VLMs Map Urban Flooding, Identify 100k At-Risk New Yorkers Missed by Current Methods
2plus2make5 · x · 2026-08-28
A new paper in Nature Communications demonstrates using vision-language models (VLMs) to detect floods in large-scale street scene datasets. In New York City, the method identified flooded neighborhoods home to 100,000 people that current monitoring methods missed, highlighting VLMs' potential in environmental monitoring and urban disaster response.
Related event: VLM Maps Urban Flood Risk from Street View Imagery(2 posts)→
More from Research
- OrganicHAR at UbiComp 2026: Discovering Activities Sensors Can Actually Distinguish — mynkgoel · 2026-10-16
- Dev critiques compiling fast programs into slow neural nets: fun, but not useful — ctjlewis · 2026-10-16
- New paper uses revealed-preference methods to unpack why AI agents cooperate — brwilder · 2026-10-16
- Logit lens on a Beat Saber finetune reveals it reuses language grammar circuits — ctjlewis · 2026-10-16
- 128×128 record stands: how intermediate-work experiments foreshadowed reasoning models — ctjlewis · 2026-10-16
- TeamFusion: preference-based AI proxies debate to preserve minority views in team decisions — burkov · 2026-10-16