EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Global streamflow modelling using process-informed machine learning

Michele Magni, Edwin H. Sutanudjaja, Youchen Shen, Derek Karssenberg

Journal of Hydroinformatics · 01.09.2023 · 25 (5) · 1648-1666

DOI: 10.2166/hydro.2023.217 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Hydroinformatics, online erschienen am 04.08.2023. Verfasst von Michele Magni und 3 weiteren Autor:innen. Die Arbeit wurde bisher 15-mal zitiert (Crossref) und nennt 74 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

We present a novel hybrid framework that incorporates information from the process-based global hydrological model PCR-GLOBWB, to reduce prediction errors in streamflow simulations. In addition to catchment attributes and meteorological data, our methodology employs simulated streamflow and state variables from PCR-GLOBWB as predictors of observed river discharge. These outputs are used in a random forest, trained on a global database of streamflow measurements, to improve estimates of simulated river discharge across the globe. PCR-GLOBWB was run for the years 1979–2019 at 30 arcmin and its inputs and outputs were upscaled from daily to monthly time steps. A single random forest model was trained with these state variables, meteorological data and catchment attributes, as predictors of observed streamflow at 2,286 stations worldwide. Model performance was evaluated using Kling–Gupta efficiency (KGE). Results based on cross-validation show that the model is capable of discerning between a variety of hydroclimatic conditions and river flow dynamics, improving KGE of PCR-GLOBWB simulations at more than 80% of testing locations and increasing median KGE from −0.03 in uncalibrated runs to 0.51 after post-processing. Performance boosts are usually independent of the availability of streamflow data, making our method a potential candidate in addressing prediction in poorly gauged and ungauged basins.

Zitieren

APA

Magni, M., Sutanudjaja, E. H., Shen, Y., & Karssenberg, D. (2023). Global streamflow modelling using process-informed machine learning. Journal of Hydroinformatics, 25(5), 1648-1666. https://doi.org/10.2166/hydro.2023.217

Vancouver

Magni M, Sutanudjaja EH, Shen Y, Karssenberg D. Global streamflow modelling using process-informed machine learning. Journal of Hydroinformatics. 2023;25(5):1648-1666. doi:10.2166/hydro.2023.217

BibTeX
@article{Magni2023,
  author = {Magni, Michele and Sutanudjaja, Edwin H. and Shen, Youchen and Karssenberg, Derek},
  title = {Global streamflow modelling using process-informed machine learning},
  journal = {Journal of Hydroinformatics},
  year = {2023},
  volume = {25},
  number = {5},
  pages = {1648--1666},
  doi = {10.2166/hydro.2023.217}
}
Kostenlos starten →