Across-domains transferability of Deep-RED in de-noising and compressive sensing recovery of seismic data

TL;DR

This paper presents a workflow that enables transfer of deep learning operators from camera images to seismic data for de-noising and compressive sensing, overcoming domain bias and without retraining.

Contribution

The authors develop a transferability workflow that applies deep learning operators across domains, specifically from camera images to seismic data, using similar algorithms and optimization methods.

Findings

Effective transfer of deep learning operators demonstrated on simulated seismic data.

Workflow successfully applied to real-world seismic data for de-noising and compressive sensing.

Proposed method maintains performance without retraining or parameter tuning.

Abstract

In the past decade, deep learning algorithms gained a remarkable interest in the signal processing community. The availability of big datasets and advanced computational resources resulted in developing efficient algorithms. However, such algorithms are biased towards the training dataset. Thus, the transferability of deep-learning-based operators are challenging, especially when the goal is to apply the learned operator on a new dataset/domain. Lack of transferability of learned operator across domains hinders the applicability of deep learning algorithms in processing seismic data. Unlike camera images, the comprehensively labeled seismic datasets are not available. Moreover, from one task to another, the training parameters should be tuned. To remedy this shortcoming, we have developed a workflow that transfers the learned operator from the camera images to the seismic domain, without modifying its training parameters. The similarities in the algorithms and optimization methods in camera and seismic data processing allow us to do so. Accordingly, by incorporating feed-forward de-noising convolutional neural networks (DnCNN) in regularization by de-noising regularizer, we formulate two transferable optimization problems for de-noising and compressive sensing recovery of seismic data. Simulated and real-world data examples show the efficiency of our proposed workflow.