Urban residential fires seriously threaten public safety, causing significant property damage and severely impacting urban sustainability. To enhance the understanding of urban residential fire risks, a framework that combines tree-based machine learning algorithms and resampling techniques is proposed to predict damage and casualties in residential building fires. All algorithms achieved similar results on the original dataset, with 86 % and 93 % accuracy and the highest average F1 scores of 61 % and 51 %, respectively. Various resampling techniques addressed the issue of data imbalance, with the combination of random undersampling and SMOTE achieving the best model performance, elevating the average F1 scores to 75 % and 77 %, representing improvements of 14 % and 26 % over the original dataset, respectively. Furthermore, the internal mechanisms of the model were explored using the explainable Shapley additive explanations, which identified the key features influencing model outputs. Additionally, the study revealed significant heterogeneity in different regions, sources of ignition, causes of fires, types of residences, locations of fire origin, and types of households. This research not only improves emergency response strategies for urban residential fires but also provides tailored fire safety policies to reduce risks in various urban environments effectively.

中文翻译：

---

使用重采样技术和可解释的机器学习进行调查，以最大限度地减少住宅建筑的火灾损失


城市住宅火灾严重威胁公共安全，造成重大财产损失，严重影响城市可持续发展。为了增强对城市住宅火灾风险的理解，提出了一种结合基于树的机器学习算法和重采样技术的框架来预测住宅建筑火灾中的损失和伤亡。所有算法在原始数据集上都取得了相似的结果，准确率分别为 86% 和 93%，最高平均 F1 分数分别为 61% 和 51%。各种重采样技术解决了数据不平衡问题，随机欠采样和 SMOTE 相结合实现了最佳模型性能，将平均 F1 分数提高到 75% 和 77%，分别比原始数据集提高了 14% 和 26% 。此外，使用可解释的 Shapley 加法解释探索了模型的内部机制，确定了影响模型输出的关键特征。此外，该研究还揭示了不同地区、火源、火灾原因、住宅类型、起火地点和家庭类型的显着异质性。这项研究不仅改进了城市住宅火灾的应急响应策略，还提供了量身定制的消防安全政策，以有效降低各种城市环境的风险。