Advances and Applications of Distributed Optical Fiber Sensing (DOFS) in Multi-scales Geoscience Problems

In recent years, distributed optical fiber acoustic sensing (DAS) technology has been increasingly used for vertical seismic profile (VSP) exploration. Even though this technology has the advantages of high spatial resolution, strong resistance to high temperature and pressure variations, long sensing distance, DAS seismic noise has expanded from random noise to optical abnormal noise, fading noise and horizontal noise, etc. This seriously affects the quality of the seismic data and brings huge challenges to subsequent imaging, inversion and interpretation. Moreover, the noise is more complex and more difficult to simultaneously suppress using traditional methods. Therefore, for the purpose of effectively improving the signal-to-noise ratio (SNR) of DAS seismic data, we introduce a denoising network named attention-guided denoising convolutional neural network (ADNet). The network is composed of four blocks, including a sparse block (SB), a feature enhancement block (FEB), an attention block (AB) and a reconstruction block (RB). The network uses different kinds of convolutions alternately to enlarge the receptive field size and extract global feature of the input. Meanwhile, the attention mechanism is introduced to extract the hidden noise information in the complex background. The network predicts the noise, and denoised data are obtained by subtracting the predicted results from the noisy inputs. In addition, we uniquely construct a large number of complex forward models for pure seismic data training set to enhance the network suitability. The combination design improves the denoising performance and reduces computational cost and memory consumption. The results obtained from both synthetic- and field data illustrate that the network has the ability to denoise the seismic images and retrieve weak effective signals better than conventional methods and common networks.

The importance of railway safety cannot be overemphasized; hence it requires reliable traffic monitoring systems. Widespread trackside telecommunication fiber-optic cables can be suitably deployed in the form of dense vibration sensors using Distributed Acoustic Sensing technology (DAS). Train-induced ground motion signals are recorded as continuous “footprints” in the DAS recordings. As the DAS system records huge datasets, it is thus imperative to develop optimized/stable algorithms which can be used for accurate tracking of train position, speed, and the number of trains traversing the position of the DAS system. In this study, we transform a 6-days continuous DAS data sensed by a 2-km cable into time-velocity domain using beamforming on phase-squeezed signals and automatically extract the position and velocity information from the time-beampower curve. The results are manually checked and the types of the trains are identified by counting the peaks of the signals. By reducing the array aperture and moving subarrays, the train speed-curve/motion track is obtained with acceptable computational performance. Therefore, the efficiency and robustness of our approach, to continuously collect data, can play a supplementary role with conventional periodic and time-discrete monitoring systems, for instance, magnetic beacons, in railway traffic monitoring. In addition, our method can also be used to automatically slice time windows containing train-induced signals for seismic interferometry.