Random-noise denoising for turnaround-fibre DAS-VSP data via the Noise2Noise framework

Summary In this study, we develop a deep learning-based approach for denoising raw distributed acoustic sensing (DAS)-vertical seismic profiling (VSP) data. The data were acquired using vibroseis sources at borehole sites in Dangu-ri and Janghang-ri, Gyeongju, Republic of Korea. The proposed workflow based on the Noise2Noise (N2N) framework has two key features. First, to ensure that a denoising model reflects site-specific noise characteristics rather than relying on pre-trained external datasets, the N2N network is trained directly on field data from the same site to which it is applied. Second, rather than applying denoising only after correlation, we perform denoising directly on the raw DAS records before correlation with the vibroseis sweep. This approach produces both denoised raw records and their corresponding correlated shot gathers, which is advantageous for field quality control, immediate operational decisions, and the flexibility to reprocess data from the raw-data domain. Once the raw sweep records are transformed into correlated shot gathers, the processing workflow does not provide a practical route back to the original raw DAS records; therefore, pre-correlation denoising retains greater processing flexibility. At the Gyeongju sites, DAS fibres were deployed in a turnaround configuration, which yields symmetric data that enable the construction of training datasets by cutting and flipping traces around the midpoint. This strategy provides corresponding pairs of seismic records that share the same signal but have independent background noise, enabling efficacious N2N training without requiring clean labels. The performance is evaluated through three approaches: 1) qualitative assessment focusing on amplitude suppression and spatial noise suppression trends; 2) quantitative analysis based on a trace-based signal-to-noise ratio metric; and 3) spectral analysis of the suppressed noise. In addition, the effect of training data discrepancies on denoising performance is investigated by evaluating how models trained on datasets with different offset ranges and acquisition sites generalise to unseen data configurations. Lastly, the N2N-based denoising method is compared against the self-supervised deep learning techniques (i.e., Noise2Void and blind-spot network), as well as conventional techniques such as stacking and band-pass filters. These results demonstrate that N2N-based denoising provides an effective way for improving the quality of field DAS-VSP data.