Articles | Volume 25, issue 7
https://doi.org/10.5194/nhess-25-2421-2025
https://doi.org/10.5194/nhess-25-2421-2025
Research article
 | 
21 Jul 2025
Research article |  | 21 Jul 2025

An automated approach for developing geohazard inventories using news: integrating natural language processing (NLP), machine learning, and mapping

Aydoğan Avcıoğlu, Ogün Demir, and Tolga Görüm

Model code and software

tr-news-scraper: Scrape Turkish news articles Ogün Demir and Aydoğan Avcıoğlu https://github.com/demirogun/tr-news-scraper

Download
Short summary
We demonstrate an approach for the development of inventories from internet sources to geolocalize geohazard incidents. We created a tool that autonomously gets news, processes it using natural language processing, and then builds inventories. Consequently, we present spatiotemporal inventories for geohazards, resulting in a total of 13 940 incidents between 1997 and 2023 in Türkiye. Our alternative and easy-to-implement development inventory method aids geohazard management and resilience.
Share
Altmetrics
Final-revised paper
Preprint