This webinar presents an AI-driven approach to time-series Interferometric Synthetic Aperture Radar (InSAR) for monitoring and understanding Earth surface deformation and supporting geohazard assessment. It will provide an overview of the principles of InSAR and multi-temporal analysis, including the extraction and interpretation of deformation patterns from satellite radar observations over time.

The webinar will explore how Artificial Intelligence and Machine Learning can be integrated with InSAR time-series techniques to improve the detection, characterization, classification, and prioritization of deformation signals and anomalous areas. Particular attention will be given to AI-based approaches for identifying persistent and emerging deformation hotspots, distinguishing significant deformation patterns from noise and measurement uncertainties, and transforming large-scale satellite observations into actionable information.

Practical examples will be presented to demonstrate the potential of combining Sentinel-1 SAR data, time-series InSAR processing, and AI techniques for monitoring phenomena such as land subsidence, ground instability, landslides, and other geohazard-related deformation processes. The webinar will also discuss challenges related to temporal variability, atmospheric effects, spatial and temporal resolution, data quality, and the generalization of AI models across different geographic and environmental conditions.

Finally, the webinar will highlight the potential of AI-driven InSAR as a scalable Earth Observation framework for continuous deformation monitoring, early detection of abnormal surface movements, geohazard assessment, and the development of intelligent early-warning and decision-support systems.