AI-Enhanced Disaster and Health Threats Storylines

This dataset complements Health Threats and Disaster event data through generative AI techniques, including the use of Retrieval Augmented Generation (RAG) with the Europe Media Monitoring (EMM) service (https://emm.newsbrief.eu/overview.html), and Large Language Models (LLMs) from the GPT@JRC portfolio (https://gpt.jrc.ec.europa.eu/).
It draws from sources like the EM-DAT database (https://www.emdat.be/), augmenting each event with news-derived information in a storytelling fashion.
The dataset has been constructed using the EMM RAG service to retrieve relevant news chunks for each event data, transforming the unstructured news chunks into structured narratives and causal knowledge graphs using LLMs and text-to-graph techniques, linking health threats and disaster events to their causes and impacts.
The dataset enables decision-makers to better explore health threats and disaster dynamics, identify patterns, and simulate scenarios for improved response and readiness.