Disaster events: AI used "to build a more complete risk mapping in underrepresented contexts" (JRC)

"We present a dataset of over 3,000 global disaster events from 2014 to 2024, across 175 countries, spanning 26 disaster types and accounting for around 80% of global economic losses recorded by the Emergency Events Database (EM-DAT) over the same period", state the authors of the study "Disaster Storylines and Knowledge Graphs from Global News with Large Language Models and Retrieval-Augmented Generation", published on 17/03/2026 and featured on 05/05/2026 on the Joint Research Centre website.

The researchers used AI to gather global news and create a structured narrative of natural disasters that took place from 2014 to 2024 worldwide. It helped build a more complete picture of disaster events, especially in underrepresented regions of the world, and highlighted how one event can trigger other cascading events. The overall aim of the tool is to help make more informed policy decisions.

"The outputs were validated at a dedicated workshop in Brussels in June 2025, attended by disaster risk professionals from the Commission’s Directorate-General for Civil Protection and Humanitarian…