From prediction to regionalization: Enhancing flash flood susceptibility mapping using machine learning and GeoDetector

作者：Xinyue Ke, Ni Wang, Tianhao Li, Zheng Liu, Zhiwei Li, Ganggang Zuo, Yiting Chen · 发表于：Geoscience Frontiers · 年份：2025 · DOI：10.1016/j.gsf.2025.102213 · 被引用次数：4 · 研究领域：Flood Risk Assessment and Management、Hydrology and Drought Analysis、Hydrology and Watershed Management Studies

• A novel framework turns susceptibility predictions into regionalization maps. • Grid-sampled CatBoost model shows superior adaptability and robustness. • Regionalization considers both susceptibility prediction and exposed element. • GeoDetector-based iteration enhances the clarity of the regionalization map. • Final regionalization explains 73% of past flash flood distribution patterns. Flash floods cause substantial economic losses and casualties worldwide. Susceptibility-based flash flood mapping supports the development of effective flood mitigation strategies. While machine learning (ML) models offer superior accuracy, converting their outputs into spatially coherent and actionable maps remains challenging. Existing susceptibility maps often rely on subjective discretization and exhibit fragmented spatial patterns, limiting their utility in practice. In this context, this study proposes a novel framework that achieves the effective transformation of susceptibility prediction results into a management-oriented regionalization map. The framework integrates supervised learning, unsupervised clustering, and spatial explanatory feedback to enable information fusion and spatial restructuring of multi-model outputs. Flash flood susceptibility was first modelled using two supervised algorithms: Random Forest and CatBoost. Their outputs, along with exposed elements, were integrated and discretized using a two-stage clustering approach based on Self-Organizing Maps (SOM) and War...