Articles | Volume 28, issue 11
https://doi.org/10.5194/hess-28-2531-2024
https://doi.org/10.5194/hess-28-2531-2024
Research article
 | 
14 Jun 2024
Research article |  | 14 Jun 2024

Quantifying cascading uncertainty in compound flood modeling with linked process-based and machine learning models

David F. Muñoz, Hamed Moftakhari, and Hamid Moradkhani

Data sets

National Geophysical Data Center NOAA-NGDC https://www.ncei.noaa.gov/access/metadata/landing-page/bin/iso?id=gov.noaa.ngdc.mgg.dem:403

Global Inverse Tide Model TPXO 8.0 https://www.tpxo.net/global/tpxo8-atlas

Download
Short summary
Linking hydrodynamics with machine learning models for compound flood modeling enables a robust characterization of nonlinear interactions among the sources of uncertainty. Such an approach enables the quantification of cascading uncertainty and relative contributions to total uncertainty while also tracking their evolution during compound flooding. The proposed approach is a feasible alternative to conventional statistical approaches designed for uncertainty analyses.