VMDI-LSTM-ED: A novel enhanced decomposition ensemble model incorporating data integration for accurate non-stationary daily streamflow forecasting

•A novel model, VMDI-LSTM-ED, is proposed for non-stationary streamflow forecasting.•Data integration (DI) is firstly employed to enhance decomposition ensemble model.•VMDI-LSTM-ED enhances predictions by integrating recent observations.•VMDI-LSTM-ED can effectively predict peak streamflow and captu...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	Journal of hydrology (Amsterdam) Jg. 653; S. 132769
Hauptverfasser:	Liu, Jiadong, Xu, Teng, Lu, Chunhui
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 01.06.2025
Schlagworte:	Data integration Decomposition ensemble model Deep learning Encoder-decoder framework flood control neural networks Non-stationary streamflow prediction stream flow Deep learning Decomposition ensemble model Non-stationary streamflow Encoder-decoder framework Data integration
ISSN:	0022-1694
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!