What question did this study set out to answer?

The aim is to develop a framework combining machine learning and spatial analysis for assessing urban flood susceptibility.

May 11, 2026Scientific Reports0 citationsOpen Access

Interpretable machine learning framework for urban flood susceptibility assessment: a multi-model comparison with spatial heterogeneity analysis in Yancheng

XZXuan ZhangYancheng Teachers University DGDongdong GuoYancheng Teachers University

Key Points

The aim is to develop a framework combining machine learning and spatial analysis for assessing urban flood susceptibility.
Analyzed 486 historical flood points and 10 conditioning factors.
Compared predictive performance of Random Forest, XGBoost, and Support Vector Machine.
Conducted SHAP interpretability and spatial heterogeneity analyses.
XGBoost showed the highest accuracy (AUC = 0.938) compared to RF (AUC = 0.912) and SVM (AUC = 0.876).
Topographic wetness index, elevation, and impervious surface ratio contributed 47.6% to flood susceptibility.
19.2% of the study area was identified as high to very high flood risk, with Tinghu District at 37.0%.

Abstract

Under the combined effects of global climate change and rapid urbanization, low-lying coastal plain cities face increasingly severe flood threats. This study developed an urban flood susceptibility assessment framework integrating multi-model comparison, SHAP interpretability analysis, and spatial heterogeneity evaluation, using Yancheng City as a case study. Based on 486 historical flood points and 10 conditioning factors, the predictive performance of Random Forest (RF), XGBoost, and Support Vector Machine (SVM) was compared. Results showed XGBoost performed best (AUC = 0.938, accuracy = 0.891), significantly outperforming RF (AUC = 0.912) and SVM (AUC = 0.876). SHAP analysis identified topographic wetness index (TWI), elevation, and impervious surface ratio as key driving factors, with a cumulative contribution of 47.6%. Spatial heterogeneity analysis revealed distinct flood mechanisms across geomorphic units: urban built-up areas were dominated by impervious surfaces (31.5% high-risk), Lixiahe lowland by TWI (28.6%), coastal tidal flats by elevation (23.1%), while the Yellow River paleo-channel showed the lowest risk (11.2%). Susceptibility mapping indicated 19.2% of the study area at high to very high levels, with Tinghu District reaching 37.0%. The proposed integrated framework provides scientific support for differentiated flood control strategies in coastal plain cities.

اسأل الذكاء الاصطناعي

Bookmark

View Full Paper