Landslides are among the most widespread and destructive natural hazards. Effective monitoring and forecasting are crucial for risk management, yet traditional approaches remain limited by coarse observations, high cost, complex deployment requirements and analysis of large and heterogeneous datasets.
Recent advances in the Internet of Things (IoT), low-power sensor networks, real-time communication systems, and machine learning (ML) methods are providing the means to effectively monitor and understand landslide processes. IoT-based monitoring offers scalable, low-cost, and flexible solutions for continuous data acquisition in challenging environments, while ML enables the detection of patterns, early warning signals, and predictive modeling based on heterogeneous datasets (e.g., displacement, rainfall, soil water content, suction, pore water pressure). The use of these technologies is enabling innovative applications in landslide hazard assessment, operational early warning systems, and risk management.
This session focuses on contributions dealing with design, implementation, and application of IoT monitoring systems and machine learning methods for landslide studies. Test cases describing operational applications are particularly welcome, as well as studies dealing with promising recent innovations, even if still at an experimental stage.
Topics of interest include, but are not limited to:
● design and deployment of IoT-based monitoring networks
● processing of geotechnical, hydrological, and meteorological data in IoT/ML frameworks
● methods for the analysis of complex datasets
● ML applications for landslide detection and forecasting
● real-time monitoring and analysis.