Weak Signals Recovery of Downhole DAS With Scale-Weighted Nonlocal Selective Attention

The comprehensive requirements of effectively suppressing various noises, preserving signal amplitudes, recovering weak signals, balancing the effects between local and global, and reducing computational costs have always been the crucial task of data processing of downhole distributed acoustic sensing (DAS). Traditional methods, single-mechanism convolutional neural network (CNN) models, and training methods with a single patch size, due to their simplistic structures, limited data processing capabilities, and a large number of network layers often struggle to meet the aforementioned comprehensive requirements. In this article, using a progressive training method, we propose a novel nonlocal selective attention multiscale residual network (NSKMRNet). At its core lies an iterative multiscale residual block (MRB): multiple resolution convolution streams allow for the transfer of contextual information from the low-resolution stream to consolidate high-resolution features; parallel nonlocal contextual processing uses a distillation mechanism for extracting useful information, and weighted attention handling between adjacent scale streams for merging information. The feature maps selected from a randomly chosen training iteration clearly reflect the noise suppression process and the importance of iterative process. In experiments conducted on both synthetic and field DAS data, our method achieved a signal-to-noise ratio (SNR) improvement of around 30 dB, surpassing other methods. It maximally preserves signal amplitudes, resulting in minimal signal residuals in the amplified field records. Moreover, in terms of floating point operations (FLOPs) and training time, our method is within an acceptable range but significantly lower than more complex networks. The proposed network holds promise as a potentially valuable tool in meeting the comprehensive requirements for processing of downhole DAS data.