Published: Jan. 1, 2024
Language: Английский
Journal of Hydrology Regional Studies, Journal Year: 2025, Volume and Issue: 58, P. 102214 - 102214
Published: Feb. 6, 2025
Language: Английский
Citations
0
Agricultural Water Management, Journal Year: 2025, Volume and Issue: 312, P. 109452 - 109452
Published: April 2, 2025
Language: Английский
Citations
0
The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 958, P. 178131 - 178131
Published: Dec. 19, 2024
Language: Английский
Citations
3
Published: Jan. 1, 2024
Predicting future drought conditions is of great significance for developing scientifically effective management plans to reduce losses caused by disasters. This study describes a machine learning framework predict and understand the hydrological in Huaihe River Basin China. The interpretable Extreme Gradient Boosting (XGBoost) model applied four categories 28 grid regions basin, using 26 18 different influencing factors monthly prediction seasonal prediction, respectively. also integrates Shapley Additive Explanation (SHAP) variable importance metric capture dynamics infer affecting prediction. found that can effectively spatial structure temporal drought. Among all factors, Standard Precipitation Index (SPI) has greatest influence on results, second third most important mainly include large-scale climatic evapotranspiration, soil water content wind speed. In addition, contribution varies with season location basin. addition SPI being main factor each season, influenced summer, while it moisture evapotranspiration spring, autumn winter. Overall, this provides an avenue quickly accurately evaluating complex impacts help stakeholders better relationships between multi-dimensional indicators at regional level.
Language: Английский
Citations
0
River, Journal Year: 2024, Volume and Issue: 3(3), P. 304 - 315
Published: Aug. 1, 2024
Abstract Drought risk assessment plays a crucial role in effective drought management. However, it is often challenging due to the intricate relationships among various indicators and lack of practical guidance. This study presents model developed using Semi‐partial Quadratic Subtraction Set Pair Potential (SQSSPP) method, which derived from theory set pair analysis. The indicator system comprises 21 divided into four subsystems. SQSSPP method utilizes uncertainty information overall development trend regional states by extracting connection numbers (SSPP), improving reliability evaluation results. validated through case Suzhou City, China, 2007 2017. Three grades are used evaluate comprehensive risk. result shows an decreasing over time, with level III 2010 consistently at II 2011 Indicators hazard resilience subsystems primary factors influencing City. Specific requiring emphasis for improvement identified, including arable land rate, agricultural population ratio, reservoir regulation current water supply capacity, irrigation index. not only provides targeted but also valuable guidance future resource While focuses on proposed approach applicable broader‐scale management evaluations practices.
Language: Английский
Citations
0
Published: Jan. 1, 2024
Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI
Language: Английский
Citations
0
Published: Jan. 1, 2024
Language: Английский
Citations
0
Published: Jan. 1, 2024
Language: Английский
Citations
0