Abstract: A computer-implemented method and system provide the ability to detect an earthquake. Distributed acoustic sensing (DAS) data is obtained. A deep neural network model that picks seismic phase arrival times on the DAS data is acquired. A semi-supervised learning approach is utilized to train the deep neural network model. The semi-supervised learning approach utilizes existing labels from a defined seismic dataset to generate pseudo labels on the DAS data. An earthquake is detected by applying the trained deep neural network model to new DAS data.

Abstract: A sensor system including an optical fiber comprising a first spatial channel and a second spatial channel, wherein the spatial channels are coupled and electromagnetic radiation propagates with different group velocities in each of the spatial channels. The sensor system further includes a source inputting the electromagnetic radiation into the first spatial channel at an input; and a detection system coupled to an output of the fiber, the detection system including a detector detecting transmission of the electromagnetic radiation coupled into the second spatial channel at different positions along the fiber between the input to the output, and generating a signal in response thereto; and a computer processing the signal to obtain a localized measurement of a physical parameter at one or more of the different positions along the fiber.