Residual Learning of Deep Convolutional Neural Network for Seismic Random Noise Attenuation

Wang Feng; Chen Shengchang

首页> 外文期刊>IEEE Geoscience and Remote Sensing Letters >Residual Learning of Deep Convolutional Neural Network for Seismic Random Noise Attenuation

【24h】

Residual Learning of Deep Convolutional Neural Network for Seismic Random Noise Attenuation

机译：深度卷积神经网络对地震随机噪声衰减的残差学习

获取原文

获取原文并翻译 | 示例

掌桥外文数据库（机构版） >>

开具论文收录证明 >>

文献代查 >>

页面导航

摘要
著录项
相似文献
相关主题

摘要

Over the last decades, seismic random noise attenuation has been dominated by transform-based denoising methods over the last decades. However, these methods usually need to estimate the noise level and select an optimal transformation in advance, and they may generate some artifacts in the denoising result (e.g., nonsmooth edges and pseudo-Gibbs phenomena). To overcome these disadvantages, we trained a deep convolutional neural network (CNN) with residual learning for seismic data denoising. We used synthetic seismic data for network training rather than seismic images, and we adopted a method to preprocess the seismic data before it was inputted in the network to help network training. We demonstrate the performance of the deep CNN in seismic random noise attenuation based on the synthetic seismic data. Results of numerical experiments show that our network adaptively and effectively suppresses noise of different levels and exhibits a competitive performance in comparison with the traditional transform-based methods.

机译：在过去的几十年中，地震随机噪声衰减在过去的几十年中一直被基于变换的降噪方法所控制。然而，这些方法通常需要估计噪声水平并预先选择最佳变换，并且它们可能在去噪结果中产生一些伪像（例如，非平滑边缘和伪Gibbs现象）。为了克服这些缺点，我们训练了带有残差学习的深度卷积神经网络（CNN），用于地震数据去噪。我们使用合成地震数据进行网络训练，而不是使用地震图像，并采用一种方法对地震数据进行预处理，然后再将其输入网络以帮助进行网络训练。我们基于合成地震数据证明了深CNN在地震随机噪声衰减中的性能。数值实验结果表明，与传统的基于变换的方法相比，我们的网络能够自适应，有效地抑制不同级别的噪声，并具有竞争优势。

著录项

来源
《IEEE Geoscience and Remote Sensing Letters》 |2019年第8期|1314-1318|共5页
作者
Wang Feng; Chen Shengchang;
展开▼
作者单位

Zhejiang Univ Sch Earth Sci Hangzhou 310027 Zhejiang Peoples R China|Minist Nat Resources Peoples Republ China Key Lab Geol Informat Technol Beijing 100037 Peoples R China;

Zhejiang Univ Sch Earth Sci Hangzhou 310027 Zhejiang Peoples R China;

展开▼
收录信息
原文格式 PDF
正文语种 eng
中图分类
关键词
Convolutional neural network (CNN); residual learning; seismic data denoising;

机译：卷积神经网络（CNN）;残余学习;地震数据去噪;

相似文献

外文文献
中文文献
专利

1. Random Noise Attenuation Based on Residual Convolutional Neural Network in Seismic Datasets [J] . Yang Liuqing, Chen Wei, Liu Wei, Quality Control, Transactions . 2020,第期

机译：基于地震数据集残留卷积神经网络的随机噪声衰减
2. Seismic random noise suppression using deep convolutional autoencoder neural network [J] . Song Hui, Gao Yang, Chen Wei, Journal of Applied Geophysics . 2020,第1期

机译：利用深卷积自动化器神经网络的地震随机噪声抑制
3. An improved model training method for residual convolutional neural networks in deep learning [J] . Li Xuelei, Li Rengang, Zhao Yaqian, Multimedia Tools and Applications . 2021,第5期

机译：深度学习中剩余卷积神经网络的改进模型训练方法
4. Deep Learning Residual-like Convolutional Neural Networks for Optic Disc Segmentation in Medical Retinal Images [C] . Amir Hossein Panahi, Reza Askari Moghadam, Kurosh Madani International Conference on Deep Learning Theory and Applications . 2020

机译：医学视网膜图像中光盘分割的深度学习剩余卷积神经网络
5. Plant Segmentation by Supervised Machine Learning Methods and Phenotypic Trait Extraction of Soybean Plants Using Deep Convolutional Neural Networks with Transfer Learning [D] . Adams, Jason R. 2020

机译：植物分割通过深度卷积神经网络与转移学习的豆豆植物的植物分割和表型特性
6. A Novel Deep-Learning-Based Bug Severity Classification Technique Using Convolutional Neural Networks and Random Forest with Boosting [O] . Ashima Kukkar, Rajni Mohana, Anand Nayyar, 2019

机译：基于卷积神经网络和Boosting随机森林的基于深度学习的错误严重性分类新技术
7. Deep Convolutional Denoising Autoencoders with Network Structure Optimization for the High-Fidelity Attenuation of Random GPR Noise [O] . Deshan Feng, Xiangyu Wang, Xun Wang, 2021

机译：具有网络结构优化的深度卷积去噪，随机GPR噪声的高保真衰减

Residual Learning of Deep Convolutional Neural Network for Seismic Random Noise Attenuation

摘要

著录项

相似文献

相关主题

期刊订阅