Hourly U.S.-wide flood simulation beyond the limits of traditional and data-driven models
Abstract
As increasingly-damaging floods can strike within hours of a storm and in ungauged reaches, hourly network-wide simulation has become critical societal infrastructure. Here we demonstrate a multi-timescale physics-embedded learning model which outperforms the United States' operational system and surpasses AI-based systems at flood peaks. Covering more than 800,000 river reaches of the conterminous U.S., the model elevates median hourly Nash-Sutcliffe efficiency at 2,831 gauges to 0.683 from 0.461 for the operational National Water Model v3.0, and narrows flood-peak timing errors from 7-8 hours to 4.5-6 hours. dHBV2.0MTS-MC captures 33% more >=50-year floods than NWM3.0 and 159% more than an operational LSTM baseline. Against recent AI models, overall hourly skill is comparable while rare-flood accuracy is distinctly higher, with relative peak-magnitude error reduced by 34% for >=100-year floods. It combines long-term hydrologic context, short-term shocks, and infiltration excess to resolve extraordinary hourly peaks not visible on a daily plot. Process-model parameters and hourly discharge are produced for every reach, seamlessly covering the continent at 7.2 km2 median resolution. This candidate for the next-generation National Water Model sets a new operational accuracy level for national-scale flood prediction.
Related
- Skillful Data-Driven Subseasonal Soil Moisture Forecasting: Prospects and Limits for Flash Drought Prediction
- Comparison of machine learning and spatial interpolation methods for hourly rainfall data imputation in the Oliwski Stream catchment
- A stochastic model of continuous hourly areal rainfall series applied to a wide range of French catchments
- AeroTrans: Hourly AOD retrieval over land from MSG-1/SEVIRI imagery integrating Transformer and transfer learning
- A novel hourly PM2.5 concentration prediction model using IMSTL-FVMD-HLDT hybrid architecture with Adam optimized by Schrödinger search strategy
BibTeX
@misc{yang2026hourly,
title = {{Hourly U.S.-wide flood simulation beyond the limits of traditional and data-driven models}},
author = {Wencong Yang and Leo Lonzarich and Yalan Song and Haoyu Ji and Ming Pan and Kathryn Lawson and Chaopeng Shen},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.06794},
eprint = {2609.06794},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.06794},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Hourly U.S.-wide flood simulation beyond the limits of traditional and data-driven models
AU - Wencong Yang
AU - Leo Lonzarich
AU - Yalan Song
AU - Haoyu Ji
AU - Ming Pan
AU - Kathryn Lawson
AU - Chaopeng Shen
PY - 2026
DA - 2026/09/06
PB - arXiv
DO - 10.48550/arxiv.2609.06794
UR - https://arxiv.org/abs/2609.06794
AB - As increasingly-damaging floods can strike within hours of a storm and in ungauged reaches, hourly network-wide simulation has become critical societal infrastructure. Here we demonstrate a multi-timescale physics-embedded learning model which outperforms the United States' operational system and surpasses AI-based systems at flood peaks. Covering more than 800,000 river reaches of the conterminous U.S., the model elevates median hourly Nash-Sutcliffe efficiency at 2,831 gauges to 0.683 from 0.461 for the operational National Water Model v3.0, and narrows flood-peak timing errors from 7-8 hours to 4.5-6 hours. dHBV2.0MTS-MC captures 33% more >=50-year floods than NWM3.0 and 159% more than an operational LSTM baseline. Against recent AI models, overall hourly skill is comparable while rare-flood accuracy is distinctly higher, with relative peak-magnitude error reduced by 34% for >=100-year floods. It combines long-term hydrologic context, short-term shocks, and infiltration excess to resolve extraordinary hourly peaks not visible on a daily plot. Process-model parameters and hourly discharge are produced for every reach, seamlessly covering the continent at 7.2 km2 median resolution. This candidate for the next-generation National Water Model sets a new operational accuracy level for national-scale flood prediction.
ER -