A hybrid data assimilation and machine learning approach for enhancing operational forecasting in 2D hydrodynamic models
Journal of Hydroinformatics · 01.03.2025 · 27 (3) · 493-507
DOI: 10.2166/hydro.2025.289 ↗Kurz gefasst
Fachartikel in der Zeitschrift Journal of Hydroinformatics, online erschienen am 05.02.2025. Verfasst von Clemens Johannes Matthias Cremer und 2 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Danish Ministry of Higher Education and Science..
Abstract (Originalsprache)
Data assimilation (DA) integrates observations to enhance model predictions, but its benefits can rapidly decay during forecast for models heavily influenced by boundary conditions. To extend forecast accuracy, we combine machine learning (ML) with DA in a hybrid approach. We utilize ML to create synthetic point observations, which are assimilated into the model and thus propagated to other positions and model variables. In a case study, we apply the approach to a tidal estuary hydrodynamic model using a long short-term memory (LSTM) network for ML forecasts and the Ensemble Kalman Filter (EnKF) for assimilation. Hereby, physical consistency and spatial representation of water levels in the estuary are maintained. Our results from 100 forecast runs show significant improvements: over 40% accuracy increase in forecasts up to 4 h ahead, and a >5% error reduction at 9 h compared with a traditional numerical model without assimilation.
Förderung
- Danish Ministry of Higher Education and Science.
Zitieren
APA
Cremer, C. J. M., Mariegaard, J. S., & Andersson, H. J. (2025). A hybrid data assimilation and machine learning approach for enhancing operational forecasting in 2D hydrodynamic models. Journal of Hydroinformatics, 27(3), 493-507. https://doi.org/10.2166/hydro.2025.289
Vancouver
Cremer CJM, Mariegaard JS, Andersson HJ. A hybrid data assimilation and machine learning approach for enhancing operational forecasting in 2D hydrodynamic models. Journal of Hydroinformatics. 2025;27(3):493-507. doi:10.2166/hydro.2025.289
BibTeX
@article{Cremer2025,
author = {Cremer, Clemens Johannes Matthias and Mariegaard, Jesper Sandvig and Andersson, Henrik Johan},
title = {A hybrid data assimilation and machine learning approach for enhancing operational forecasting in 2D hydrodynamic models},
journal = {Journal of Hydroinformatics},
year = {2025},
volume = {27},
number = {3},
pages = {493--507},
doi = {10.2166/hydro.2025.289}
}
EUVIMED