While unprecedented amounts of building damage data are now produced after earthquakes, stakeholders do not have a systematic method to synthesize and evaluate damage information, thus leaving many datasets unused. We propose a Geospatial Data Integration Framework (G-DIF) that employs regression kriging to combine a sparse sample of accurate field surveys with spatially exhaustive, though uncertain, damage data from forecasts or remote sensing. The framework can be implemented after an earthquake to produce a spatially distributed estimate of damage and, importantly, its uncertainty. An example application with real data collected after the 2015 Nepal earthquake illustrates how regression kriging can combine a diversity of datasets—and downweight uninformative sources—reflecting its ability to accommodate context-specific variations in data type and quality. Through a sensitivity analysis on the number of field surveys, we demonstrate that with only a few surveys, this method can provide more accurate results than a standard engineering forecast.

中文翻译：

---

G-DIF：一种地理空间数据集成框架，用于快速估计震后损失

虽然地震后现在产生了空前数量的建筑物损坏数据，但利益相关者没有系统的方法来综合和评估损坏信息，因此许多数据集未使用。我们提出了一种地理空间数据集成框架 (G-DIF)，该框架采用回归克里金法将精确实地调查的稀疏样本与来自预测或遥感的空间详尽但不确定的损坏数据相结合。该框架可以在地震后实施，以产生空间分布的损害估计，重要的是，它的不确定性。一个包含 2015 年尼泊尔地震后收集的真实数据的示例应用程序说明了回归克里金法如何结合各种数据集——并降低无信息来源的权重——反映其适应数据类型和质量方面特定于上下文的变化的能力。通过对实地调查数量的敏感性分析，我们证明，只需进行少量调查，这种方法就可以提供比标准工程预测更准确的结果。