Poststack Seismic Data Preconditioning via Dynamic Guided Learning

TL;DR

This paper introduces a dynamic guided learning approach for poststack seismic data preconditioning that improves noise attenuation and generalization across diverse datasets without relying on predefined statistical models.

Contribution

It proposes a novel two-process dynamic training method with domain adaptation via neural style transfer, enhancing seismic noise reduction and adaptability.

Findings

Outperforms state-of-the-art methods on synthetic and field data.

Effective in unknown noise domains and diverse geological settings.

Eliminates reliance on predefined statistical noise models.

Abstract

Seismic data preconditioning is essential for subsurface interpretation. It enhances signal quality while attenuating noise, improving the accuracy of geophysical tasks that would otherwise be biased by noise. Although classical poststack seismic data enhancement methods can effectively reduce noise, they rely on predefined statistical distributions, which often fail to capture the complexity of seismic noise. On the other hand, deep learning methods offer an alternative but require large and diverse data sets. Typically, static databases are used for training, introducing domain bias, and limiting adaptability to new noise poststack patterns. This work proposes a novel two-process dynamic training method to overcome these limitations. Our method uses a dynamic database that continuously generates clean and noisy patches during training to guide the learning of a supervised enhancement network. This dynamic-guided learning workflow significantly improves generalization by introducing variability into the training data. In addition, we employ a domain adaptation via a neural style transfer strategy to address the potential challenge of encountering unknown noise domains caused by specific geological configurations. Experimental results demonstrate that our method outperforms state-of-the-art solutions on both synthetic and field data, within and outside the training domain, eliminating reliance on known statistical distributions and enhancing adaptability across diverse data sets of poststack data.