Predicting elastic parameters based on digital rock images is an interesting application of a convolutional neural network (CNN), which can improve the efficiency of prediction. Predicting elastic parameters by a conventional CNN, which is used for image classification such as LeNet and AlexNet, lacks geophysical constraints, and its accuracy in predicting elastic parameters is poor, with limited training data available. The combination of a U-Net and a convolutional neural network (CUCNN) is proposed to predict the elastic parameters from digital rock images with limited training data. In CUCNN, the rock matrix and pore types segmented from gray-scale images are treated as constraints that induce the convolutional kernels to extract the global as well as the local-scale rock features. The loss function, designed in a composite form to accelerate the convergence speed, contains the segmentation error and elastic parameters predicted from the gray-scale images. By adding geophysical constraints to the CNN, an implicit representation from the gray-scale image to the elastic parameters can be gained, which can improve the accuracy and efficiency of parameter prediction. Our method was tested using training and verification data derived from 1800 2D image slices of Berea sandstone samples, and the results were compared against the CNN model. The VP and VS were calculated by the finite-element method as the control to test the performance of both models. Our results show that CUCNN’s R2 score is 0.84, which increased by as much as 0.21 compared to the conventional CNN.

An accurate seismic facies analysis (SFA) can provide insight into the subsurface sedimentary facies and has guiding significance for geological exploration. Many machine learning algorithms, including unsupervised, supervised, and deep learning algorithms, have been developed successfully for SFA over the past decades. However, SFA and facies classification are still challenging tasks due to the complex characteristics of geological and seismic data. A multiattribute SOM-K-means clustering algorithm, which implements a two-stage clustering by using multiple geological attributes, is proposed and applied for SFA. The proposed algorithm can effectively extract complementary features from the multiple attribute volumes and comprehensively use the different attributes to improve the recognition ability of seismic facies. Experimental results show that the proposed algorithm improves clustering accuracy and can be used as an effective and powerful tool for SFA.

A sandwiched piezoelectric accelerometer is developed and optimized for acquiring low-frequency, wide-band seismic data. The proposed accelerometer addresses the challenges of capturing seismic signals in the low-frequency range while maintaining a broad frequency response through the design of multi-stage charge amplifiers and a sandwiched structure. The device’s design, fabrication process, and performance evaluation are discussed in detail. Experimental results demonstrate its performance in amplitude and phase response characteristics.

Road traffic noise is a special kind of high amplitude noise in seismic or acoustic data acquisition around a road network. It is a mixture of several surface waves with different dispersion and harmonic waves. Road traffic noise is mainly generated by passing vehicles on a road. The geophones near the road will record the noise while receiving the seismic signal. The amplitude of the traffic noise is much larger than the signal, which masks the effective information and degrades the quality of acquired data. At the same time, the traffic noise is coupled with the effective signal, which makes it difficult to separate them. Therefore, attenuating traffic noise is the key to improving the quality of the final processing results. In recent years, denoising methods based on convolution neural networks (CNN) have shown good performance in noise attenuation. These denoising methods can learn the potential characteristics of acquired data, thus establishing the mapping relationship between the original data and the effective signal or noise. Here, we introduce a method combining UNet networks with asymmetric convolution blocks (ACBs) for traffic noise attenuation, and the network is called the ACB-UNet. The ACB-UNet is a supervised deep learning method, which can obtain the distribution characteristics of noise and effective signal through learning the training data and then effectively separate the two to achieve noise removal. To validate the performance of the proposed method, we apply it to synthetic and real data. The data tests show that the ACB-UNet can obtain good results for high amplitude noise attenuation and is practical and efficient.

Grid size has a significant influence on the computation efficiency and accuracy of finite-difference seismic modeling and can change the workload of reverse time migration (RTM) remarkably. This paper proposes a non-orthogonal analytical coordinate system, beam coordinate system (BCS), for the solution of seismic wave propagation and RTM. Starting with an optical Gaussian beam width equation, we expand the representation on vertically variable velocity media, which is the most common scenario in seismic exploration. The BCS based on this representation can be used to implement an irregular-grid increment finite-difference that improves the efficiency of RTM. Based on the Laplacian expression in Riemannian space, we derive the wave equation in the BCS. The new coordinate system can generate an irregular grid with increment increasing vertically along depth. Through paraxial ray tracing, it can be extended to non-analytical beam coordinate system (NBCS). Experiments for the RTM on the Marmousi model with the BCS demonstrate that the proposed method improves the efficiency about 52% while maintaining good image quality.

Beam forming is one of the important steps for beam migration. Based on the alternating directions method of the augmented Lagrangian multiplier method (ADMM), a robust sparse linear radon transform (SLRT) for beam forming and migration is proposed in order to improve the representation of intermediate beam data and the quality of final image result. The ADMM splits sparse constrain the least-square problem into two main parts: updating least-square solutions and thresholding, which can handle sparse, near-sparse and even non-sparse optimization problems. We tailor it for SLRT of local seismic data through introducing the fast algorithm of a Hamiltonian matrix and recasting regularization parameters and threshold variable for soft-thresholding. Compared with matching pursuit (MP), it is faster with an average four iterations, increased robustness and improved performance for possible non-strict sparse situations. Experiments for beam migration show that the proposed method could obtain better results while maintaining good performance.