The rapid growth of SAR constellations, continental-scale ground-motion services, cloud computing, and artificial intelligence is transforming radar remote sensing from specialist analysis toward scalable and operational monitoring. Beyond interferometric phase and displacement time series, SAR amplitude observations can support rapid change detection and contextual interpretation of surface processes.
A key challenge is no longer only how to generate interferograms or deformation maps, but how to convert large volumes of radar observations into reliable, interpretable, predictive, and actionable information. Important barriers include automated quality control, large-scale processing, complex spatio-temporal interpretation, model transferability, uncertainty quantification, forecasting, and integration with operational decisions.
This session focuses on the transition from scalable SAR and InSAR processing to predictive and actionable ground-motion intelligence. We welcome contributions on AI and machine learning for SAR amplitude and InSAR processing; scalable, cloud-native, high-performance, and near-real-time workflows; automated detection, classification, attribution, and change-point analysis of radar image stacks and deformation time series; physics-informed, explainable, and uncertainty-aware learning; deformation forecasting, anomaly detection, early warning, and alert generation; and integration with GNSS, optical, geological, meteorological, infrastructure, and in-situ data.
Applications may include subsidence, landslides, infrastructure, mining, groundwater or hydrocarbon extraction, volcanic and seismic deformation, and other natural or human-induced ground-motion processes. We also encourage studies on validation, benchmarking, reproducibility, transferability, failure modes, and operational implementation.
Particular emphasis is placed on contributions that critically assess when AI adds measurable value, quantify uncertainty and limitations, and demonstrate how SAR- and InSAR-derived information can support transparent, timely, and defensible decisions for hazard assessment, infrastructure management, early warning, and risk-informed decision-making.