Seismic data denoising based on attention dual dilated CNN

Abstract

Abstract Seismic data denoising is essential for accurate seismic-exploration data processing and interpretation. Traditional noise suppression methods often result in the loss of critical signals, affecting subsurface structure characterization. This study introduces an innovative Attention Dual-Dilated Convolutional Neural Network (ADDC-Net) to address random noise in seismic data. The network expands its model width to extract complementary features, effectively handling complex random noise. By incorporating dilated convolution, the model increases its receptive field without altering kernel size, enabling a more comprehensive analysis of global data features and extraction of effective signal characteristics. An attention mechanism further enhances noise suppression, reducing signal leakage in local similarity graphs. Experimental results show that ADDC-Net outperforms feedforward DnCNN and DudeNet, improving PSNR by 2.8905 dB and 0.6410 dB, respectively. Additionally, ADDC-Net operates faster than convolutional networks with equivalent receptive fields, demonstrating superior denoising performance while preserving signals.

Keywords

• Dilated convolution
• Deep learning
• Denoising
• Seismic data