Preprints
https://doi.org/10.5194/hess-2024-212
https://doi.org/10.5194/hess-2024-212
29 Jul 2024
 | 29 Jul 2024
Status: this preprint is currently under review for the journal HESS.

Deep learning based sub-seasonal precipitation and streamflow forecasting over the source region of the Yangtze River

Ningpeng Dong, Haoran Hao, Mingxiang Yang, Jianhui Wei, Shiqin Xu, and Harald Kunstmann

Abstract. Hydrometeorological forecasting is crucial for managing water resources and mitigating the impacts of extreme hydrologic events. At sub-seasonal scales, readily available hydrometeorological forecast products often exhibit large uncertainties and insufficient accuracies to support decision making. We propose a deep learning based modelling framework for sub-seasonal joint precipitation and streamflow forecasts for a lead time of up to 30 days. This is achieved by coupling (1) a convolutional neural network (CNN) architecture with ResNet blocks for statistically downscaling of the ECMWF raw precipitation forecasts to (2) a hybrid hydrologic model integrating the conceptual Xin’anjiang model (XAJ) and the long-short term memory network (LSTM) for streamflow forecasting. The CNN incorporates a specialized loss function that combines the continuous form of threat score and mean absolute error. Applying the modeling framework to the source region of the Yangtze River Basin, results indicate that the CNN-based downscaling model exhibits ~13 % and ~10 % less RMSE than the raw ECMWF forecasts and the quantile mapping (QM) forecasts, respectively, averaged over the 30-day lead time. Similarly, the CNN achieves a ~2 % and ~5 % lower RMSE than raw forecasts and QM for precipitation events above the 90th percentile of historic daily precipitation. Using these precipitation forecasts as meteorological drivers for the hybrid XAJ-LSTM hydrologic model, we found that forecasted streamflow and flood peaks driven by CNN-based precipitation forecasts have 18 %–32 % lower relative errors and 13 %–22 % lower RMSE compared to those driven by raw forecasts. However, the standalone XAJ model shows marginal improvements, or in some cases, no improvement at all, with the same enhanced precipitation forecasts. This highlights the importance of understanding the effectiveness of the hydrologic model as part of the sub-seasonal hydrometeorological modeling chain. Our study is expected to provide implications for leveraging advanced AI techniques to enhance sub-seasonal hydrometeorological forecasting accuracy and operational efficiency for effective water resources management and disaster preparedness.

Publisher's note: Copernicus Publications remains neutral with regard to jurisdictional claims made in the text, published maps, institutional affiliations, or any other geographical representation in this preprint. The responsibility to include appropriate place names lies with the authors.
Ningpeng Dong, Haoran Hao, Mingxiang Yang, Jianhui Wei, Shiqin Xu, and Harald Kunstmann

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-2024-212', Anonymous Referee #1, 21 Aug 2024
  • RC2: 'Comment on hess-2024-212', Anonymous Referee #2, 12 Sep 2024
Ningpeng Dong, Haoran Hao, Mingxiang Yang, Jianhui Wei, Shiqin Xu, and Harald Kunstmann
Ningpeng Dong, Haoran Hao, Mingxiang Yang, Jianhui Wei, Shiqin Xu, and Harald Kunstmann

Viewed

Total article views: 530 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
351 122 57 530 58 14 5
  • HTML: 351
  • PDF: 122
  • XML: 57
  • Total: 530
  • Supplement: 58
  • BibTeX: 14
  • EndNote: 5
Views and downloads (calculated since 29 Jul 2024)
Cumulative views and downloads (calculated since 29 Jul 2024)

Viewed (geographical distribution)

Total article views: 520 (including HTML, PDF, and XML) Thereof 520 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 08 Oct 2024
Download
Short summary
Hydrometeorological forecasting is crucial for managing water resources and mitigating extreme weather impacts, yet current long-term forecast products are often embedded with uncertainties. We develop a deep learning based modelling framework to improve 30-day rainfall and streamflow forecasts by combining advanced neural networks and outputs from physical models. With the forecast error reduced by up to 32%, the framework has the potential to enhance water management and disaster preparedness.