Geospatial Bayesian Methods for Disaster Impact Estimation

在灾害事件（如地震或飓风）发生后的最初几个小时和几天内，在协调反应和救济工作方面作出了一些重要决定。这包括关于紧急基础设施的地点、主要人道主义捐助者提供的资金数额以及紧急援助的动员的决定。该项目的目标是进一步发展牛津灾害流离失所实时信息网，这是一个旨在对灾害事件的人道主义影响作出初步估计的工具。ODDRIN将关于灾害严重程度的实时信息与描述人口接触和脆弱性的现有数据，如人口密度和国民生产总值相结合。通过该模型，这被用来估计人道主义影响，如人口流离失所。ODDRIN目前的重点是地震影响评估。这项研究的贡献是开发了一个统一的预测工具，死亡率，位移和建筑物的破坏，已安装使用贝叶斯方法和相关的不确定性量化的好处。目前，灾害影响估计的主要提供者包括全球灾害警报和协调系统（GDACS）、美国灾害（HAZUS）、太平洋数据中心（PDC）和气候适应。这些工具要么需要数据，使其无法在全球范围内应用，要么不提供人类影响的数字估计，要么无法提供透明的基本模型。该项目的目标包括：进一步开发ODDRIN，以预测死亡率和建筑物的总损坏;应用和开发贝叶斯方法来拟合模型;利用高性能计算资源来加速模型拟合;以及使用测试数据验证模型拟合。拟合和测试模型还需要收集和处理来自一系列来源的数据，包括紧急事件数据库（EMDAT），国际地球科学信息网络中心（CIESIN），世界银行，开放街道地图和美国地质调查局（USGS）。进一步的目标将包括将ODDRIN扩展到旋风和洪水等持续性事件，并开发一个在线界面，用户可通过该界面应用ODDRIN并调查历史事件的绩效。该项目属于EPSRC统计和应用概率研究领域的福尔斯。

In the first hours and days following a disaster event (such as an earthquake or cyclone), a number of critical decisions are made in the coordination of response and relief efforts. These include decisions regarding the locations of emergency infrastructure, the amount of funding provided by major humanitarian donors, and the mobilisation of emergency aid. The goal of this project is the further development of the Oxford Disaster Displacement Real-time Information Network (ODDRIN), a tool aiming to provide initial estimates of the humanitarian impact of a disaster event. ODDRIN combines real-time information on hazard severity with existing data describing population exposure and vulnerability such as population density and GNP. Via the model, this is then used to estimate humanitarian impacts such as population displacement. ODDRIN currently focuses on earthquake impact estimation. The contribution of this research is the development of a unified prediction tool for mortality, displacement and building destruction that has been fitted using Bayesian methodologies and benefits from the associated uncertainty quantification. Currently, the main providers of hazard impact estimates include the Global Disaster Alert and Coordination System (GDACS), Hazard-US (HAZUS), the Pacific Data Center (PDC), and Climate-Adapt. These tools either require data that prevents them from being applied globally, do not offer numeric human impact estimates, or do not accessibly provide a transparent underlying model. The aims of this project include the further development of ODDRIN to predict mortality and aggregated building damage; applying and developing Bayesian approaches to fit the model; leveraging high-performance computing resources to accelerate model fit; and validating the model fit using testing data. Fitting and testing the model also requires the collection and processing of data from a range of sources including the Emergency Events Database (EMDAT), the Center for International Earth Science Information Network (CIESIN), the World Bank, Open Street Maps, and the United States Geological Survey (USGS). Further objectives will include the extension of ODDRIN to sustained events such as cyclones and floods, and the development of an online interface through which users can apply ODDRIN and investigate performance on historical events. This project falls within the EPSRC Statistics and Applied Probability research area.