Hydrology and Earth System Sciences
Hydrology and Earth System Sciences
HESS
Articles | Volume 30, issue 1
Articles | Volume 30, issue 1
https://doi.org/10.5194/hess-30-205-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
https://doi.org/10.5194/hess-30-205-2026
© Author(s) 2026. This work is distributed under
the Creative Commons Attribution 4.0 License.
Articles | Volume 30, issue 1
Research article
 | 
14 Jan 2026
Research article |  | 14 Jan 2026

Multi-Machine Learning Ensemble Regionalization of Hydrological Parameters for Enhancing Flood Prediction in Ungauged Mountainous Catchments

Kai Li, Linmao Guo, Genxu Wang, Jihui Gao, Xiangyang Sun, Peng Huang, Jinlong Li, Jiapei Ma, and Xinyu Zhang

Viewed

Total article views: 4,827 (including HTML, PDF, and XML)
HTML PDF XML Total Supplement BibTeX EndNote
3,570 1,068 189 4,827 321 132 204
  • HTML: 3,570
  • PDF: 1,068
  • XML: 189
  • Total: 4,827
  • Supplement: 321
  • BibTeX: 132
  • EndNote: 204
Views and downloads (calculated since 10 Jun 2025)
Cumulative views and downloads (calculated since 10 Jun 2025)

Viewed (geographical distribution)

Total article views: 4,827 (including HTML, PDF, and XML) Thereof 4,728 with geography defined and 99 with unknown origin.
Country # Views %
  • 1
1
 
 
 
 

Cited

Saved (final revised paper)

Latest update: 27 Sep 2026
Download
Short summary
We propose a multi-machine learning ensemble—integrating Gradient Boosting Machine, K-Nearest Neighbors, and Extremely Randomized Trees (GBM-KNN-ERT)—to improve Topography-Based Subsurface Storm Flow (Top-SSF) parameter regionalization for flood prediction in ungauged catchments. Validated across 80 Chinese catchments, the ensemble achieved a Nash-Sutcliffe Efficiency (NSE) greater than 0.9 for 90 % of catchments, showing superior robustness to climate and donor variability.
Read more
Share