Articles | Volume 25, issue 5
https://doi.org/10.5194/hess-25-2543-2021
https://doi.org/10.5194/hess-25-2543-2021
Research article
 | 
18 May 2021
Research article |  | 18 May 2021

Resampling and ensemble techniques for improving ANN-based high-flow forecast accuracy

Everett Snieder, Karen Abogadil, and Usman T. Khan

Download

Interactive discussion

Status: closed
Status: closed
AC: Author comment | RC: Referee comment | SC: Short comment | EC: Editor comment
Printer-friendly Version - Printer-friendly version Supplement - Supplement

Peer-review completion

AR: Author's response | RR: Referee report | ED: Editor decision
ED: Reconsider after major revisions (further review by editor and referees) (17 Jan 2021) by Elena Toth
AR by Usman T Khan on behalf of the Authors (19 Feb 2021)  Author's response    Author's tracked changes    Manuscript
ED: Referee Nomination & Report Request started (10 Mar 2021) by Elena Toth
RR by Anonymous Referee #2 (16 Mar 2021)
RR by K.S. Kasiviswanathan (01 Apr 2021)
ED: Publish as is (06 Apr 2021) by Elena Toth
Download
Short summary
Flow distributions are highly skewed, resulting in low prediction accuracy of high flows when using artificial neural networks for flood forecasting. We investigate the use of resampling and ensemble techniques to address the problem of skewed datasets to improve high flow prediction. The methods are implemented both independently and in combined, hybrid techniques. This research presents the first analysis of the effects of combining these methods on high flow prediction accuracy.