The lower course of the Yellow River is a “hanging river” across the hinterland of China, and the safety of its flood control measures/systems is closely tied to the stability of the nation. Ensuring high-quality, sustainable development of the lower Yellow River floodplain while maintaining flood safety is crucial for the entire Yellow River Basin. Previous studies have primarily focused on the overall development of the Yellow River Basin or the economic–ecological coupling development of cities along the river, often neglecting the flood safety development of the floodplain. This study optimizes the socio-economic–flood-safety–ecological (SFE) system of the typical downstream Landong floodplain within the Yellow River Basin. The system dynamics model (SDM) can simulate the dynamic behavior of SFE systems by constructing mathematical models that incorporate feedback loops and time delays. The primary components include causal loop modules and stock-flow modules. Then, a coupling coordination degree model for the Landong floodplain is established using a comprehensive subjective and objective weighting method, assessing the SFE system’s coordination under five scenarios: inertial development, economic development, environmental protection, flood safety, and sustainable development. The results of historical and validity tests indicate that the SDM can effectively simulate the coupling coordination degree of the SFE system. The study results suggest that the coupling coordination degree increases the most under the sustainable development scenario, indicating that the development of the Landong floodplain should not only focus on socio-economic growth, but should also consider flood safety and ecological concerns. In addition, comprehensive regulation from socio-economic, flood safety, and ecological environment indicators are necessary to achieve high-quality, coordinated development. This study has significant implications for policy formulation and management to achieve high-quality and sustainable development in the downstream floodplain of the Yellow River.

Urban floods increasingly pose threats to transportation systems, residential areas, and public safety, which has created an urgent need for rapid urban flood susceptibility mapping (UFSM) under varying rainfall conditions. In this study, five tree-based machine learning models, namely, random forest (RF), extreme gradient boosting (XGBoost), light gradient boosting machine (LightGBM), categorical boosting (CatBoost), and gradient boosting decision tree (GBDT) models, are evaluated for rapid UFSM generation under 18 rainfall scenarios with different return periods and rainfall patterns. Model performance is assessed on the basis of accuracy (ACC), F1 score (F1), precision (PRE), and recall (REC). Among the five models, the RF model performs best overall, with ACC, F1, PRE, and REC values ranging from 0.97 to 0.99, and is the most robust under the 50- and 100-year rainfall scenarios. The GBDT and CatBoost models perform poorly under low-return-period scenarios, whereas the XGBoost and LightGBM models perform better under high-return-period conditions but remain inferior to the RF model. Feature importance analysis reveals elevation, topographic position index, and curvature as the main controlling factors. These findings provide an efficient framework for rapid UFSM generation and offer useful support for urban flood risk management and planning.