Attention-Based Neural Network for Erratic Noise Attenuation From Seismic Data With a Shuffled Noise Training Data Generation Strategy

Wang, Shaowen; Song, Peng; Tan, Jindong; He, Bingshou; Wang, Qianqian; Du, Guoning

doi:10.1109/tgrs.2022.3197929

Cited by 11 publications

(1 citation statement)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Deep learning (DL) based method shows the potential for denoising field seismic data and requires no pre‐processing. The most common used supervised DL‐based method for seismic denoising is convolutional‐based neural network (CNN), such as DnCNN (Sang et al., 2021; Zhang et al., 2017), U‐net (Sun et al., 2020), Generative adversarial network (Kaur et al., 2020; Yuan et al., 2020), ResNet (Ma et al., 2020) and attention‐based network (Wang et al., 2022). For addressing the problem of training set generation based on field data, unsupervised and self‐supervised denoising methods provide an approach for extracting the noise features without labelled noise‐free data (Birnie et al., 2021; Jeong et al., 2021; Liu, Birnie, et al., 2022; Liu, Deng, et al., 2022; Liu, Yue, et al., 2022; Sun et al., 2022; Zhao et al., 2022).…”

Section: Introductionmentioning

confidence: 99%

Deep learning for noise attenuation from the ocean bottom node 4C data

Wang

Tan

Song

et al. 2023

Geophysical Prospecting

View full text Add to dashboard Cite

The source vessel noise is a very common noise type in offshore seismic surveys. The state‐of‐art deep learning‐based methods provide an end‐to‐end framework for seismic data denoising. The denoising performance of a pretrained network is, however, highly dependent on the completeness of the training set. When training a denoising network with only field data, especially for attenuating erratic noise, it is hard to obtain a noise‐free data as the training target for the network. Transfer learning, by combining the synthetic and field data, is an alternative solution for improving the generalization capabilities of the network, although being able to model such erratic noise represents also a challenge. Although the denoising results by traditional methods are not accurate enough for creating a complete training set, the features in residual noise by subtracting the denoised data from noisy data are enough for the network to learn. Considering the aforementioned factors, we develop a deep learning‐based workflow for the attenuation of the erratic source vessel noise from ocean bottom node 4C data. Instead of using denoising results directly, we use the conventional methods to extract noise and add them to the high signal‐to‐ratio region of the field data. The created noisy dataset is different from the original noisy data in noise regions; thus, the pretrained network can also be used for predicting the same original data. The denoising results of synthetic and field data all show that even the network is trained on a noisy labelled dataset, we still can obtain high signal‐to‐noise ratio denoising result. Besides, when compare with the results by filtering‐based methods, our proposed method can attenuate the vessel noise more effectively and preserve the near offsets reflections.

show abstract