A Ground-Roll Separation Method Based on Neural Networks With Morphological Similarity Loss
- 20 September 2023
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Geoscience and Remote Sensing Letters
- Vol. 20 (1545598X) , 1-5
Abstract
Ground-roll is a typical Rayleigh-type interference noise in field seismic data, which is characterized by low frequency, low velocity and high amplitude. Since it will interfere effective seismic signals and severely degrade the signal-to-noise ratio of observed seismic records, many approaches have been developed for ground-roll attenuation or separation. In this letter, we proposed an improved ground-roll separation algorithm through the combination of deep learning based low-frequency generation and dictionary learning based low-frequency reconstruction. Moreover, to utilize the inter-band morphological similarity prior in seismic response, we introduce the morphological similarity constraint into the learning approach of pseudo low-frequency generation networks. Experiments demonstrate that compared to previous methods, the introduced the morphological similarity loss can effectively improve the quality of generated pseudo low-frequency signals, which results in better low-frequency reflection reconstruction and ground-roll separation performances.Keywords
Funding Information
- National Key Research and Development Program of China through the Multivariate Information Compatibility Expression via Artificial Intelligence (2018YFA0702501)
- nsfc youth science foundation project (42104117)
- Natural Science Foundation of China (41974126)
- Natural Science Foundation of China (41674116)
This publication has 18 references indexed in Scilit:
- GaborNet: Gabor filters with learnable parameters in deep convolutional neural network2019
- LGCN: Learnable Gabor Convolution Network for Human Gender Recognition in the WildIEICE Transactions on Information and Systems, 2019
- Classification of Hyperspectral Images by Gabor Filtering Based Deep NetworkIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 2017
- Hyperspectral Images Classification With Gabor Filtering and Convolutional Neural NetworkIEEE Geoscience and Remote Sensing Letters, 2017
- Adaptive multiple subtraction based on multiband pattern codingGeophysics, 2015
- Ground-Roll Noise Attenuation Using a Simple and Effective Approach Based on Local Band-Limited OrthogonalizationIEEE Geoscience and Remote Sensing Letters, 2015
- Face Recognition Using Gabor Filter Bank, Kernel Principle Component Analysis and Support Vector MachineInternational Journal of Computer Theory and Engineering, 2012
- The Split Bregman Method for L1-Regularized ProblemsSIAM Journal on Imaging Sciences, 2009
- Localized 2-D filter-based linear coherent noise attenuationIEEE Transactions on Image Processing, 2001
- A method of ground-roll eliminationGeophysics, 1988