Deep learning with upstream-aware terrain representations and rainfall adapter for generalizable pluvial flood prediction
Authors:
- Thomas LutonskyTLThomas Lutonsky
- Viktor BirschitzkyVBViktor Birschitzky
- Stefan JeschkeSJStefan Jeschke
- Andreas Buttinger-KreuzhuberABAndreas Buttinger-Kreuzhuber
- Nils WandelNWNils Wandel
- Daniel CornelDCDaniel Cornel
- Viola HaaseVHViola Haase
- Reinhard KleinRKReinhard Klein
- Jürgen WaserJWJürgen Waser
- Michael WimmerMWMichael Wimmer
Open Access
- 25 September 2026
- journal article
- Published by Elsevier in Journal of Hydrology
- Vol. 680
Abstract
No abstract availableFunding Information
- Wirtschaftsagentur Wien
- Amt der Vorarlberger Landesregierung
This publication has 31 references indexed in Scilit:
- Drowning overconfidence with uncertainty: mitigating deep learning overconfidence in flood depth super-resolution through maximum entropy regularizationStochastic Environmental Research and Risk Assessment, 2025
- A 1D-2D dynamic bidirectional coupling model for high-resolution simulation of urban water environments based on GPU acceleration techniquesJournal of Cleaner Production, 2023
- Fast simulation and prediction of urban pluvial floods using a deep convolutional neural network modelJournal of Hydrology, 2023
- Generalizing rapid flood predictions to unseen urban catchments with conditional generative adversarial networksJournal of Hydrology, 2023
- An integrated GPU-accelerated modeling framework for high-resolution simulations of rural and urban flash floodsEnvironmental Modelling & Software, 2022
- Data-driven rapid flood prediction mapping with catchment generalizabilityJournal of Hydrology, 2022
- U-FLOOD – Topographic deep learning for predicting urban pluvial flood water depthJournal of Hydrology, 2021
- Explainable Artificial Intelligence (XAI): Concepts, taxonomies, opportunities and challenges toward responsible AIInformation Fusion, 2020
- A fast second-order shallow water scheme on two-dimensional structured grids over abrupt topographyAdvances in Water Resources, 2019
- Geomorphic classifiers for flood-prone areas delineation for data-scarce environmentsAdvances in Water Resources, 2017