Work

Projection of hydrological droughts in the upper Hanjiang River under the climate change impact based on stacking machine learning model

Year: 2026

Type: article

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.

Source: Journal of Hydrology Regional Studies

DOI: 10.1016/j.ejrh.2026.104096