Subnational Geocoding of Global Disasters Using Large Language Models
This provides a scalable and reliable method for disaster risk assessment and reduction by enabling automated subnational geocoding without manual intervention, though it is incremental in applying LLMs to a known bottleneck in geospatial data processing.
The researchers tackled the problem of inconsistent and unstructured location data in global disaster databases by developing an automated LLM-assisted workflow that geocodes events using GPT-4o and cross-checks multiple geoinformation sources, resulting in the geocoding of 14,215 events across 17,948 unique locations from 2000 to 2024.
Subnational location data of disaster events are critical for risk assessment and disaster risk reduction. Disaster databases such as EM-DAT often report locations in unstructured textual form, with inconsistent granularity or spelling, that make it difficult to integrate with spatial datasets. We present a fully automated LLM-assisted workflow that processes and cleans textual location information using GPT-4o, and assigns geometries by cross-checking three independent geoinformation repositories: GADM, OpenStreetMap and Wikidata. Based on the agreement and availability of these sources, we assign a reliability score to each location while generating subnational geometries. Applied to the EM-DAT dataset from 2000 to 2024, the workflow geocodes 14,215 events across 17,948 unique locations. Unlike previous methods, our approach requires no manual intervention, covers all disaster types, enables cross-verification across multiple sources, and allows flexible remapping to preferred frameworks. Beyond the dataset, we demonstrate the potential of LLMs to extract and structure geographic information from unstructured text, offering a scalable and reliable method for related analyses.