A Real Benchmark Swell Noise Dataset for Performing Seismic Data Denoising via Deep Learning

TL;DR

This paper introduces a new benchmark dataset of synthetic seismic data with real noise for evaluating deep learning models in seismic denoising, along with a novel evaluation metric.

Contribution

It provides the first benchmark dataset for seismic denoising with real noise and compares two DL models, facilitating future research in the field.

Findings

DL models effectively denoise seismic data

The new metric captures small variations in model performance

Some challenges in seismic denoising remain unsolved

Abstract

The recent development of deep learning (DL) methods for computer vision has been driven by the creation of open benchmark datasets on which new algorithms can be tested and compared with reproducible results. Although DL methods have many applications in geophysics, few real seismic datasets are available for benchmarking DL models, especially for denoising real data, which is one of the main problems in seismic data processing scenarios in the oil and gas industry. This article presents a benchmark dataset composed of synthetic seismic data corrupted with noise extracted from a filtering process implemented on real data. In this work, a comparison between two well-known DL-based denoising models is conducted on this dataset, which is proposed as a benchmark for accelerating the development of new solutions for seismic data denoising. This work also introduces a new evaluation metric that can capture small variations in model results. The results show that DL models are effective at denoising seismic data, but some issues remain to be solved.