A multimodal CNN with interpretable value and temporal modulators predicts daily pluvial flood insurance claims at ~1 km across the 100 highest-claim US regions, outperforming tree baselines on dollar-weighted precision-recall.
James and Russ S
1 Pith paper cite this work, alongside 4 external citations. Polarity classification is still indexing.
1
Pith paper citing it
4
external citations · OpenAlex
fields
cs.LG 1years
2026 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
DELUGE: Towards Continental-Scale Daily Pluvial Flood Damage Prediction via Interpretable Conditioning on Foundation Model Embeddings
A multimodal CNN with interpretable value and temporal modulators predicts daily pluvial flood insurance claims at ~1 km across the 100 highest-claim US regions, outperforming tree baselines on dollar-weighted precision-recall.