SavedAdd your journal

Journals / Yerbilimleri / 2026 / Cilt: 34 Sayı: 1

Signal and Noise Detection in Magnetotelluric Data by the Artificial Neural Network Method

Yapay Sinir Ağı Yöntemi ile Manyetotellürik Veride Sinyal ve Gürültü Ayırımı

Ebru Şengül Uluocak
Emin U. Ulugergerli
Hilal Göktaş
Pages
141–168
Publication Date
2013-02-01
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

In addition, when all types of noise in the data are defined (synthetic data), all noisy time windows can be sellected and eliminated by artificial neural network method.Test results from synthetic and field data indicate that artificial neural network classification is succesfull in identifying and eliminating the noisy data windows compared to both visual inspection and conventional assessment methods

📌 3 Key Takeaways

🎯
Objective & Hypothesis:In this study artificial neural network method was used to classify noisy components in the MT method data.
📊
Key Findings & Data:Noisy time windows were determined to an accuracy of 89 % depending on the training data set.
💡
Conclusion & Impact:In addition, when all types of noise in the data are defined (synthetic data), all noisy time windows can be sellected and eliminated by artificial neural network method.Test results from synthetic and field data indicate that artificial neural network classification is succesfull in identifying and eliminating the noisy data windows compared to both visual inspection and conventional assessment methods
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Manyetotellürik · Yapay Sinir Ağı · Zaman Serisi

Abstract

In this study artificial neural network method was used to classify noisy components in the MT method data. For this purpose a multi-layered, feed-foorward and back propagation model was employed. Noisy time windows were determined to an accuracy of 89 % depending on the training data set. In addition, when all types of noise in the data are defined (synthetic data), all noisy time windows can be sellected and eliminated by artificial neural network method.Test results from synthetic and field data indicate that artificial neural network classification is succesfull in identifying and eliminating the noisy data windows compared to both visual inspection and conventional assessment methods

Özet

Bu çalışma kapsamında manyetotellürik yöntem verisindeki gürültü bileşenlerini sınıflamak için yapay sinir ağı yöntemi kullanılmıştır. Bu amaçla çok katmanlı, ileri beslemeli ve geri yayılımlı bir model oluşturulmuştur. Seçilen eğitim setine bağlı olarak gürültülü zaman pencereleri % 89 doğrulukla belirlenmiştir. Ayrıca verideki gürültü türlerinin hepsi tanımlandığında (yapay veri), tüm gürültülü pencereler yapay sinir ağı yöntemi ile seçilip elenebilmektedir.Yapay veri ve arazi verisi ile yapılan uygulamalar sonucunda, hem görsel denetlemeye hem de geleneksel değerlendirme yöntemlerine göre, gürültülü veri pencerelerini sınıflayıp elemede yapay sinir ağı yönteminin daha başarılı oldugu gösterilmiştir

🔖

Cite This Article

Uluocak, E. Ş., Ulugergerli, E. U., Göktaş, H. (2013). Signal and Noise Detection in Magnetotelluric Data by the Artificial Neural Network Method. Yerbilimleri, Cilt: 34 Sayı: 1, 141–168. https://ajindex.com/articles/1315812

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (53)

  1. Al-Nuaimy, W., Huang, Y., Nakhkash, M., Fang, M.T.C., Nguyen, V.T. ve Eriksen, A., 2000. Automatic detection of buried utilities and solid objects with GPR using neural networks and pattern re- cognition: Journal of Applied Geoph- ysics, v. 43, Issues 2-4, 157-165.
  2. Ardjmandpour, N., Pain C, Singer J., Saunders J., Aristodemou E. ve Carter, J., 2011. Artificial neural network forward model- ling and inversion of electrokinetic log- ging data, Geophysical Prospecting, 59, 721–748.
  3. Chave A. D. ve Thomson D. J., 1989. Some comments on magnetotelluric respon- se function estimation. J. Geophys. Res., 94: 14215–14225.
  4. Chave A. D. ve Thomson D. J., 2004. Bounded influence magnetotelluric response function estimation. Geophys. J. Int., 157: 988–1006.
  5. Efe M. ve Kaynak O., 2000. Yapay sinir ağları ve uygulamaları. Boğaziçi Üniv. Yay., 148 s.
  6. Egbert G. D. ve Booker J. R., 1986. Robust es- timation of geomagnetic transfer func- tions. Geophys. J. Roy Astr. Soc., 87: 173-194.
  7. Ehret, B., Leibniz Institute for Applied Geoph- ysics, Stilleweg 2, 30655 Hannover, Germany, Geoderma 160 (2010) 111– 125.
  8. El-Qady G. ve Ushijima K., 2001. Inversion of DC resistivity data using neural net- works. Geophysical Prospecting, 49: 417-430.
  9. Gamble T. D., Goubau W. M. ve Clarke J., 1979. Magnetotelluric with a remote magnetic reference. Geophysics, 44 (1): 53-68.
  10. Goring D. G ve Nikora V. I, 2002. Despiking acoustic doppler velocimeter data, J. Hydraul. Eng. 128, 117.
  11. Goubau W. M., Gamble T. D. ve Clarke J., 1978. Magnetotelluric data analysis: removal of bias. Geophysics, 43: 1157-1166.
  12. Haykin S., 1999. Neural network: a comprehen- sive foundation, Second ed. Prentice Hall, New Jersey, USA.
  13. Jones A.G., Chave A. D., Egbert G., Auld D. ve Ahr K., 1989. A comparison of techniques for magnetotelluric respon- se function estimation. Journal of Ge- ophysical Research, 94 (10): 201-213.
  14. Kaftan I., Salk M ve Senol Y., 2011. Evaluation of gravity data by using artificial neural networks case study: Seferihisar geot- hermal area (Western Turkey), Journal of Applied Geophysics, 75, 711-718.
  15. Karnin, E. D., 1990. A simple procedure for pru- ning back-propagation trained neural networks, IEEE IEEE Transaction on Neural Networks, 1, 2, 239-242.
  16. Larsen J. C., Mackie R. L., Manzella A., Fiorde- lisi A. ve Rieven S., 1996. Robust smo- oth magnetotelluric transfer function. Geophys. J. Int., 124: 801-819.
  17. Leung F.H.F, Lam H. K., Ling S. H. ve Peter K. S.
  18. Tam, 2003. Tuning of the structure and
  19. parameters of a neural network using
  20. an improved genetic algorithm, IEEE
  21. Transaction on Neural Networks, 14, 1, 79-88.
  22. Macias C.C., Sen M.K. ve Stoffa P.L., 2000. Ar- tificial neural networks for parameter estimation in geophysics. Geophysical Prospecting 48, 21–47.
  23. Manoj C. ve Nagarajan N., 2003. The Applicati- on of artificial neural networks to mag- netotelluric time-series analysis. Ge- ophys. J. Int., 153, 409–423.
  24. Mori N, Suzuki T. ve Kakuno S., 2007. Noise of acoustic doppler velocimeter data in bubbly flows, J. Eng. Mech. 133, 122.
  25. Öztemel E., 2003. Yapay Sinir Ağları. Papatya Yay., 232 s.
  26. Proakis J.G., Rader C.M., Fuyun L. ve Chrysos- tomosL., 1992. Advanced digital signal processing; Macmillan, New York.
  27. Poulton M., Stenberg B. ve Glass C., 1992. Lo- cation of subsurface targets in geoph- ysical data using neural networks, Ge- ophysics, 57, 1534–1544.
  28. Raiche A., 1991. A pattern recognition appro- ach to geophysical inversion using neu- ral nets. Geophys. J. Int., 105, 629–648.
  29. Rittler O., Junge A. ve Dawes G. J. K., 1998. New equipment and processing for magne- totelluric remote reference observations. Geophys. J. Int., 132,535-548.
  30. Rumelhart D.E., Hinton, G.E. ve Williams, R.J.,
  31. 19 Parallel distributed processing:
  32. explorations in microstructure of cogni
  33. tion. MIT Press Cambridge, MA, USA, 1, 318- 362 pp.
  34. Simpson F. ve Bahr K., 2005. Practical Magne- totellurics. Cambridge University Pres., 254 pp.
  35. Sims W., Bostick F. ve Smith H., 1971. The es- timation of magnetotelluric impedance tensor eelements from measured data. Geophysics, 36, 938-942.
  36. Smirnov M. Y., 2003. Magnetotelluric data pro- cessing with a robust statistical proce- dure having a high breakdown point. Geophys. J. Int., 152-1–7.
  37. Spichak, V.V., Fukuoka, K., Kobayashi, T., Mogi,
  38. T., Popova, I., ve Shima, H., 2002. Ar
  39. tificial neural network reconstruction of
  40. geoelectrical parameters of the Minou
  41. fault zone by scalar CSAMT data. J.
  42. Appl. Geoph., 49 (1/2), 75-90.
  43. Spichak V. ve Popova I., 2000. Artificial neu- ral network inversion of magnetotellu- ric data in terms of three-dimensional Earth macroparameters. Geophys. J. Int., 142, 15–26.
  44. Swift C. M., 1967. A Magnetotelluric investiga- tion of an electrical conductivity ano- maly in the Southwestern United States. (Ph.D. dissertation), Mass. Institute of Technology.
  45. Şahin M., 2005. Çeşitli Geriye Yayılım Yapay Si- nir Ağı Algoritmalarının Karşılaştırılması ve Bazı Uygulamaları. (Yüksek Lisans Tezi), Çanakkale.
  46. Ulugergerli E.U., Fontes S. L., Carvalho R. M, Germano C. R. ve Carrasquilla A., 2011. Magnetotelluric response estimates under the equatorial electrojet in Bra- zil, 12th International Congress of the Brazilian Geophysical Society August
  47. 18, 2011, Rio de Janeiro, Brazil.
  48. van der Baan M. ve Jutten C., 2000. Neural networks in geophysical applications. Geophysics, 65: 1032 - 1047.
  49. Vozoff K., 1991. The magnetotelluric method. In: M.N. Nabighian (Ed). Electromagnetic Methods in Applied Geophysics, SEG,
  50. Tulsa, OK, 2: 641-711.
  51. Weckmann U., Magunia A. ve Ritter O., 2005. Effective noise separation for magne- totelluric single site data processing using a frequency domain selection sheme. Geophys. J. Int., 161, 635-652.
  52. Zhang Y. ve Paulson K. V., 1997. magnetotellu- ric inversion using regularized hopfield neural networks. Geophysical Prospec- ting, 45, 725–743.
  53. Zurada J.M., 1992. Introduction to artificial neu- ral systems. West Pub. Comp., 679 pp.