Random Noise Attenuation Based on Residual Convolutional Neural Network in Seismic Datasets

Liuqing Yang,Wei Chen,Wei Liu,Bei Zha,Linqi Zhu

doi:10.1109/access.2020.2972464

Abstract

Seismic random noise attenuation is a key step in seismic data processing. The random seismic data recorded by the detector tends to have strong noise, and this noisy seismic ratio can be seen as a low signal-to-noise ratio (SNR). Low SNR data can seriously affect the subsequent processing of seismic data, such as migration and imaging. Therefore, it is crucial to eliminate random noise in seismic data. In this paper, we aimed to improve the SNR of seismic data, and proposed an intelligent convolutional neural network noise reduction framework to adaptively capture seismic signals from seismic data with noise. The eponential linear unit (ELU) activation function and the Adam optimization algorithm were used to train the network, which increased the effective information extraction of the network in the negative interval. In order to speed up network training, we added residual learning and batch normalization methods to the network. In addition, three datasets were used to train and test the network. The experimental results show that the method proposed in this paper is better than feed-forward denoising convolutional neural networks (DnCNNs) and other contrast methods in denoising performance. More importantly, a well-trained network not only preserves weak features in learning, but also removes spatially random noise. First, the proposed method is fully trained to extract random noise from the training data, then we retain the data features learned in the training, and estimate the waveform characteristics in the test set by reconstructing the recorded seismic data. Secondly, the characteristics of seismic data in the field record are quite different from those of the training set. However, the proposed adaptive denoising framework can still capture the connection between prediction and reality from the difference. The processing results of theoretical pure record, common-shot-point record, and field data showed great potential in random noise attenuation applications.

Highlights

In seismic exploration, seismic data is interfered with various random noises during seismic data acquisition, which will affect the post-processing of seismic data, such as imaging and interpretation [1]–[3]
We calculate the peak signal-to-noise ratio (PSNR) of the denoised data, compare the denoising results of the NLM, BM3D, and denoising convolutional neural networks (DnCNNs) methods, and plot the point and line image based on the noise level increasing from 5 to 40
We find that the PSNR and selection similarity index measurement (SSIM) based on patch changes shows a trend of rising first and falling, i.e., the accuracy gradually increased with the patch size from 20 to 35, and gradually decreased from 35 to 45

Summary

Introduction

Seismic data is interfered with various random noises during seismic data acquisition, which will affect the post-processing of seismic data, such as imaging and interpretation [1]–[3]. These random noises are usually caused by environmental disturbances. In order to solve the problem of noise attenuation, many researchers have proposed a variety of random noise elimination technology [4]–[6]. Based on f-x predictive filtering, Chen and Ma [15] proposed the f-x empirical mode decomposition predictive filtering (EMDPF) algorithm, which solves the problem of complex seismic data denoising. Chen et al [16] combined ensemble empirical

Objectives

Methods

Discussion

Conclusion