Her research focuses on understanding environmental and ecological processes through physical sensing and data-driven analysis. A central theme is environmental seismology, where acoustic and elastic signals are used to study dynamic Earth surface processes and their relevance for ecosystem and biodiversity dynamics across scales.

Methodologically, her work centers on advanced time-series analysis and machine learning, with an emphasis on denoising, prediction, explainable AI, and image segmentation and tracking. She works with a range of data sources, including seismic measurements, satellite, drone, and time-lapse imagery, and uses Earth system data cubes as a common data format to organize and analyze multimodal environmental data. A key research direction is the development of machine learning tooling that enables scalable, interpretable, and, in the long term, integrated analysis of heterogeneous Earth system datasets.

ORCID

Google Scholar