Unravelling information on impactful geo-hydrological hazard events with HazMiner, a multilingual text mining method developed through a global scale coverage application
- 1Vrije Universiteit Brussel (Brussels, Belgium)
- 2Royal Museum for Central Africa (Tervuren, Belgium)
Abstract
The incidence and impacts of geo-hydrological hazards such as floods, flash floods and landslides are changing globally due to anthropogenic environmental changes and increased exposure driven by population growth. Reliable datasets on geo-hydrological hazards are essential to deepen our understanding of these hazards and their impacts. However, existing geo-hydrological hazard datasets contain data gaps leading to biased interpretations, especially in low- and lower-middle-income countries where populations are commonly the most impacted. Text mining offers new opportunities in documenting geo-hydrological hazards by automatically extracting information from large text corpora. Despite its potential, current methodologies are not adapted to improve documentation in data-scarce contexts. We introduce HazMiner, a paragraph-based text mining method designed to document the location, timing and impact of geo-hydrological hazards through transformer-based natural language processing models across multiple languages and at various scales. Applied here globally on 6 366 905 news articles published from 2017 through 2024 in 58 languages, HazMiner extracted 15 313 flood, 6836 landslide and 2258 flash flood events with a known location and time information and, in some cases, impact data. Compared to existing hazard datasets, HazMiner significantly improved hazard documentation, reducing the data gaps in many regions, especially in low- and lower-middle-income countries. This new versatile multilingual method and its dataset advance the accessibility and use of text mined natural hazard data.
Versions
Related
- Robust identification of impactful boreal summer anticyclones
- Attribution of the most impactful heatwaves, cyclones and floods hitting Africa in the period 2019-2024 to climate change
- Accounting for spatial structure and surface conditions through in situ soil spectral information: application to soil organic carbon modelling
- Benchmarking conditioners in Liang–Kleeman Information Flow: application to land–atmosphere interactions in humid forests
- Setting Up Living Labs for Water Reuse in Water-Stressed Social-Hydrological Systems
BibTeX
@article{valkenborg2026unravelling,
title = {{Unravelling information on impactful geo-hydrological hazard events with HazMiner, a multilingual text mining method developed through a global scale coverage application}},
author = {Bram Valkenborg and Olivier Dewitte and I Wayan Gita Krishna Dananjaya and Benoît Smets},
journal = {Natural Hazards and Earth System Sciences},
year = {2026},
month = nov,
doi = {10.5194/nhess-26-5507-2026},
url = {https://nhess.copernicus.org/articles/26/5507/2026/},
note = {CC BY 4.0},
}
RIS
TY - JOUR
TI - Unravelling information on impactful geo-hydrological hazard events with HazMiner, a multilingual text mining method developed through a global scale coverage application
AU - Bram Valkenborg
AU - Olivier Dewitte
AU - I Wayan Gita Krishna Dananjaya
AU - Benoît Smets
PY - 2026
DA - 2026/11/02
JO - Natural Hazards and Earth System Sciences
DO - 10.5194/nhess-26-5507-2026
UR - https://nhess.copernicus.org/articles/26/5507/2026/
AB - The incidence and impacts of geo-hydrological hazards such as floods, flash floods and landslides are changing globally due to anthropogenic environmental changes and increased exposure driven by population growth. Reliable datasets on geo-hydrological hazards are essential to deepen our understanding of these hazards and their impacts. However, existing geo-hydrological hazard datasets contain data gaps leading to biased interpretations, especially in low- and lower-middle-income countries where populations are commonly the most impacted. Text mining offers new opportunities in documenting geo-hydrological hazards by automatically extracting information from large text corpora. Despite its potential, current methodologies are not adapted to improve documentation in data-scarce contexts. We introduce HazMiner, a paragraph-based text mining method designed to document the location, timing and impact of geo-hydrological hazards through transformer-based natural language processing models across multiple languages and at various scales. Applied here globally on 6 366 905 news articles published from 2017 through 2024 in 58 languages, HazMiner extracted 15 313 flood, 6836 landslide and 2258 flash flood events with a known location and time information and, in some cases, impact data. Compared to existing hazard datasets, HazMiner significantly improved hazard documentation, reducing the data gaps in many regions, especially in low- and lower-middle-income countries. This new versatile multilingual method and its dataset advance the accessibility and use of text mined natural hazard data.
SN - 1684-9981
ER -