research
High-Water Marks Teach the Model Before the Peak
A fusion network trained on 5,689 field surveys predicts flood depth six hours ahead with 0.39-meter mean absolute error on sampled events.
Summary
A fusion network trained on 5,689 field surveys predicts flood depth six hours ahead with 0.39-meter mean absolute error on sampled events.
The dataset spans 39 events from 2011 through 2025 across 24 U.S. states and Puerto Rico, pairing USGS high-water marks with terrain, geospatial embeddings and 144 hours of meteorological forcing. At surveyed marks, the model reaches 0.39-meter mean absolute error six hours before peak, while a measured-water-level-minus-terrain baseline has 0.93-meter error. Attribution assigns 77 percent of the reduction to forcing. But on 11 held-out events, the model still separates flooded from rain-free cases while depth resolution collapses to an R-squared of 0.03. The authors therefore limit the reported skill to sampled regions and storms.
Why it matters
A fusion network trained on 5,689 field surveys predicts flood depth six hours ahead with 0.39-meter mean absolute error on sampled events.
Limits and context
No additional limitation was separately recorded.
Key claims
A fusion network trained on 5,689 field surveys predicts flood depth six hours ahead with 0.39-meter mean absolute error on sampled events.
Evidence: source-2026-11-04-015
Sources
- arXiv preprint 2611.05220, original v1arXiv · primary research
Corrections
No corrections have been recorded for this story.