Flood modelling in a montane basin using machine learning, deep learning and sensor network data
Journal of Hydroinformatics · 01.06.2026 · 28 (6) · 553-574
DOI: 10.2166/hydro.2026.175 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Hydroinformatics, online erschienen am 02.06.2026. Verfasst von Doudou Ba und 1 weiteren Autor:innen. Die Arbeit nennt 57 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC 4.0). Gefördert von: Grantová Agentura České Republiky, Ministerstvo Školství, Mládeže a Tělovýchovy.
Abstract (Originalsprache)
Conceptual workflow linking sensor-network observations and meteorological data with flood typology, machine-learning and deep-learning modelling, scenario-based flood simulations, model performance evaluation, and SHAP feature-contribution analysis. This study presents a scenario-based framework for rainfall–runoff modelling that evaluates classical machine learning, tree-based ensembles, and deep learning architectures across distinct flood types in a montane basin. Using 15 years of hourly hydrometeorological and sensor-network observations from the Upper Vydra Basin (2008–2023), we assessed eight models and an equal-weight ensemble to link predictive skill to flood-generating processes. Model performance varied across six flood typologies. The extended LSTM achieved the highest individual accuracy for long-duration and multi-peak events, whereas Random Forest and XGBoost were most effective for short-duration floods under contrasting antecedent wetness. Transformer models showed systematic overprediction, and support vector regression performed weakest. An equal-weight ensemble combining eight ML/DL architectures provided the most robust overall performance, with the highest prediction accuracy (NSE = 0.955) and reduced error variance. SHAP analysis highlighted the dominant influence of precipitation and snowmelt and the value of distributed water-level observations for representing catchment storage dynamics. These findings show that predictive skill depends strongly on the match between model architecture and hydrometeorological context. Scenario-based evaluation combined with ensemble integration offers a practical pathway toward reliable and operationally efficient flood forecasting in montane environments.
Förderung
- Grantová Agentura České Republiky
- Ministerstvo Školství, Mládeže a Tělovýchovy
Zitieren
APA
Ba, D., & Langhammer, J. (2026). Flood modelling in a montane basin using machine learning, deep learning and sensor network data. Journal of Hydroinformatics, 28(6), 553-574. https://doi.org/10.2166/hydro.2026.175
Vancouver
Ba D, Langhammer J. Flood modelling in a montane basin using machine learning, deep learning and sensor network data. Journal of Hydroinformatics. 2026;28(6):553-574. doi:10.2166/hydro.2026.175
BibTeX
@article{Ba2026,
author = {Ba, Doudou and Langhammer, Jakub},
title = {Flood modelling in a montane basin using machine learning, deep learning and sensor network data},
journal = {Journal of Hydroinformatics},
year = {2026},
volume = {28},
number = {6},
pages = {553--574},
doi = {10.2166/hydro.2026.175}
}
EUVIMED