Nature paper uses VLMs to map urban flooding

2plus2make5 · x · 2026-08-28

A new paper in Nature Communications demonstrates a method to map urban flooding by using vision-language models (VLMs) to detect floods in large-scale street scene datasets.

In New York City, the approach identified flooded neighborhoods housing 100,000 people that were missed by current methods. This highlights the potential of VLMs in environmental monitoring and disaster response.

Related event: VLM Maps Urban Flood Risk from Street View Imagery(2 posts)→

Original post →

More from Research

Research channel →