Bridging the gap between data generation and data comprehension in seismology: Towards new insights and improved understandings in seismology via Intelligent Data Analysis

• Antragsteller: Dr. Carsten Riggelsen
• Fachliche Zuordnung: Physik des Erdkörpers
• Förderung: Förderung von 2010 bis 2014
• Projektkennung: Deutsche Forschungsgemeinschaft (DFG) - Projektnummer 170386084

Pattern recognition, machine learning and data mining is a non-exhaustive list of research fields that collectively define the Intelligent Data Analysis (IDA) paradigm. It provides a wealth of non-trivial (“intelligent”) algorithms, techniques and methodologies aimed at analyzing empirical data. IDA is successfully being applied in various domains, resulting in new insights and improved understanding of many processes. In seismology, IDA has yet to be applied on a large scale, and widespread usage of IDA remains a challenge because, although IDA is generic in nature, it needs to be tailored to the specific needs of seismology. In general we aim for investigating the applicability of IDA in seismology and to demonstrate the advantages of so-called graphical models in seismology. In doing so, we specifically focus on graphical models in the context of (real-time) analysis, classification and data-mining of seismic data streams and the improvements graphical models can bring about in probabilistic seismic hazard analysis.

• DFG-Verfahren: Sachbeihilfen