SeisBench DAS standardizes machine learning for fibre optic sensing
SeisBench DAS: A machine learning framework for Distributed Acoustic Sensing
Machine Learning
Summary
Distributed Acoustic Sensing (DAS) uses fiber optic cables to detect vibrations, producing huge amounts of data. The authors created SeisBench DAS, a tool that makes it easier to use and compare machine learning models on DAS data by standardizing the data format and models. This helps experts who build models and those who analyze data work together more effectively. The tool is open and can incorporate new machine learning advances in the future.
What this means in practice
- •For geophysical data analysts: Process and analyze large-scale DAS data consistently using standardized machine learning models for improved data interpretation.
- •For infrastructure monitoring teams: Use a unified framework to deploy and evaluate deep learning models on DAS data for infrastructure health monitoring and anomaly detection.
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.