Exploring a Long Short-Term Memory based Encoder-Decoder framework for multi-step-ahead flood forecasting

•For the first time a LSTM-ED model is proposed to model multi-step-ahead flood forecasting.•Sequence-to-sequence learning converts an input sequence into an output sequence.•LSTM encoder-decoder models tackle the challenging sequence-to-sequence prediction.•The LSTM-ED model reduced RMSE by 3% (T +...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	Journal of hydrology (Amsterdam) Jg. 583; S. 124631
Hauptverfasser:	Kao, I-Feng, Zhou, Yanlai, Chang, Li-Chiu, Chang, Fi-John
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	Elsevier B.V 01.04.2020
Schlagworte:	case studies data collection Encoder-Decoder (ED) model flood control Flood forecast hydrologic data Long Short-Term Memory (LSTM) meteorological data model validation neural networks rain Recurrent neural network (RNN) runoff Sequence-to-sequence Taiwan typhoons watersheds Taiwan Sequence-to-sequence Encoder-Decoder (ED) model Long Short-Term Memory (LSTM) Flood forecast Recurrent neural network (RNN)
ISSN:	0022-1694, 1879-2707
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Schreiben Sie den ersten Kommentar!