Preprints
https://doi.org/10.5194/hess-2021-393
https://doi.org/10.5194/hess-2021-393

  30 Jul 2021

30 Jul 2021

Review status: a revised version of this preprint is currently under review for the journal HESS.

Ensemble streamflow forecasting over a cascade reservoir catchment with integrated hydrometeorological modeling and machine learning

Junjiang Liu1, Xing Yuan1, Junhan Zeng1, Yang Jiao1, Yong Li2, Lihua Zhong2, and Ling Yao3 Junjiang Liu et al.
  • 1School of Hydrology and Water Resources, Nanjing University of Information Science and Technology, Nanjing 210044, China
  • 2Guangxi Meteorological Disaster Prevention Center, Nanning 530022, China
  • 3Guangxi Guiguan Electric Power Co., Ltd., Nanning 530029, China

Abstract. A popular way to forecast streamflow is to use bias-corrected meteorological forecast to drive a calibrated hydrological model, but these hydrometeorological approaches have deficiency over small catchments due to uncertainty in meteorological forecasts and errors from hydrological models, especially over catchments that are regulated by dams and reservoirs. For a cascade reservoir catchment, the discharge of the upstream reservoir contributes to an important part of the streamflow over the downstream areas, which makes it tremendously hard to explore the added value of meteorological forecasts. Here, we integrate the meteorological forecast, land surface hydrological model simulation and machine learning to forecast hourly streamflow over the Yantan catchment, where the streamflow is influenced both by the upstream reservoir water release and the rainfall-runoff processes within the catchment. Evaluation of the hourly streamflow hindcasts during the rainy seasons of 2013–2017 shows that the hydrometeorological ensemble forecast approach reduces probabilistic forecast error by 10 % and deterministic forecast error by 6 % as compared with the traditional ensemble streamflow prediction (ESP) approach during the first 7 days. The deterministic forecast error can be further reduced by 6 % in the first 72 hours when combining the hydrometeorological forecast with the long short-term memory (LSTM) deep learning method. However, the forecast skill for LSTM using only historical observations drops sharply after the first 24 hours. This study implies the potential of improving flood forecast over a cascade reservoir catchment by integrating meteorological forecast, hydrological modeling and machine learning.

Junjiang Liu et al.

Status: final response (author comments only)

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • RC1: 'Comment on hess-2021-393', Anonymous Referee #1, 14 Aug 2021
  • RC2: 'Comment on hess-2021-393', Anonymous Referee #2, 17 Aug 2021
  • RC3: 'Comment on hess-2021-393', Anonymous Referee #3, 18 Aug 2021
  • RC4: 'Comment on hess-2021-393', Anonymous Referee #4, 25 Aug 2021

Junjiang Liu et al.

Junjiang Liu et al.

Viewed

Total article views: 498 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
365 111 22 498 2 3
  • HTML: 365
  • PDF: 111
  • XML: 22
  • Total: 498
  • BibTeX: 2
  • EndNote: 3
Views and downloads (calculated since 30 Jul 2021)
Cumulative views and downloads (calculated since 30 Jul 2021)

Viewed (geographical distribution)

Total article views: 425 (including HTML, PDF, and XML) Thereof 425 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 24 Oct 2021
Download
Short summary
Streamflow ensemble forecasts with CSSPv2 land surface model and ECMWF meteorological forecasts reduce probabilistic forecast error by 10 % and deterministic forecast error by 6 % compared with the ESP approach during the first 7 days. The deterministic forecast error can be further reduced by 6 % in the first 72 hours when combined with the long short-term memory (LSTM) deep learning method. The forecast skill for LSTM using only historical observations drops sharply after the first 24 hours.