Efficient Processing of Distributed Acoustic Sensing Data Using a Deep Learning Approach

Automatic processing of fiber-optic distributed acoustic sensing (DAS) data is highly desired in many applications. In particular, efficient algorithms for detection of events of interest and their classification are of the utmost importance. Classical machine learning algorithms are problematic as they require hand-crafted features to be extracted and their adaptation to other sites or other DAS systems is difficult. In contrast, artificial neural networks (ANN) learn by themselves how to extract relevant features and signatures in the training phase. The training phase, however, necessitates the generation of a large database of tagged events (train-set). In this paper, we describe a new method for generating train-sets for DAS ANNs and its experimental testing. The method is based on the generative adversarial net (GAN) methodology. The use of a GAN facilitated an efficient generation of train-sets from a computer simulation of the DAS system. The train-set was then used to train an ANN, which processed experimental data from 5- and 20-km sensing fibers. Significant improvement in performance was obtained with respect to ANN trained by only simulation data or experimental data.