Study on Ensemble Calibration of Flood Forecasting Based on Response Curve of Rainfall Dynamic System and LSTM

Lu Tian (), Qiying Yu (), Zhichao Li, Chengshuai Liu, Wenzhong Li, Chen Shi and Caihong Hu ()
Additional contact information
Lu Tian: Zhengzhou University
Qiying Yu: Zhengzhou University
Zhichao Li: Zhengzhou University
Chengshuai Liu: Zhengzhou University
Wenzhong Li: Zhengzhou University
Chen Shi: Zhengzhou University
Caihong Hu: Zhengzhou University

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA), 2025, vol. 39, issue 2, No 5, 645-660

Abstract: Abstract To improve flood forecasting accuracy, the dynamic system response curve correction method was employed to invert and establish an error time series of areal rainfall in the Shouxi River Basin in Sichuan Province and the Qingyangcha Basin in Shaanxi Province. The areal rainfall in the watershed was corrected using the obtained error time series. The corrected areal rainfall was then used as input for flood forecasting using the excess storage and excess infiltration simultaneously model. Additionally, a hierarchical optimization method and LSTM error output correction method were applied to calibrate the three sources of errors. The results showed that the accuracy of flood peak discharge improved after the correction of areal rainfall. Specifically, in the validation set of the Shouxi River Basin, the absolute error of flood peak discharge decreased by 0.56% to 6.3% for 12 out of 15 flood events. The Nash–Sutcliffe Efficiency (NSE) of flood discharge increased by 0.002 to 0.015 for 13 flood events, and the time lag of two flood peaks shortened by 1 h. In the validation set of the Qingyangcha Basin, the absolute error of flood peak discharge decreased by 0.23% to 5.49% for 5 out of 6 flood events. The NSE of flood discharge increased by 0.01 to 0.071 for 5 flood events, and the time lag of two flood peaks shortened by 1 h. Overall, the results demonstrate that this method can reduce the forecast error and improve the accuracy of flood forecasting in the watershed.

Keywords: Response curve of rainfall dynamic system; Flood classification; Error correction; Long short-term memory; Flood forecasting; Real-time forecasting; The excess storage and excess infiltration simultaneously model (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s11269-024-03955-0 Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:waterr:v:39:y:2025:i:2:d:10.1007_s11269-024-03955-0

Ordering information: This journal article can be ordered from
http://www.springer.com/economics/journal/11269

DOI: 10.1007/s11269-024-03955-0

Access Statistics for this article

Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) is currently edited by G. Tsakiris

More articles in Water Resources Management: An International Journal, Published for the European Water Resources Association (EWRA) from Springer, European Water Resources Association (EWRA)
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().