Journal metrics

Journal metrics

  • IF value: 1.129 IF 1.129
  • IF 5-year value: 1.519 IF 5-year 1.519
  • CiteScore value: 1.54 CiteScore 1.54
  • SNIP value: 0.798 SNIP 0.798
  • SJR value: 0.610 SJR 0.610
  • IPP value: 1.41 IPP 1.41
  • h5-index value: 21 h5-index 21
  • Scimago H index value: 48 Scimago H index 48
Discussion papers | Copyright
© Author(s) 2018. This work is distributed under
the Creative Commons Attribution 4.0 License.

Research article 02 Oct 2018

Research article | 02 Oct 2018

Review status
This discussion paper is a preprint. It is a manuscript under review for the journal Nonlinear Processes in Geophysics (NPG).

A denoising stacked autoencoders for transient electromagnetic signal denoising

Fanqiang Lin1, Kecheng Chen1, Xuben Wang2,3, Hui Cao2, Danlei Chen1, and Fanzeng Chen1 Fanqiang Lin et al.
  • 1School of Information Science and Technology, Chengdu University of Technology, Chengdu 610059, China
  • 2College of Geophysics, Chengdu University of Technology, Chengdu 610059, China
  • 3Key Lab of Geo-Detection and Information Techniques of Ministry of Education, Chengdu 610059, China

Abstract. Transient electromagnetic method (TEM) is extremely important in geophysics. However, the secondary field signal(SFS) in TEM received by coil is easily disturbed by random noise, sensor noise and man-made noise, which results in the difficulty in detecting deep geological information. To reduce the noise interference and detect deep geological information, we apply autoencoders, an unsupervised learning model in deep learning, on the basis of analyzing the characteristic of SFS, to denoise SFS. We introduce SFSDSA, a Secondary Field Signal Denoising Stacked Autoencoders, based on deep neural networks of feature extraction and denoising. SFSDSA maps the signal points of the noise interference to the high probability points with clean signal as reference according to the deep characteristics of the signal, so as to realize the signal denoising and reduce noise interference. The method is validated by the measured data comparison, and the comparison results show that the noise reduction method can effectively reduce the noise of SFS, in contrast with the Kalman and wavelet transform methods, and strongly support the speculation of deeper underground features.

Fanqiang Lin et al.
Interactive discussion
Status: open (until 27 Nov 2018)
Status: open (until 27 Nov 2018)
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
[Subscribe to comment alert] Printer-friendly Version - Printer-friendly version Supplement - Supplement
Fanqiang Lin et al.
Fanqiang Lin et al.
Total article views: 150 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
116 32 2 150 1 0
  • HTML: 116
  • PDF: 32
  • XML: 2
  • Total: 150
  • BibTeX: 1
  • EndNote: 0
Views and downloads (calculated since 02 Oct 2018)
Cumulative views and downloads (calculated since 02 Oct 2018)
Viewed (geographical distribution)
Total article views: 150 (including HTML, PDF, and XML) Thereof 150 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
No saved metrics found.
No discussed metrics found.
Latest update: 15 Oct 2018
Publications Copernicus
Short summary
The deep-seated information is reflected in the late-stage data of the second field. By introducing the deep learning algorithm integrated with the characteristics of the secondary field data, it can map the contaminated data in late track data to a high probability position. By comparing several filtering algorithms, the stack noise reduction from the encoder method can reduce the MAE, it is conducive to the subsequent pumping processing to further improve the effective detection depth.
The deep-seated information is reflected in the late-stage data of the second field. By...