Noise Suppression of DAS Seismic Data by Attention-guided Multi-scale Generative Adversarial Network

Distributed fiber-optical acoustic sensing (DAS) is an emerging technology which uses optical fiber as a sensor for signal acquisition and recently has been applied to seismic exploration. Seismic records collected with DAS equipments are often contaminated with multi-component noise induced by complex causes and consequently affect the subsequent imaging, inversion, and even the interpretation work. Therefore, research on effective noise suppression algorithm in DAS seismic data has become a hot topic in geophysical prospecting. In this study, we proposed an attention-guided multi-scale generative adversarial network (AMGAN) based on the traditional GAN architecture and discussed its feasibility in multi-component DAS noise suppression. In AMGAN, multi-scale ideas are introduced to extract features of raw DAS data in different scales. Additionally, attention mechanism is imported and trained at each hierarchy to help extract and fuse the features from different scales. Overall, AMGAN, attributed to the inversely fused multi-scale features, can reveal more detailed reflected signal information in DAS data denoising task. Both synthetic and field DAS data experiments show that AMGAN can effectively remove the multi-component seismic noise in DAS data and recover the weak seismic events with advantage in clarity and continuity. © 2023 Society of Exploration Geophysicists.