Preprints
https://doi.org/10.5194/hess-2024-56
https://doi.org/10.5194/hess-2024-56
14 Mar 2024
 | 14 Mar 2024
Status: this discussion paper is a preprint. It has been under review for the journal Hydrology and Earth System Sciences (HESS). The manuscript was not accepted for further review after discussion.

Incremental learning for rainfall-runoff simulation on deep neural networks

Zeqiang Chen, Jiashun Li, Changjiang Xiao, and Nengcheng Chen

Abstract. Rainfall-runoff simulation based on deep learning always costs plenty of time for training with large datasets. This may affect quick decision making in some flood emergency decision-making situations. To address this issue, this study proposes an incremental learning method to accelerate rainfall-runoff simulation with deep learning model. The method consists of two components, regular training and incremental operation. In regular training phase, the model is regularly trained using historical data. In the incremental operation phase, the method selects representative samples from historical data with distribution estimation metrics and time series similarity metrics, then updates the regularly trained model with the sampled data and recent data in case of emergency. The proposed method was tested using ten hydrological observation stations in the Yangtze River and Han River drainage basin, with three different modified Recurrent Neural Networks. The results show that the incremental learning method achieves a training efficiency acceleration of over 4 times, with only a little increase in percentage error and decrease in Nash-Sutcliffe efficiency coefficient. The results also illustrate the robustness of this method for different models in different places, as well as during continuous incremental scenarios. The findings indicate that the incremental learning method has great potential applications in rapid rainfall-runoff simulation for flood emergency decision-making.

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.
Zeqiang Chen, Jiashun Li, Changjiang Xiao, and Nengcheng Chen

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on hess-2024-56', John Ding, 31 Mar 2024
  • RC1: 'Comment on hess-2024-56', Anonymous Referee #1, 24 Apr 2024
  • RC2: 'Comment on hess-2024-56', Anonymous Referee #2, 30 May 2024

Status: closed

Comment types: AC – author | RC – referee | CC – community | EC – editor | CEC – chief editor | : Report abuse
  • CC1: 'Comment on hess-2024-56', John Ding, 31 Mar 2024
  • RC1: 'Comment on hess-2024-56', Anonymous Referee #1, 24 Apr 2024
  • RC2: 'Comment on hess-2024-56', Anonymous Referee #2, 30 May 2024
Zeqiang Chen, Jiashun Li, Changjiang Xiao, and Nengcheng Chen
Zeqiang Chen, Jiashun Li, Changjiang Xiao, and Nengcheng Chen

Viewed

Total article views: 675 (including HTML, PDF, and XML)
HTML PDF XML Total BibTeX EndNote
440 195 40 675 31 27
  • HTML: 440
  • PDF: 195
  • XML: 40
  • Total: 675
  • BibTeX: 31
  • EndNote: 27
Views and downloads (calculated since 14 Mar 2024)
Cumulative views and downloads (calculated since 14 Mar 2024)

Viewed (geographical distribution)

Total article views: 636 (including HTML, PDF, and XML) Thereof 636 with geography defined and 0 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 
Latest update: 05 Oct 2024
Download
Short summary
Rainfall-runoff simulation based on deep learning has become popular approaches in recent years with the drawback of significant time required for training. The study proposes an incremental learning method to accelerate rainfall-runoff simulation with deep learning models. The method was tested in Yangtze River and Han River drainage basin. The results show the feasibility, robustness, suitability and potential applications in flood emergency decision-making of the method.