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

An LLM pipeline that turns disaster-risk-reduction reports into georeferenced event records with a fixed schema and controlled hazard vocabulary. Applied to 10,000 PreventionWeb documents, it produced 3,572 records across 24 hazard types.

September 2026 · Camilla Andreozzi, Phuong-Anh Nguyen-Le, Zhijing Jin, Revati Mani