Global to local: a novel encoder-decoder framework for urban real-time rainfall-runoff forecasting

Urban real-time rainfall-runoff forecasting (URRF) offers an economical and efficient approach to assessing flood risks in urban areas. However, the hydrological processes of urban rainfall are characterized by high nonlinearity and long-term dependencies due to strong uncertainties and significant...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Veröffentlicht in:Earth science informatics Jg. 18; H. 2; S. 403
Hauptverfasser: Tian, Yuan, Fu, Wenlong, Dong, Yajing, Han, Qi, Xiong, Qian, Cui, Ruonan, Ao, Zhenyu, Lei, Xinyu
Format: Journal Article
Sprache:Englisch
Veröffentlicht: Berlin/Heidelberg Springer Berlin Heidelberg 01.06.2025
Springer Nature B.V
Schlagworte:
Ablation
Artificial neural networks
Deep learning
Earth and Environmental Science
Earth Sciences
Earth System Sciences
Encoders-Decoders
Environmental risk
Flood forecasting
Flood management
Flood risk
Floods
Human influences
Hydrologic data
Hydrologic processes
Hydrology
Information Systems Applications (incl.Internet)
Machine learning
Neural networks
Ontology
Rainfall runoff
Rainfall-runoff relationships
Real time
Recurrent neural networks
Risk management
Runoff
Runoff forecasting
Simulation and Modeling
Space Exploration and Astronautics
Space Sciences (including Extraterrestrial Physics
Time response
Urban areas
Urban rainfall
Urban runoff
Deep learning
Global-encoder and local-decoder framework
Temporal convolutional network
Urban runoff
Real-time prediction
ISSN:1865-0473, 1865-0481
Online-Zugang:Volltext
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Beschreibung
Zusammenfassung:Urban real-time rainfall-runoff forecasting (URRF) offers an economical and efficient approach to assessing flood risks in urban areas. However, the hydrological processes of urban rainfall are characterized by high nonlinearity and long-term dependencies due to strong uncertainties and significant human influences, making URRF a challenging task in hydrological simulation. Existing methods often fall short in meeting the requirements for real-time response and accuracy. To address these limitations, this paper proposes a novel global-encoder and local-decoder (GL-ED) model. The global encoder extracts global temporal features, while the local decoder focuses on forecasting. A temporal fully connected (TFC) module is introduced within the global encoder to capture the global features of runoff sequences, overcoming the limitation of convolutional operations that primarily focus on local information. Additionally, to tackle the uneven distribution of urban rainfall-runoff data, a novel RD loss function is proposed, combining dynamic time warping (DTW) with RMSE to better guide the training of complex features. The GL-ED model was evaluated using observed urban rainfall events from January 2018 to December 2019 in a 3.52 k m 2 complex terrain area in Chongqing, China. Experimental results demonstrate that the GL-ED model outperforms conventional deep learning models, including convolutional neural networks (CNNs), recurrent neural networks (RNNs), and long short-term memory (LSTM) networks, in terms of NSE, MAE, and RMSE. In ablation experiments, the GL-ED model trained with the RD loss function achieved an average improvement of 2.51 % in NSE and 5.62 % in KGE, while reducing RMSE, MAE, and Pbias by 6.08 % , 11.31 % , and 93 % , respectively. These findings highlight the model’s capability to provide reliable and accurate real-time rainfall-runoff forecasting, offering significant potential for enhancing urban flood risk management and decision-making processes.
Bibliographie:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1865-0473
1865-0481
DOI:10.1007/s12145-025-01907-9