Abstract Compound natural hazards like El Niño events cause high damage to society, which to manage requires reliable risk assessments. Damage modelling is a prerequisite for quantitative risk estimations, yet many procedures still rely on expert knowledge, and empirical studies investigating damage from compound natural hazards hardly exist. A nationwide building survey in Peru after the El Niño event 2017 – which caused intense rainfall, ponding water, flash floods and landslides – enables us to apply data-mining methods for statistical groundwork, using explanatory features generated from remote sensing products and open data. We separate regions of different dominant characteristics through unsupervised clustering, and investigate feature importance rankings for classifying damage via supervised machine learning. Besides the expected effect of precipitation, the classification algorithms select the topographic wetness index as most important feature, especially in low elevation areas. The slope length and steepness factor ranks high for mountains and canyons. Partial dependence plots further hint at amplified vulnerability in rural areas. An example of an empirical damage probability map, developed with a random forest model, is provided to demonstrate the technical feasibility.

中文翻译：

---

秘鲁厄尔尼诺事件损害建模的数据挖掘方法

摘要 厄尔尼诺事件等复合自然灾害对社会造成严重破坏，管理需要可靠的风险评估。损害建模是定量风险估计的先决条件，但许多程序仍然依赖于专业知识，而且几乎不存在调查复合自然灾害造成的损害的实证研究。在 2017 年厄尔尼诺事件导致强降雨、积水、山洪暴发和山体滑坡之后，秘鲁进行了全国性的建筑调查，使我们能够利用遥感产品和开放数据生成的解释性特征，将数据挖掘方法应用于统计基础工作。我们通过无监督聚类将不同主要特征的区域分开，并通过监督机器学习研究特征重要性等级以对损伤进行分类。除了降水的预期效果外，分类算法还选择地形湿度指数作为最重要的特征，尤其是在低海拔地区。山地和峡谷的坡长和陡度系数排名靠前。部分依赖图进一步暗示农村地区的脆弱性被放大。提供了使用随机森林模型开发的经验损坏概率图的示例，以证明技术可行性。