EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Multi-step ahead streamflow and uncertainty forecasting using a HyMoLAP rainfall-runoff model-based framework integrated with Bayesian neural networks in the Ouémé river basin, Benin

Sianou Ezéckiel Houénafa iD, Olatunji Johnson iD, Erick K Ronoh iD, Stephen E Moore iD

PLOS One · 2025

DOI: 10.1371/journal.pone.0333590 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PLOS One, 2025. Verfasst von Sianou Ezéckiel Houénafa und 3 weiteren Autor:innen. Beteiligte Einrichtung: Department of Mathematics, Pan African University Institute for Basic Sciences, Technology and Innovation, Nairobi, Kenya. Hauptthemen laut MEDLINE: Rivers, Rain, Neural Networks, Computer, Models, Theoretical. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 116 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-step forecasting is crucial for capturing future streamflow variations and managing water resources but remains challenging due to limited accuracy of upstream flow forecasts and meteorological predictions over lead times. While data-driven methods are commonly used, this study extends the Hydrological Model based on the Least Action Principle (HyMoLAP) from daily rainfall-runoff simulation to multi-day-ahead streamflow predictions. Additionally, it integrates Bayesian Long Short-Term Memory (Bayesian LSTM), primarily to enable uncertainty quantification (UQ). Applied to the Bonou and Savè sub-catchments of the Ouémé River Basin, Benin, the HyMoLAP-based framework yields NSE values ranging from 0.997 to 0.921 at Bonou and from 0.970 to 0.799 at Savè, showing slightly higher performance than the LSTM model overall, except at Savè from the 3-day lead time onward where it becomes slightly lower, with a more pronounced difference at the 7-day horizon. Our UQ approach provides reliable prediction intervals, with a coverage probability around 90%, as nearly 90% of the observed data fall within the 90% credible intervals in both sub-catchments.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

RiversRainNeural Networks, ComputerModels, TheoreticalBeninBayes TheoremForecastingUncertaintyWater Movements

Autor:innen und Institutionen

  • Department of Mathematics, Pan African University Institute for Basic Sciences, Technology and Innovation, Nairobi, Kenya.
  • Department of Mathematics, University of Manchester, Manchester, United Kingdom.
  • Department of Agricultural and Biosystems Engineering, Jomo Kenyatta University of Agriculture and Technology, Nairobi, Kenya.
  • Department of Mathematics, University of Cape Coast, Cape Coast, Ghana.
  • Center for Artificial Intelligence Research, Cape Coast, Ghana.

ORCID-Profile: Sianou Ezéckiel Houénafa, Olatunji Johnson, Erick K Ronoh, Stephen E Moore

Zitieren

APA

Ezéckiel Houénafa, S., Johnson, O., Ronoh, E. K., & Moore, S. E. (2025). Multi-step ahead streamflow and uncertainty forecasting using a HyMoLAP rainfall-runoff model-based framework integrated with Bayesian neural networks in the Ouémé river basin, Benin. PLOS One. https://doi.org/10.1371/journal.pone.0333590

Vancouver

Ezéckiel Houénafa S, Johnson O, Ronoh EK, Moore SE. Multi-step ahead streamflow and uncertainty forecasting using a HyMoLAP rainfall-runoff model-based framework integrated with Bayesian neural networks in the Ouémé river basin, Benin. PLOS One. 2025. doi:10.1371/journal.pone.0333590

BibTeX
@article{EzckielHounafa2025,
  author = {Ezéckiel Houénafa, Sianou and Johnson, Olatunji and Ronoh, Erick K and Moore, Stephen E},
  title = {Multi-step ahead streamflow and uncertainty forecasting using a HyMoLAP rainfall-runoff model-based framework integrated with Bayesian neural networks in the Ouémé river basin, Benin},
  journal = {PLOS One},
  year = {2025},
  doi = {10.1371/journal.pone.0333590}
}
Kostenlos starten →