Nonideal Phase Error Compensation Based on Global-Aware 3-D U-Net for GNSS-InSAR

Global Navigation Satellite System (GNSS)-InSAR employs ground-based fixed receivers to simultaneously capture scene reflection signals from multiple navigation satellites, enabling 3-D deformation monitoring. However, asymmetric multistatic configurations introduce various nonideal interferometric phase errors, while the system's relatively low SNR and resolution further exacerbate the challenges of error compensation. This article proposes a GNSS-InSAR nonideal phase error compensation method based on a globally aware 3-D U-Net. To overcome the constraint of scarce training data, a simulated dataset was generated by modeling deformation processes through four temporal patterns and a six-parameter spatial model. Various nonideal errors were incorporated into the dataset based on the constructed signal model. To achieve spatiotemporal coherence across the entire scene, the network incorporates a global-aware module, employs a 2-D-3-D hybrid encoding-decoding mechanism, and adopts an alternating training strategy that balances local extremum points with global accuracy. Experimental validation was conducted across natural slopes and highway bridges covered by eight BeiDou Inclined Geosynchronous Orbit (IGSO) satellites. Measurement accuracy was assessed using differential GNSS positioning data, demonstrating the network's exceptional performance within GNSS-InSAR systems. This study pioneers the application of a globally aware 3-D U-Net for GNSS-InSAR phase error compensation, significantly enhancing 3-D deformation monitoring accuracy. It outperforms conventional methods in both landslide and bridge field data, demonstrating strong practical utility and scalability potential.