DCMSA: Multi-Head Self-Attention Mechanism Based on Deformable Convolution For Seismic Data Denoising

TL;DR

This paper introduces DCMSA, a deformable convolution-based multi-head self-attention mechanism integrated into UNet, significantly improving seismic data denoising by better capturing local features and spatial relationships.

Contribution

The paper presents a novel attention mechanism, DCMSA, that enhances diffusion models for seismic data denoising by integrating deformable convolution with multi-head self-attention.

Findings

Outperforms traditional diffusion models in noise suppression

Enhances local feature recognition in seismic data

Preserves seismic data integrity better than standard methods

Abstract

When dealing with seismic data, diffusion models often face challenges in adequately capturing local features and expressing spatial relationships. This limitation makes it difficult for diffusion models to remove noise from complex structures effectively. To tackle this issue, we propose a novel convolutional attention mechanism Multi-head Self-attention mechanism based on Deformable convolution (DCMSA) achieving efficient fusion of diffusion models with convolutional attention. The implementation of DCMSA is as follows: First, we integrate DCMSA into the UNet architecture to enhance the network's capability in recognizing and processing complex seismic data. Next, the diffusion model utilizes the UNet enhanced with DCMSA to process noisy data. The results indicate that this method addresses the shortcomings of diffusion models in capturing local features and expressing spatial relationships effectively, proving superior to traditional diffusion models and standard neural networks in noise suppression and preserving meaningful seismic data information.