NH004
AI-Driven Approaches to Monitoring Fault Activity and land subsidence in Urban Environments
AI-Driven Approaches to Monitoring Fault Activity and land subsidence in Urban Environments
Session ID#: 250286
Session Description:
This session explores the integration of artificial intelligence (AI), geodesy, and remote sensing for detecting, monitoring, and modeling land subsidence and fault activity in urban settings. As urban areas rapidly expand, increased infrastructure load and groundwater extraction accelerate subsidence. Additionally, tectonic activity and sediment compaction further contribute to surface deformation, highlighting the need for innovative hazard assessment methods. We welcome contributions applying AI and machine learning with GNSS and InSAR data to enhance time series interpretation, detect deformation patterns, and forecast subsidence or fault behavior. Topics may include automated classification, urban hazard mapping, deep learning, and multi-sensor data fusion. This session encourages interdisciplinary studies that link tectonics, geodesy, engineering geology, remote sensing, and AI for risk assessment in urban infrastructure. Case studies from high-density or data-scarce regions are especially encouraged, particularly in the Middle East, Central Asia, Southeast Asia, and Latin America
Co-Sponsor(s):
- EP - Earth and Planetary Surface Processes
- G - Geodesy
- IN - Informatics
- S - Seismology
Index Terms:
4315 Monitoring, forecasting, prediction [NATURAL HAZARDS]
4325 Megacities and urban environment [NATURAL HAZARDS]
4333 Disaster risk analysis and assessment [NATURAL HAZARDS]
4337 Remote sensing and disasters [NATURAL HAZARDS]
Primary Convener: Ava Osman Pour, Bu-Ali Sina University, Hamedan, Iran
Conveners: Mimmo Palano, Università degli studi di Palermo, Palermo, Italy, Franz Antezana Lopez, Beihang University, Beijin, China and Peyman Heidarian, School of Transportatting Science and Engineering,Beihang University, Beijing, China
See more of: Natural Hazards