S., Song, Y., Yi, M. J., Chung, H. J., and Kim, K. S., 2006, Case histories of electrical resistivity and controlledsource magnetotelluric surveys for the site investigation of tunnel construction, J. Environ. Eng. Geoph., 11(4), 237-248, doi: 10.2113/JEEG11.4.237.
  10. Lan, J., and Shi, Y., 2009, Vehicle detection and recognition based on a MEMS magnetic sensor, Proceedings of the 2009 4th IEEE International Conference on Nano/Micro Engineered and Molecular Systems, 404-408, doi: 10.1109/NEMS.2009.5068605
  11. Lan, J., Xiang, Y., Wang, L., and Shi, Y., 2011, Vehicle detection and classification by measuring and processing magnetic signal, Measurement, 44(1), 174-180, doi: 10.1016/j.measurement.2010.09.044.
  12. Lee, C. K., 2006, Magnetotelluric study on the deep geolelectrical structure across the Korean Peninsula, Ph.D. thesis, Seoul Nat'l University.
  13. Lee, T. J., Han, N. R., Ko, K. B., Hwang, S. H., Park, K. G., Kim, H. C., and Park, Y. C., 2009, Site investigation for pilot scale CO2 sequestration by magnetotelluric surveys in Uiseong, Korea, Geophys. and Geophys. Explor., 12(4), 299-308 (in Korean with English abstract).
  14. Lee, T. J., Kim, M. S., Park, I. H, Song, Y., Nam, M. J., Song, S. Y., and Yun, K. H., 2019, Geoelectrical structure of Ulleung Island, Korea: interpretation of three-dimensional magnetotelluric data, Explor. Geophy., 50(5), 481-489, doi: 10.1080/08123985.2019.1634192.
  15. Lee, T. J., Lee, S. K., Lee, C., Park, I. H., Song, Y., and Uchida T., 2008, Two-dimensional magnetotelluric surveys for investigating possible deep geothermal regime in the midmountain area of Jeju island, Geosystem Eng., 45(4), 315-325 (in Korean with English abstract).
  16. Lee, T. J., Song, Y., and Uchida T., 2005, Two- and threedimensional interpretations of magnetotelluric data from Pohang geothermal site, J. Korea Inst. Mineral Mining Eng., 42(4), 297-307 (in Korean with English abstract).
  17. Li, J., Zhang, X., Gong, J., Tang J., Ren, Z, Li, G., Deng, Y., and Cai, J., 2018, Signal-noise identification of magnetotelluric signals using fractal-entropy and clustering algorithm for targeted de-noising, Fractals, 26(2), 1840011, doi: 10.1142/S0218348X1840011X.
  18. Lorrain, P., and Corson, D. R., 1907, Electromagnetic fields and waves, W.H. Freeman and Company, 319-322.
  19. Manoj, C. and Nagarajan, N., 2003, The application of artificial neural networks to magnetotelluric time-series analysis, Geophys. J. Int., 153(2), 409-423, doi: 10.1046/j.1365-246X.2003.01902.x
  20. Markevicius, V., Navikas, D., Daubaras, A. Cepenas, M., Zilys, M., and Andriukaitis, D., 2014, Vehicle influence on the earth's magnetic field changes, Elektronika ir Elektrotechnika, 20(4), 43-48, doi: 10.5755/j01.eee.20.4.4552.
  21. Markevicius, V., Navikas, D., Zilys, M., Andriukaitis, D., Valinevicius, A. and Cepenas, M., 2016, Dynamic vehicle detection via the use of magnetic field sensors, sensors, 16(1), 1-9, doi: 10.3390/s16010078.
  22. Meng, Y., Wang, G., Bai, Y., Zhang, Z., and Wang, W., 2019, High-speed railway interference and remote reference suppression in MT survey, AGUFM, 2019, GP11A-07.
  23. Sim, I. H, 2020, Noise reduction in MT time series measured in the vicinity of highway and electric train line using supervised learning and wavelet transform, MS thesis, Kangwon Nat'l University.
  24. Uchida, T., Song, Y., Lee, T. J., Mitsuhata, Y. Lim, S. K., and Lee, S. K., 2005, Magnetotelluric survey in an extremely noisy environment at the Pohang low-enthalpy geothermal area, Korea, Proceedings World Geothermal Congress 2005.
  25. Varentsov, I. M., Sokolova, E. Y., Martanus, E. R., and Nalivaiko, K. V., 2003, System of electromagnetic field transfer operators for the BEAR array of simultaneous soundings: methods and results, Izv., Phys. Solid Earth, 39(2), 118-148.
  26. Wang, Q., Zheng, J, Xu, H., Xu, B., and Chen, R., 2018, Roadside magnetic sensor system for vehicle detection in urban environments, IEEE Trans. Intell. Transp. Syst., 19(5), 1365-1374, doi: 10.1109/TITS.2017.2723908.