Methodological study demonstrates automated AI-driven extraction of diachronic hazard data, indicating improved disaster risk reduction and spatial data infrastructure accessibility.
Natural hazards are among the most frequent threats to humanity, causing significant societal and economic impacts. Geospatial data infrastructures support disaster risk reduction and urban resilience. However, disaster data are highly dispersed, heterogeneous, and distributed; a unified data repository is not available and its conventional development requires substantial time and resources. This study presents a workflow to adapt and utilize AI tools to extract semantically classified and structurally organized diachronic data on natural hazards, to develop a unified spatial data infrastructure and a web-based tool for accessing the disaster database. The presented method has been successfully applied in Greece.
No takes yet. Share an insight, caveat, or question.
Tsoutsos et al. (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: