Comparisons of wavelets, contourlets and curvelets in seismic denoising

Deep learning has been successfully applied to image denoising. In this study, we take one step forward by using deep learning to suppress random noise in poststack seismic data from the aspects of network architecture and training samples. On the one hand, poststack seismic data denoising mainly aims at 3-D seismic data. We designed an end-to-end 3-D denoising convolutional neural network (3-D-DnCNN) that takes raw 3-D cubes as input in order to better extract the features of the 3-D spatial structure of poststack seismic data. On the other hand, denoising images with deep learning require noisy–clean sample pairs for training. In the field of seismic data processing, researchers usually try their best to suppress noise by using complex processes that combine different methods, but clean labels of seismic data are not available. In addition, building training samples in field seismic data has become an interesting but challenging problem. Therefore, we propose a training sample selection method that contains a complex workflow to produce comparatively ideal training samples. Experiments in this study demonstrate that deep learning can directly learn the ability to denoise field seismic data from selected samples. Although the building of the training samples may occur through a complex process, the experimental results of synthetic seismic data and field seismic data show that the 3-D-DnCNN has learned the ability to suppress the Gaussian noise and super-Gaussian noise from different training samples. Moreover, the 3-D-DnCNN network has better denoising performance toward arc-like imaging noise. In addition, we adopt residual learning and batch normalization in order to accelerate the training speed. After network training is satisfactorily completed, its processing efficiency can be significantly higher than that of conventional denoising methods.

Poststack Seismic Data Denoising Based on 3-D Convolutional Neural Network

Locational accuracy of underground utility mapping using ground penetrating radar

In this letter, we introduce the utilization of discrete cosine transform (DCT) coefficients as features supplied to the support vector machine (SVM) classifier to identify underground utility material from ground penetrating radar (GPR) imagery. Different types of features, reflected signal amplitudes, and statistical features, combined with the SVM classifier for material identification of underground utilities, are also studied and compared to the DCT-based approach. The system performance is conducted by simulation studies using generated GPR images created by a GPR finite-difference time-domain-based simulator used to develop various acquisition situations by changing the utility material type, position, and size parameters. The efficiency of the proposed technique in material identification is assessed using noisy generated GPR images degraded with speckle noise. Two-dimensional median and adaptive Wiener filters are also examined as a preprocessing step to the studied techniques. Simulation results show that the proposed technique combined with adaptive Wiener filter reveals a good performance regarding the recognition accuracy compared to the other studied techniques in noisy environment.

Yi Wei Li

Papers

Adaptive filtering of random noise in near-surface seismic and ground-penetrating radar data

Application of sub-image multiresolution analysis of Ground-penetrating radar data in a study of shallow structures