Land subsidence is one of the most critical geohazards threatening urban and industrial regions worldwide. This session highlights the integration of artificial intelligence (AI), geodesy, and remote sensing for the detection, monitoring, and modeling of surface deformation, with a particular focus on subsidence.
Subsidence results from both natural processes (e.g., tectonic activity, sediment compaction) and human activities (e.g., groundwater and hydrocarbon extraction, urban expansion). These complex drivers call for innovative approaches to hazard assessment, risk forecasting, and mitigation.
We invite contributions from data-rich and data-scarce regions alike, especially those employing AI and machine learning with GNSS and InSAR observations to improve time series interpretation, identify deformation patterns, and forecast subsidence trends. Topics of interest include automated classification, hazard mapping, deep learning, and multi-sensor data fusion. Interdisciplinary studies bridging tectonics, geodesy, engineering geology, remote sensing, and AI for enhanced risk assessment are strongly encouraged.