SeisBench DAS improves machine learning for fiber optic seismic sensing
SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing
Machine Learning
Summary
Processing data from fiber optic cables used to detect earth vibrations is hard because different datasets and methods don’t easily work together. To fix this, the authors created SeisBench DAS, a tool that sets common rules for organizing data and models in this field. Their framework makes it easier for scientists to test and use machine learning on these vibrations, helping connect developers with people who analyze the data. SeisBench DAS also supports future improvements by being open and flexible.
Distributed Acoustic SensingFibre optic sensingMachine learningSeismologyDeep learning modelsData standardizationBenchmark datasetsPyTorchSeisBenchGeophysical studies
Authors
Jannes Münchmeyer, Han Xiao, Frederik Tilmann
Abstract
Fibre optic sensing, such as distributed acoustic sensing (DAS), has become a widespread technology for geophysical studies. To process the large-scale datasets produced by DAS, several machine learning methods have been proposed. However, without standardization of data and models, these methods lack comparability and interoperability. This introduces a gap between model developers and practitioners analyzing DAS data and inhibits adoption of deep learning for DAS. To address these limitations, here we present SeisBench DAS, an extension to the SeisBench library for machine learning in seismology. SeisBench DAS defines standard formats for DAS benchmark datasets, including standardised metadata and labels, and DAS models. It builds on the xdas framework for data ingestion and virtual array handling, and on PyTorch for reading and applying the machine learning models. Importantly, SeisBench provides an engine to efficiently apply deep learning models to diverse formats of DAS data, bridging the gap between model developers and practitioners. SeisBench DAS is designed as an open and extensible framework, allowing to easily incorporate future developments in deep learning for DAS.