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.

The integration of deep learning with optical flow estimation in Particle Image Velocimetry (PIV) represents an emerging solution. Extensive research indicates that deep learning has potential to match or outperform state-of-the-art classical algorithms in efficiency, accuracy, and spatial resolution. However, current learning-based methods, which rely on cost volumes and convolutions for flow regression, are limited to local correlations. This limitation hinders the capture of global information. While extensive iterative refinements enhance the quality of prediction flows, they also result in a linear increase in inference time. To enhance both efficiency and accuracy, we propose a global matching method for PIV. This method directly compares feature similarities to identify correspondences between images and generate estimated flows. The underlying idea is to first extract initial features of particle image pairs, then enhance these features through a Transformer specifically designed for PIV, and perform operations for feature correlation matching, followed by global optical flow propagation and optimization. Additionally, higher-resolution features are introduced for refinement. By employing both synthetic and experimental data, including benchmark sets and data from turbulent wave channel flow experiments, we demonstrate that global matching method in PIV achieves superior efficiency and accuracy compared to existing learning-based methods.

A partition method, with an efficient divide and conquer partition strategy, for the non-uniform sampling signal reconstruction based on Fourier reconstruction sparse inversion (FRSI) is developed. The novel partition FRSI(P-FRSI) is motivated by the...