Cite this article：
Patten, H., Anderson Loake, M. & Steinsaltz, D. Data-Driven Earthquake Multi-impact Modeling: A Comparison of Models. Int J Disaster Risk Sci (2024). https://doi.org/10.1007/s13753-024-00567-5
数据驱动的地震多重影响建模：模型间的对比研究
Hamish Patten, Max Anderson Loake & David Steinsaltz
摘要：
本研究广泛应用了有监督的机器学习、参数统计、地理空间和非地理空间模型，通过回归和分类模型分别对地震的综合观测影响估计数据和卫星图像生成的地理定位建筑损坏数据进行了建模。对于综合观测数据，本文通过预测375个观测值在61个国家的161次地震中关于死亡率、人口流离失所、建筑损坏和建筑损毁的预测性能来对模型进行排名；对于卫星图像生成的数据，通过预测26次地震中15个国家的369813座地理定位建筑的损坏（受损/未受损）情况来对模型进行排名。模型使用分组k折交叉验证和3次重复交叉验证以确保样本外预测性能。模型中代表灾害脆弱性的若干变量的重要性表明了协变量的实用性。本文采用2023年土耳其-叙利亚地震事件探讨模型在极端事件中应用的局限性。然而，应用AdaBoost模型对2023年土耳其-叙利亚地震事件中27032座作为测试数据集的建筑物进行预测，结果表明模型的AUC值达到0.93。因此，在没有任何地理空间、特定建筑或直接卫星图像信息的情况下，该模型准确地分类了建筑损坏情况，其性能显著优于文献中基于卫星图像训练的模型。
关键词：
灾害风险建模；地震影响模型；机器学习；灾害统计；卫星图像生成的建筑损坏情况
Data-Driven Earthquake Multi-impact Modeling: A Comparison of Models
Hamish Patten, Max Anderson Loake & David Steinsaltz
Abstract：
In this study, a broad range of supervised machine learning and parametric statistical, geospatial, and non-geospatial models were applied to model both aggregated observed impact estimate data and satellite image-derived geolocated building damage data for earthquakes, via regression- and classification-based models, respectively. For the aggregated observational data, models were ranked via predictive performance of mortality, population displacement, building damage, and building destruction for 375 observations across 161 earthquakes in 61 countries. For the satellite image-derived data, models were ranked via classification performance (damaged/unaffected) of 369,813 geolocated buildings for 26 earthquakes in 15 countries. Grouped k-fold, 3-repeat cross validation was used to ensure out-of-sample predictive performance. Feature importance of several variables used as proxies for vulnerability to disasters indicates covariate utility. The 2023 Türkiye–Syria earthquake event was used to explore model limitations for extreme events. However, applying the AdaBoost model on the 27,032 held-out buildings of the 2023 Türkiye–Syria earthquake event, predictions had an AUC of 0.93. Therefore, without any geospatial, building-specific, or direct satellite image information, this model accurately classified building damage, with significantly improved performance over satellite image trained models found in the literature.
Keywords：
Disaster risk modeling, Earthquake impact models, Machine learning, Disaster statistics, Satellite image-derived building damage
文章链接：
https://link.springer.com/article/10.1007/s13753-024-00567-5