Conference Agenda

Geohazard monitoring plays a crucial role in proactively addressing and mitigating the risks associated with natural disasters, thereby safeguarding human lives, critical infrastructure, and fostering sustainable development in vulnerable regions. The escalating occurrences of land subsidence and landslides globally present a substantial hazard to human settlements and vital infrastructure, necessitating immediate attention and mitigation strategies. Effectively managing the risks associated with geohazards and reducing their impacts requires a thorough assessment of displacement rates and a comprehensive understanding of their underlying mechanics. Integration of diverse techniques and sensor modalities contributes significantly to enhancing the efficacy of these monitoring efforts. This study presents key findings pertaining to the collaborative project "Earth observation for seismic hazard assessment and landslide early warning system." (ID 59339), a joint initiative between the European Space Agency (ESA) and the Chinese Ministry of Science and Technology (MOST) under the Dragon-5 program. In the preceding year, the research team has principally concentrated on two primary domains: a) harnessing Earth Observation (EO) data to monitor land subsidence induced by mining activities and groundwater extraction, involving the computation of mining exploitation features, and the assessment of flooding potential; and b) integrating various sensors, diverse remote sensing techniques, and in situ data to monitor landslides in mining and reservoir regions, entailing the identification of triggering factors and the modeling of specific landslides. The outcomes of this study are centered on specific vulnerable regions in China, Spain and Turkey, offering valuable insights to guide current and future scientific endeavors directed at the surveillance and management of landslides and land subsidence, along with the assessment of associated risks.

The accurate detection and comprehension of seismic anomalies from electromagnetic data observed by Swarm satellites present ongoing challenges within the fields of earthquake study and electromagnetism. This study employs Long Short-Term Memory (LSTM) networks, renowned for their adeptness in managing time series data, alongside TIMEGAN (generative adversarial network), a specialized generative model for time-series generation, to identify seismic anomalies within the Swarm satellite datasets. While LSTMs demonstrate commendable predictive capabilities across numerous cases, the anomaly detection using LSTM yields a notable number of false positives. Conversely, TIMEGAN models encounter difficulties in generating synthetic data, often resulting in non-informative or repetitive values. These findings underscore both the promise and hurdles associated with the application of deep learning techniques to electromagnetic data gathered by satellites.

Despite these challenges, the integration of LSTM and TIMEGAN outputs remains an unexplored avenue, offering significant potential for future research endeavors. Furthermore, this report will present the results obtained through integrating tectonic background information derived from EU Sentinel 1 data, in particular possible impact of the tectonic background in detecting seismic anomalies, emphasizing the potential of deep learning methodologies in uncovering seismic precursors from satellite data. Nevertheless, these findings underscore the imperative need for further refinement and continued research in this field to enhance the efficacy and reliability of seismic anomaly detection and understanding.