SavedAdd your journal

Journals / Yerbilimleri / 2013 / 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. ULUGERGERLİ
Hilal GÖKTAŞ
Pages
53–72
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., ULUGERGERLİ, E. U., GÖKTAŞ, H. (2013). Signal and Noise Detection in Magnetotelluric Data by the Artificial Neural Network Method. Yerbilimleri, Cilt: 34 - Sayı: 1, 53–72. https://ajindex.com/articles/336587

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (8)

  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. Chave A. D. ve Thomson D. J., 1989. Some comments on magnetotelluric respon- se function estimation. J. Geophys. Res., 94: 14215–14225. Chave A. D. ve Thomson D. J., 2004. Bounded influence magnetotelluric response function estimation. Geophys. J. Int., 157: 988–1006. Efe M. ve Kaynak O., 2000. Yapay sinir ağları ve uygulamaları. Boğaziçi Üniv. Yay., 148 s. Egbert G. D. ve Booker J. R., 1986. Robust es- timation of geomagnetic transfer func- tions. Geophys. J. Roy Astr. Soc., 87: 173-194.
  3. Ehret, B., Leibniz Institute for Applied Geoph- ysics, Stilleweg 2, 30655 Hannover, Germany, Geoderma 160 (2010) 111– 125. El-Qady G. ve Ushijima K., 2001. Inversion of DC resistivity data using neural net- works. Geophysical Prospecting, 49: 417-430.
  4. Gamble T. D., Goubau W. M. ve Clarke J., 1979. Magnetotelluric with a remote magnetic reference. Geophysics, 44 (1): 53-68. Goring D. G ve Nikora V. I, 2002. Despiking acoustic doppler velocimeter data, J. Hydraul. Eng. 128, 117. Goubau W. M., Gamble T. D. ve Clarke J., 1978. Magnetotelluric data analysis: removal of bias. Geophysics, 43: 1157-1166. Haykin S., 1999. Neural network: a comprehen- sive foundation, Second ed. Prentice Hall, New Jersey, USA. 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.
  5. 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.
  6. 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.
  7. 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.
  8. Leung F.H.F, Lam H. K., Ling S. H. ve Peter K. S. Tam, 2003. Tuning of the structure and parameters of