建成环境视角下高密度城市内涝风险预测与影响因素机器学习解析:以深圳市为例  

Prediction and Machine Learning Analysis of Urban Waterlogging Risks in High-Density Areas From the Perspective of the Built Environment:A Case Study of Shenzhen,China

作　　者：周士奇 贾蔚怡 刘治宇 王墨 Shiqi ZHOU;Weiyi JIA;Zhiyu LIU;Mo WANG(College of Design and Innovation,Tongji University,Shanghai 200092,China;College of Architecture and Urban Planning,Tongji University,Shanghai 200092,China;Shanghai Tongji Urban Planning&Design Institute Co.,Ltd.,Shanghai 200082,China;College of Architecture and Urban Planning,Guangzhou University,Guangzhou 510006,China)

机构地区：[1]同济大学设计创意学院,上海200092 [2]同济大学建筑与城市规划学院,上海200092 [3]上海同济城市规划设计研究院有限公司,上海200082 [4]广州大学建筑与城市规划学院,广州510006

出　　处：《景观设计学（中英文）》2024年第5期48-67,共20页Landscape Architecture Frontiers

基　　金：广东省自然科学基金青年提升项目“基于气候适应性的城市灰绿基础设施韧性增强及动态规划”(编号:2023A1515030158)。

摘　　要：伴随着大数据和人工智能技术的演进,多种基于数据驱动的机器学习算法已逐渐在城市韧性研究中得到广泛应用,尤其是针对城市内涝这一关键问题。目前,解决城市内涝的重要任务是从建成环境的角度理解内涝影响因素,并指导动态监测和预警服务。本研究选取深圳市作为高密度城市的典型代表,构建了涵盖水文、气象、城市形态和内涝事件等多方面数据的多因子联动数据集,并对比了四种主流机器学习模型(Light GBM、RF、SVR和BPDNN)在预测城市内涝风险方面的性能差异。结果显示,Light GBM在精确性和鲁棒性上表现最佳,能够有效预测城市街区的内涝深度及相应的风险等级。研究进一步采用了可解释性算法(SHAP)对Light GBM模型进行解耦分析,结果显示,水文气象因子(降雨总量和降雨延时)及部分建筑配置因子(如建筑密度和建筑拥挤度)为主要的灾害影响因子;另外,水体率对内涝的调节和蓄积起到重要作用,特别是当其超过2.5%时,表现出显著的内涝抑制效果。本研究为城市内涝预测提供了新的技术方法,并从建成环境视角揭示了影响城市内涝的因素以及其内在机制,对高密度城市韧性的提升具有重要的科学意义。With the continuous advance of big data and artificial intelligence technologies,various data-driven machine learning algorithms have been widely applied in the studies of urban resilience,particularly in addressing the challenging issue of urban waterlogging.Currently,it is a pressing task to understand the influencing factors of waterlogging from the perspective of built environment,and provide guidance on dynamic monitoring and early alarm services.Focusing on Shenzhen,China,a typical high-density urbanized city,this research constructed a multifactorial dataset encompassing hydrological,meteorological,urban morphology,and waterlogging event data.Then,this research assessed and compared the performance of four mainstream machine learning modelsDLightGBM,RF,SVR,and BPDNNDin predicting urban waterlogging risks.The results showed that LightGBM had the best accuracy and robustness in predicting waterlogging depths and risk levels in urban areas.The research also employed interpretability algorithmDShapley Additive Explanations(SHAP)Dfor decoupling analysis.The results indicated that hydro-meteorological factors(the total rainfall volume and the rainfall lasting time)and several architectural configuration factors(e.g.,density of buildings,building congestion degree)are the main influencing factors.In addition,the percentage of water body is vital to waterlogging regulation and retention,especially exhibiting a significant mitigating effect when exceeding 2.5%.This research provides a new technical method for urban waterlogging prediction and reveals the influencing factors and intrinsic mechanisms from the perspective of built environment,which is of great significance for the enhancement of the resilience of high-density cities.

关 键 词：城市内涝 机器学习 模型性能评估 比较研究 可解释性分析 高密度城市 

分 类 号：TU984.116[建筑科学—城市规划与设计] TP181[自动化与计算机技术—控制理论与控制工程]