EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

A parsimonious setup for streamflow forecasting using CNN-LSTM

Sudan Pokharel, Tirthankar Roy

Journal of Hydroinformatics · 01.11.2024 · 26 (11) · 2751-2761

DOI: 10.2166/hydro.2024.114 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Journal of Hydroinformatics, online erschienen am 30.10.2024. Verfasst von Sudan Pokharel und 1 weiteren Autor:innen. Die Arbeit wurde bisher 24-mal zitiert (Crossref) und nennt 42 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: University of Nebraska Collaboration Initiative.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Significant strides have been made in advancing streamflow predictions, notably with the introduction of cutting-edge machine-learning models. Predominantly, long short-term memories (LSTMs) and convolution neural networks (CNNs) have been widely employed in this domain. While LSTMs are applicable in both rainfall-runoff and time-series settings, CNN–LSTMs have primarily been utilized in rainfall-runoff scenarios. In this study, we extend the application of CNN–LSTMs to time-series settings, leveraging lagged streamflow data in conjunction with precipitation and temperature data to predict streamflow. Our results show a substantial improvement in predictive performance in 21 out of 32 HUC8 basins in Nebraska, showcasing noteworthy increases in the Kling–Gupta efficiency values. These results highlight the effectiveness of CNN–LSTMs in time-series settings, particularly for spatiotemporal hydrological modeling, for more accurate and robust streamflow predictions.

Förderung

  • University of Nebraska Collaboration Initiative

Zitieren

APA

Pokharel, S., & Roy, T. (2024). A parsimonious setup for streamflow forecasting using CNN-LSTM. Journal of Hydroinformatics, 26(11), 2751-2761. https://doi.org/10.2166/hydro.2024.114

Vancouver

Pokharel S, Roy T. A parsimonious setup for streamflow forecasting using CNN-LSTM. Journal of Hydroinformatics. 2024;26(11):2751-2761. doi:10.2166/hydro.2024.114

BibTeX
@article{Pokharel2024,
  author = {Pokharel, Sudan and Roy, Tirthankar},
  title = {A parsimonious setup for streamflow forecasting using CNN-LSTM},
  journal = {Journal of Hydroinformatics},
  year = {2024},
  volume = {26},
  number = {11},
  pages = {2751--2761},
  doi = {10.2166/hydro.2024.114}
}
Kostenlos starten →