Conference Agenda

This abstract presents a comprehensive research initiative aimed at advancing the utilization of Earth Observation (EO) data and associated methodologies for effective risk management in diverse geographical settings. Building upon the foundations laid by previous Dragon projects, namely Dragon-5 and Dragon-4, our project leverages multi-source remote sensing data to monitor and mitigate various hazards, including landslides, mining subsidence, infrastructure deformation, and city subsidence. Through collaborative efforts between European and Chinese researchers, this project seeks to stimulate scientific research by integrating techniques such as optical remote sensing, satellite Interferometric Synthetic Aperture Radar (InSAR), Lidar, Ground-Based Synthetic Aperture Radar (GBSAR), and numerical simulation.

Key objectives include advancing methodologies for hazard mapping, inventorying, monitoring, and early warning systems, with a particular focus on landslides and mining subsidence. The project aims to offer tangible examples of collaborative analysis addressing complex geological disasters, thereby contributing to informed decision-making processes. Additionally, the project facilitates knowledge exchange and shared expertise through enhanced technical communication channels between Europe and China.

Key findings resulting from this joint effort will be disseminated through publication in renowned scientific journals worldwide and presentation at international symposia and conferences. Furthermore, relevant outcomes will be shared with interested authorities to support evidence-based decision-making. In line with the project's collaborative spirit, opportunities for young scientists, including Postdoctoral researchers, MSc, and Ph.D. candidates, from collaborating institutions will be facilitated to conduct research work abroad, fostering academic growth and professional development within their respective institutions.

Overall, this project represents a significant advancement in the exploitation of EO data for risk management, stimulating collaborative scientific research, promoting knowledge dissemination, and supporting the development of the next generation of scientists in the field.

An earthquake is a natural and devastating hazard that causes enormous human and economic losses and disruption, its impact continues to grow globally. The aim of the project is to develop innovative data analytics using Generative Artificial Intelligence (AI) and deep predictive neural networks. These methods will be employed to analyze and detect anomalies from electromagnetic data observed by SWARM and CSES satellites, and the CSELF (Control Source Extremely Low Frequency) network for monitoring and studying earthquakes, which will be cross-examined by the seismic deformation analysis based on the high-quality SAR data over the affected regions acquired from the Sentinel-1A/1B satellites.

Railways, as a fundamental component of transportation infrastructure, play a vital role. However, over time, increased freight loads and fluctuating weather conditions may lead to issues such as cracks, deformations, and wear on the tracks. Furthermore, the instability of the geological environment surrounding railways can also impact the safety of railway operations.

Our goal is to utilize the capabilities of Synthetic Aperture Radar (SAR) interferometric (InSAR) technology, which is satellite-based and known for its extensive coverage and high accuracy, for railway monitoring. Our proposed methodology comprises several key parts: Utilizing a 3D ray-tracing approach to interpret the InSAR coherent points over railway tracks. Developing an InSAR sensitivity matrix to evaluate monitoring capabilities along railway lines accurately. Creating a fusion model enables precise InSAR deformation estimation by leveraging data from multiple platforms and orbits. Establishing metrics aimed at identifying anomalous railway deformations, achieved through integrating geodesy theory and deep learning techniques. These methods will be applied to monitor both the Dutch and China-Laos international railway systems. Through this project, we aim to develop a framework for railway monitoring and produce InSAR deformation data at the product level.