Projection of hydrological droughts in the upper Hanjiang River under the climate change impact based on stacking machine learning model
5 affiliations
- 1Institute of Soil and Water Conservation, Northwest A&F University, Yangling, Shaanxi, 712100, China
- 2College of Water Resources and Architectural Engineering, Northwest A&F University, Yangling, Shaanxi, 712100, China
- 3School of Environmental Science and Engineering, Southern University of Science and Technology, Shenzhen, 518055, China
- 4College of Hydraulic Science and Engineering, Yangzhou University, Yangzhou, China
- 5College of Water Resources and Architectural Engineering, Northwest A&F University, Yangling, Shaanxi, 712100, China; Corresponding author.
Abstract
Study region: The upper Hanjiang River Basin, a crucial water source region for multiple large-scale inter-basin water transfer projects in China, including the South-to-North Water Diversion Project and the Han-to-Wei Water Transfer Project. Study focus: This study focuses on hydrological drought in the upper Hanjiang River Basin, a critical water supply region for major inter-basin water transfer projects. With global warming, droughts have intensified and occurred more frequently, posing potential threats to water supply security for both the source and recipient regions. We projected future runoff (2030–2099) at two key hydrological stations by constructing an ensemble machine learning (ML) runoff model driven by 20 CMIP6 GCMs. Future hydrological droughts under global warming were then identified and analyzed. New hydrological insights for the region: The ensemble ML model showed improved performance over individual ML models. Future annual runoff is projected to increase overall, albeit with substantial spread among individual climate models. For hydrological drought, duration is projected to shorten while intensity shows an increasing trend, and a higher proportion of extreme droughts is expected under SSP585 than under SSP245. Despite an overall wetting trend, the increasing intensity and severity of hydrological droughts could undermine the stability and reliability of water supply for inter-basin water transfer projects, necessitating enhanced adaptive management strategies in this critical water-source region.
Related
- How could climate change affect the magnitude, duration and frequency of hydrological droughts and floods in West Africa during the 21st century? A storyline approach
- Machine Learning-Based Hydrological Drought Prediction Integrating Teleconnections and Hydrological Memory in a Semi-Arid Basin, Algeria
- Coupling hydrological simulation and deep learning for real-time flood defense in mountainous cities: A case study of the June 18, 2023 extreme flood in Guiyang Penshuichi
- From hydrological laws to catchment models: A process-based model matches deep-learning accuracy on three continents
- Physics‐Informed Fusion Learning for Nowcasting Fault Detection of Hydrological Multi Sensor Network
BibTeX
@article{gao2026projection,
title = {{Projection of hydrological droughts in the upper Hanjiang River under the climate change impact based on stacking machine learning model}},
author = {Xuerui Gao and Jingyuan Chen and Daning Liu and Ziqi Shang and Lingyao Meng and Baoni Li and Gengxi Zhang and Aili Sun and Shuyu Zhang},
journal = {Journal of Hydrology: Regional Studies},
year = {2026},
month = oct,
doi = {10.1016/j.ejrh.2026.104096},
url = {https://doi.org/10.1016/j.ejrh.2026.104096},
note = {CC BY},
}
RIS
TY - JOUR
TI - Projection of hydrological droughts in the upper Hanjiang River under the climate change impact based on stacking machine learning model
AU - Xuerui Gao
AU - Jingyuan Chen
AU - Daning Liu
AU - Ziqi Shang
AU - Lingyao Meng
AU - Baoni Li
AU - Gengxi Zhang
AU - Aili Sun
AU - Shuyu Zhang
PY - 2026
DA - 2026/10/30
JO - Journal of Hydrology: Regional Studies
DO - 10.1016/j.ejrh.2026.104096
UR - https://doi.org/10.1016/j.ejrh.2026.104096
AB - Study region: The upper Hanjiang River Basin, a crucial water source region for multiple large-scale inter-basin water transfer projects in China, including the South-to-North Water Diversion Project and the Han-to-Wei Water Transfer Project. Study focus: This study focuses on hydrological drought in the upper Hanjiang River Basin, a critical water supply region for major inter-basin water transfer projects. With global warming, droughts have intensified and occurred more frequently, posing potential threats to water supply security for both the source and recipient regions. We projected future runoff (2030–2099) at two key hydrological stations by constructing an ensemble machine learning (ML) runoff model driven by 20 CMIP6 GCMs. Future hydrological droughts under global warming were then identified and analyzed. New hydrological insights for the region: The ensemble ML model showed improved performance over individual ML models. Future annual runoff is projected to increase overall, albeit with substantial spread among individual climate models. For hydrological drought, duration is projected to shorten while intensity shows an increasing trend, and a higher proportion of extreme droughts is expected under SSP585 than under SSP245. Despite an overall wetting trend, the increasing intensity and severity of hydrological droughts could undermine the stability and reliability of water supply for inter-basin water transfer projects, necessitating enhanced adaptive management strategies in this critical water-source region.
SN - 2214-5818
ER -