大洪水
可解释性
决策树
洪水风险评估
计算机科学
弹性(材料科学)
风险评估
随机森林
环境资源管理
气候变化
Boosting(机器学习)
城市化
风险管理
心理弹性
决策支持系统
环境科学
地理
机器学习
水资源管理
水文模型
洪水风险管理
脆弱性(计算)
基线(sea)
预测建模
仰角(弹道)
决策分析
风险分析(工程)
洪水(心理学)
数字高程模型
作者
Meihong Ma,Ting Wang,Jianhua Yang,Ziyan Chen,Jinqi Wang,Ronghua Liu,Xiaoyi Miao
标识
DOI:10.1016/j.gsf.2025.102244
摘要
• A novel framework combines XAI and hydrological model for urban flood risk assessment. • With 91% accuracy, the framework pinpoints expanding high-risk zones in GBA cities during extreme floods • Interpretable analysis reveals FD, SD and DEM as dominant factors, supporting flood risk explanation. Increasingly frequent extreme climate events have intensified urban flood risks, underscoring the urgent need for accurate, interpretable assessment methodologies. This study establishes an explainable artificial intelligence (XAI) framework for flood risk assessment in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA), integrating the LISFLOOD-FP hydrodynamic model with Gradient Boosting Decision Tree (GBDT). To resolve model opacity, Local Interpretable Model-agnostic Explanations (LIME) quantifies the contributions of critical disaster-inducing indicators. The framework achieves over 91% predictive accuracy, revealing a 1.33% expansion of very high-risk zones and a 3.80% increase in high-risk areas under the 100-year flood scenario, with the most affected cities including Guangzhou, Shenzhen, Zhuhai, and Foshan. LIME-based interpretability analysis under this scenario underscores the dominant influence of hydrological and topographic variables, with FD (flood depth), SD (submerge duration), and DEM (Digital Elevation Model) collectively contributing over 60% of the total explanatory contribution. This XAI approach significantly enhances flood risk prediction precision, delivering actionable insights for evidence-based resilience planning across the GBA.
科研通智能强力驱动
Strongly Powered by AbleSci AI