SOURCE-LINKED INTELLIGENCE

From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters

arXiv · AI, language, vision and robotics · article · Sep 20, 2026 · UTC

Disaster-risk-reduction archives describe hazard events in prose that databases such as EM-DAT (Delforge et al., 2025) cannot ingest directly. We present an LLM pipeline that generates candidate georeferenced event records using a controlled hazard vocabulary and fixed schema, retaining evidence for review. Applied to 10,000 documents from PreventionWeb, the knowledge hub managed by UNDRR, it produced 3,572 records from 1,913 documents across 24 hazard types and resolved 81% of location mentions to OpenStreetMap geometries. On 171 human-positive document windows from a stratified 217-document

Read original source ↗ Open in workspace

recordType

paper

region

Global