Seismic erratic noise attenuation using unsupervised anomaly detection

Abstract

This study introduces a new attribute to identify seismic erratic noise, i.e. outlier, in the context of unsupervised anomaly detection and is defined as local outlier probabilities. The local outlier probabilities calculate scores of degrees of isolation, i.e. outlier‐ness, for each object in a data set, which represents how far an object is deviated from its surrounding objects. Since the local outlier probabilities combines a density‐based outlier detection method with a statistically oriented scheme, its scoring system provides regularized outlier‐ness, which is an outlier probability, to be used for making a binary decision to do inclusion or exclusion of an object; such a decision only requires a simple and straightforward threshold on a probability. Based on the binary decision that flags outliers versus non‐outliers, local outlier probabilities‐denoising workflows are developed by combining multiple steps to complete an application of the local outlier probabilities to attenuate seismic erratic noise. Higher stability and improved robustness in the detection and rejection of seismic erratic noise have been achieved by implementing moving windows and decision tree‐based processes. To avoid loss of useful signal energy, signal enhancement applications are additionally suggested. Numerical experiments on synthetic data investigate the applicability of the proposed algorithms to seismic erratic noise attenuation. Field data examples demonstrate the feasibility of a local outlier probabilities‐denoising application as an effective tool in seismic denoising portfolio.

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

“…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). Besides, Mosser et al (2022) compared the traditional, supervised and unsupervised denoising methods in the context of machine learning.…”

“…Besides, Mosser et al (2022) compared the traditional, supervised and unsupervised denoising methods in the context of machine learning. The aforementioned methods can also be incorporated into conventional methods for removing the noise more accurately (Jeong et al, 2021;Tian et al, 2022).…”