Denoising stacked autoencoders for transient electromagnetic signal denoising
-
Published:2019-03-01
Issue:1
Volume:26
Page:13-23
-
ISSN:1607-7946
-
Container-title:Nonlinear Processes in Geophysics
-
language:en
-
Short-container-title:Nonlin. Processes Geophys.
Author:
Lin Fanqiang,Chen Kecheng,Wang Xuben,Cao Hui,Chen Danlei,Chen Fanzeng
Abstract
Abstract. The transient electromagnetic method (TEM) is extremely important in geophysics.
However, the secondary field signal (SFS) in the 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, which
make up an unsupervised learning model in deep learning, on the basis of the analysis of the
characteristics of the SFS to denoise the SFS. We introduce the SFSDSA (secondary
field signal denoising stacked autoencoders) model 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 a 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 (i) effectively reduce the noise of the SFS in contrast with the
Kalman, principal component analysis (PCA) and wavelet transform methods and (ii) strongly support the
speculation of deeper underground features.
Publisher
Copernicus GmbH
Reference30 articles.
1. Ali, A., Fan, Y., and Shu, L.: Automatic modulation classification of digital modulation signals with stacked autoencoders,
Digit. Signal Process., 71, 108–116, https://doi.org/10.1016/j.dsp.2017.09.005, 2017. 2. Becker, S. and Plumbley, M.: Unsupervised neural network learning procedures for feature extraction and classification,
Appl. Intell., 6, 185–203, https://10.1007/bf00126625, 1996. 3. Bengio, Y., Lamblin, P., Popovici, D., Larochelle, H., and Montreal, U.: Greedy layer-wise training of deep networks,
Adv. Neur. In., 19, 153–160, 2007. 4. Caruana, R., Lawrence, S., and Giles, L.: Overfitting in neural nets: backpropagation, conjugate gradient,
and early stopping, in: Proceedings of International Conference on Neural Information Processing Systems, 402–408, 2000. 5. Chen, B., Lu, C. D., and Liu, G. D.: A denoising method based on kernel principal component analysis for airborne time
domain electro-magnetic data, Chinese J. Geophys.-Ch., 57, 295–302, https://doi.org/10.1002/cjg2.20087, 2014.
Cited by
21 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|