Horizontal Layer Constrained Attention Neural Network for Semblance Velocity Picking

TL;DR

This paper introduces an attention neural network with a point-to-point regression strategy for automatic semblance velocity picking, improving efficiency and robustness in seismic data processing.

Contribution

It proposes a novel attention neural network combined with a horizontal layer extraction strategy to enhance velocity picking accuracy and efficiency with limited labels.

Findings

Accurately predicts semblance velocity with synthetic and field data.

Maintains global velocity trend consistent with labels.

Demonstrates robustness against random noise.

Abstract

Semblance velocity analysis is a crucial step in seismic data processing. To avoid the huge time-cost when performed manually, some deep learning methods are proposed for automatic semblance velocity picking. However, the application of existing deep learning methods is still restricted by the shortage of labels in practice. In this letter, we propose an attention neural network combined with a point-to-point regression velocity picking strategy to mitigate this problem. In our method, semblance patch and velocity value are served as network input and output, respectively. In this way, global and local features hidden in semblance patch can be effectively extracted by attention neural network. A down-sampling strategy based on horizontal layer extraction is also designed to improve the picking efficiency in prediction process. Tests on synthetic and field datasets demonstrate that the proposed method can produce reasonable results and maintain global velocity trend consistent with labels. Besides, robustness against random noise is also tested on the field data.