Pre-disaster planning and mitigation necessitate detailed spatial information about flood hazards and their associated risks. In the US, the Federal Emergency Management Agency (FEMA) Special Flood Hazard Area (SFHA) provides important information about areas subject to flooding during the 1 % riverine or coastal event. The binary nature of flood hazard maps obscures the distribution of property risk inside of the SFHA and the residual risk outside of the SFHA, which can undermine mitigation efforts. Machine learning techniques provide an alternative approach to estimating flood hazards across large spatial scales at low computational expense. This study presents a pilot study for the Texas Gulf Coast region using random forest classification to predict flood probability across a 30 523 km² area. Using a record of National Flood Insurance Program (NFIP) claims dating back to 1976 and high-resolution geospatial data, we generate a continuous flood hazard map for 12 US Geological Survey (USGS) eight-digit hydrologic unit code (HUC) watersheds. Results indicate that the random forest model predicts flooding with a high sensitivity (area under the curve, AUC: 0.895), especially compared to the existing FEMA regulatory floodplain. Our model identifies 649 000 structures with at least a 1 % annual chance of flooding, roughly 3 times more than are currently identified by FEMA as flood-prone.

中文翻译：

---

在大空间尺度上使用随机森林分类和洪水保险索赔对连续洪灾危害进行量化：德克萨斯州东南部的一项试点研究

灾前规划和减灾需要有关洪水灾害及其相关风险的详细空间信息。在美国，联邦紧急事务管理局（FEMA）特殊洪灾危险区（SFHA）提供有关在1 ％的河流或沿海事件中遭受洪灾的地区的重要信息 。洪水灾害图的二元性质掩盖了SFHA内部财产风险的分布以及SFHA外部的剩余风险，这会破坏缓解工作。机器学习技术提供了一种替代方法，可以以较低的计算成本在较大的空间范围内估算洪水灾害。这项研究提供了德克萨斯州墨西哥湾沿岸地区的初步研究，该研究使用随机森林分类来预测30 523 km ^2的洪水概率区域。使用可追溯到1976年的国家洪水保险计划（NFIP）索赔记录和高分辨率的地理空间数据，我们为12个美国地质调查局（USGS）八位水文单位代码（HUC）流域生成了连续的洪水灾害图。结果表明，与现有的FEMA监管洪泛区相比，随机森林模型预测洪水的敏感性高（曲线下面积，AUC：0.895）。我们的模型确定了649 000处每年至少有1  ％发生洪水的机会的结构，大约是FEMA当前确定为容易发生洪水的3倍多。