Distributed Acoustic Sensing (DAS) is a fiber-optic technology that transforms optical fibers into dense seismic arrays. When deployed on unused telecommunication fibers ("dark fibers”), DAS provides regularly spaced seismic measurements over tens of kilometers, offering the potential for seismic monitoring over large areas. This research is conducted within the RUBADO project (BMWE, FKZ 03EE4076A), in which DAS is deployed along multiple long-range fiber-optic cables in the Upper Rhine Graben. The goal is to investigate the potential of existing fiber-optic infrastructure for monitoring geothermal reservoirs and induced seismicity at regional scales.

Efficient DAS monitoring requires automated processing of the large volumes of data generated and reliable identification of transient seismic signals, such as microseismic events, within predominantly anthropogenic noise. In addition, the identification of periods of low anthropogenic noise is relevant for applications such as ambient seismic noise interferometry. Machine learning (ML) provides a promising approach for the automated detection and classification of seismic signals in DAS data. The objective of this research is therefore to develop, implement, and validate ML-based methods for improving signal detection and classification in DAS recordings, thereby contributing to the development of efficient monitoring approaches for geothermal reservoirs and induced seismicity, as well as broader seismic applications.

In this framework, the following tasks are expected:

• Data acquisition, signal pre-processing and classification
• Collect and organize datasets acquired within the RUBADO project,
• Perform multi-domain analysis of DAS waveforms in the time, frequency, and space–wavenumber domains (and other array-based representations where relevant),
• Develop robust pre-processing workflows (e.g., denoising and segmentation) tailored to DAS data characteristics.
• Identify and extract physically meaningful signal attributes and recurring waveform patterns that capture the variability of seismic and anthropogenic sources, forming the basis for machine learning feature spaces.

• Workflow integration for seismic monitoring and subsurface imaging:
• Integrate the developed processing and machine learning pipeline into the RUBADO analysis framework for near real-time or batch seismic monitoring,
• Enhance event detection, classification, and characterization workflows to improve signal interpretability in DAS data,
• Support improved subsurface imaging by providing cleaner, better-characterized input signals for further seismic processing (e.g., ambient noise analysis, interferometry, or velocity inversion).