Cascadia Daily GNSS Time Series Denoising: Graph Neural Network and Stack Filtering

Precise Global Navigation Satellite System (GNSS) time series have greatly advanced tectonic studies, particularly in detecting transient deformation signals like slow slip events (SSEs). However, GNSS position data can be noisy, impacting the accuracy of analyses. Traditional denoising methods often struggle with spatially heterogeneous and evolving networks. This study introduces a novel Graph Neural Network (GNN) approach to denoise GNSS time series, effectively managing network heterogeneity and varying station availability. GNNs are robust against temporal gaps, making them suitable for GNSS data. Applied to daily time series for the Cascadia Region processed by the University of Nevada Reno and Central Washington University, our method reduced common-mode noise by more than 70% and 30% on horizontal components, in the two datasets respectively, significantly enhancing surface displacement measurements and slow slip events (SSE) source property estimation. We compared the GNN approach with three simple stack filtering methods, which performed comparably in many situations but are more sensitive to parameter choices. For all methods, substantial noise reduction removes artifacts that could impact geophysical interpretations. Our findings suggest that GNN-based denoising offers a robust, adaptive solution for heterogeneous GNSS networks, enhancing accuracy in tectonic and volcanic process studies, but stack filtering approaches might still outperform the machine learning technique depending on the application.