Improving signal fidelity for deep learning‐based seismic interference noise attenuation

Abstract

Deep learning has shown a considerable potential to significantly improve processing efficiency but has not yet been widely deployed to production projects of seismic signal separation such as seismic interference attenuation. The main reasons are: First, the industry has high standards for signal fidelity, which are critical for the success of subsequent seismic imaging, and deep neural network methods have not yet matched the required level; second, the network's interpretability issue has affected many geophysicists and sponsors' trust in the deep learning technique. To develop deep neural network methods towards the end of benefiting real-world production, we first attempt to better understand their performance, especially in how they make use of local and global features of the data. A novel quantitative research of the overall network model behaviour on synthetic data is conducted. We simulate three types of coherent seismic data components in the shot domain, blend them together and then train a network to separate them. In this process, random noise, a component having only learnable local features, is selectively injected into the network's training pairs. Three network models sharing the same architecture are trained individually, and they show distinctive behaviours when applied to the same test data. Step-by-step analysis of each of them reveals that training the network with additional random noise injected into both the input and the output channel of the desired signal can lead to a decent prediction of the coherent noise based on good learning of the global features and, in the meantime, preserve almost all the data information from being lost. We propose this key lesson we learnt as a new method to improve the network's signal fidelity for shot-domain seismic interference attenuation, which is essentially a signal separation task. Its effectiveness is demonstrated on field data from Africa with a comparison to a conventional physics-based seismic interference attenuation method used in production.

Deghosting dual‐component streamer data using demigration‐based supervised learning

“…Machine learning and, more specifically, artificial neural networks have recently been used for various processing steps such as swell noise attenuation (Zhao et al., 2019), debubbling (de Jonge, Vinje, Poole, et al., 2022), seismic inference noise attenuation (Sun et al., 2019; Sun & Hou, 2022) and interpolation (Greiner et al., 2019; Hlebnikov et al., 2022). Several papers have also described the use of neural networks for deghosting (Almuteri & Sava, 2021; de Jonge, Vinje, Zhao, et al., 2022; Peng et al., 2021; Vrolijk & Blacquiere, 2020).…”

Earth and environmental sciences

“…It is also a useful tool for estimation of the potential detecting power of a specific acquisition system for a given velocity structure of the medium. Most existing techniques for calculating illumination intensity distributions can be divided into two categories: one is based on ray tracing methods (Berkhout, 1997;Schneider, 1999;Bear et al, 2000;Muerdter et al, 2001aMuerdter et al, , 2001b; and the other based on wave equation methods (Wu & Chen, 2002;Xie et al, 2006;Wu & Chen, 2006;Sun et al, 2007). The ray tracing is quite efficient and inexpensive.…”