Geospatial Bayesian Methods for Disaster Impact Estimation

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.

The primary CDT impact will be training 75 PhD graduates as the next generation of leaders in statistics and statistical machine learning. These graduates will lead in industry, government, health care, and academic research. They will bridge the gap between academia and industry, resulting in significant knowledge transfer to both established and start-up companies. Because this cohort will also learn to mentor other researchers, the CDT will ultimately address a UK-wide skills gap. The students will also be crucial in keeping the UK at the forefront of methodological research in statistics and machine learning.
After graduating, students will act as multipliers, educating others in advanced methodology throughout their career. There are a range of further impacts:
- The CDT has a large number of high calibre external partners in government, health care, industry and science. These partnerships will catalyse immediate knowledge transfer, bringing cutting edge methodology to a large number of areas. Knowledge transfer will also be achieved through internships/placements of our students with users of statistics and machine learning.
- Our Women in Mathematics and Statistics summer programme is aimed at students who could go on to apply for a PhD. This programme will inspire the next generation of statisticians and also provide excellent leadership training for the CDT students.
- The students will develop new methodology and theory in the domains of statistics and statistical machine learning. It will be relevant research, addressing the key questions behind real world problems. The research will be published in the best possible statistics journals and machine learning conferences and will be made available online. To maximize reproducibility and replicability, source code and replication files will be made available as open source software or, when relevant to an industrial collaboration, held as a patent or software copyright.