logo
ResearchBunny Logo
Self-organizing maps of typhoon tracks allow for flood forecasts up to two days in advance

Engineering and Technology

Self-organizing maps of typhoon tracks allow for flood forecasts up to two days in advance

L. Chang, F. Chang, et al.

Discover how researchers Li-Chiu Chang, Fi-John Chang, Shun-Nien Yang, Fong-He Tsai, Ting-Hua Chang, and Edwin E. Herricks have harnessed machine learning techniques to predict flood hydrographs from typhoon activity, allowing for critical early warnings and real-time insights into flooding risks in East Asia.

00:00
00:00
Playback language: English
Abstract
Typhoons are a major natural hazard in East Asia, causing unpredictable flooding. This paper presents a machine-learning method using self-organizing maps (SOM) to predict flood hydrographs up to two days in advance. The method analyzes projected typhoon tracks against historical data, clustering similar tracks to associate them with landscape topography and runoff. This allows estimation of water inflow into reservoirs, providing early warnings and real-time updates of expected flooding.
Publisher
NATURE COMMUNICATIONS
Published On
Apr 24, 2020
Authors
Li-Chiu Chang, Fi-John Chang, Shun-Nien Yang, Fong-He Tsai, Ting-Hua Chang, Edwin E. Herricks
Tags
typhoons
flood prediction
machine learning
self-organizing maps
hydrographs
East Asia
early warning
Listen, Learn & Level Up
Over 10,000 hours of research content in 25+ fields, available in 12+ languages.
No more digging through PDFs, just hit play and absorb the world's latest research in your language, on your time.
listen to research audio papers with researchbunny