Seismic Coherent Noise Removal with Residual Network and Synthetic Seismic Simples

TL;DR

This paper introduces DR-Unet, a deep residual neural network designed to effectively remove seismic coherent noise from post-stack seismic data, improving image quality using synthetic and real data training.

Contribution

The paper presents a novel deep-residual-learning neural network and a workflow for generating training data by adding real noise to synthetic data, enhancing seismic noise removal.

Findings

Achieves superior denoising results compared to traditional methods.

Effective on both synthetic and field seismic data.

Utilizes synthetic data augmentation with real noise for training.

Abstract

Seismic coherent noise is often found in post-stack seismic data, which contaminates the resolution and integrity of seismic images. It is difficult to remove the coherent noise since the features of coherent noise, e.g., frequency, is highly related to signals. Recently, deep learning has proven to be uniquely advantageous in image denoise problems. To enhance the quality of the post-stack seismic image, in this letter, we propose a novel deep-residual-learning-based neural network named DR-Unet to efficiently learn the feature of seismic coherent noise. It includes an encoder branch and a decoder branch. Moreover, in order to collect enough training data, we propose a workflow that adds real seismic noise into synthetic seismic data to construct the training data. Experiments show that the proposed method can achieve good denoising results in both synthetic and field seismic data, even better than the traditional method.