Wang et al. (2025) Hydrological drought attribution analysis of six rivers in China by the coupled model of machine learning and hydrological model

⚠️ Warning: This summary was generated from the abstract only, as the full text was not available.

Identification

• Journal: Geomatics Natural Hazards and Risk
• Year: 2025
• Date: 2025-12-24
• Authors: Jiaming Wang, Jingyang Ji, Guangxing JI
• DOI: 10.1080/19475705.2025.2607460

Research Groups

Not specified in the provided text.

Short Summary

This study applied a coupled machine learning-hydrological model to monthly runoff data from six major Chinese rivers to quantify the contributions of climate change and human activities to hydrological drought, finding varying dominance of these factors across basins and seasons.

Objective

• To quantify the relative contributions of climate change and human activities to hydrological drought evolution in six major Chinese river basins.

Study Configuration

• Spatial Scale: Six major Chinese river basins: Upper Yangtze River Basin, source regions of the Yellow River, Upper Pearl River, Middle-Upper Songhua River, Upper Huaihe River, and the source region of Lancang River.
• Temporal Scale: Monthly and seasonally.

Methodology and Data

• Models used: Coupled machine learning-hydrological model.
• Data sources: Monthly runoff data from six major Chinese rivers.

Main Results

• The coupled machine learning-hydrological model demonstrated superior performance compared to single models, particularly in environmentally complex basins.
• On a monthly scale, human activities were the primary driver of hydrological drought in the Upper Yangtze River Basin during January to March, May, September, and October.
• Climate change dominated monthly drought evolution in the source regions of the Yellow River, Upper Pearl River, Middle-Upper Songhua River, Upper Huaihe River, and the source region of Lancang River during April, June–August, and October.
• Seasonally, both climate change and human activities influenced the Upper Yangtze River Basin, while climate change generally dominated other basins, with the exception of the Lancang River Basin in spring and summer.
• Overall, climate change was identified as the main driver of hydrological drought in most studied basins, whereas human activity was the dominant factor in the Lancang River Basin.

Contributions

• Developed and applied a novel coupled machine learning-hydrological model, demonstrating its enhanced performance in simulating runoff changes, especially in complex environmental settings.
• Provided a detailed, quantitative attribution of the contributions of climate change and human activities to hydrological drought across six major Chinese river basins.
• Highlighted the spatial and temporal variability (monthly and seasonal) in the dominance of climate change versus human activities as drivers of hydrological drought.

Funding

Not specified in the provided text.

Citation

@article{Wang2025Hydrological,
  author = {Wang, Jiaming and Ji, Jingyang and JI, Guangxing},
  title = {Hydrological drought attribution analysis of six rivers in China by the coupled model of machine learning and hydrological model},
  journal = {Geomatics Natural Hazards and Risk},
  year = {2025},
  doi = {10.1080/19475705.2025.2607460},
  url = {https://doi.org/10.1080/19475705.2025.2607460}
}