Analytics for Dynamic Urban Risk and Disaster Impact Modeling

The ability of our cities to thrive in the face of uncertain future risks will depend on our ability to predict the consequences of such disasters so that we can mitigate them, and our capacity to effectively respond and recover from them when they occur. The proposed research addresses this dual challenge: (1) The risk profile of many Asian cities is rapidly changing due to climate change, urbanisation, and new patterns of vulnerability. The development of large-scale risk analysis models that can account for such dynamics will enable us to anticipate future trends in risk and guide our cities towards a resilient trajectory. This will be accomplished by creating and integrating nested models for dynamic hazard, dynamic exposure and dynamic vulnerability. Multi-level agent-based modelling, remote-sensing and machine learning techniques will be used to develop urban-scale dynamic risk simulations applicable to a broad range of cities and hazards. This represents significant advancements in probabilistic risk analysis and is expected to lead to new methods for the analysis and design of resilient infrastructure systems, financial protection (insurance) products, and policy decision-support tools. (2) In the immediate aftermath of a disaster, the first estimates of overall impact are based on an ad-hoc combination of predictive models, fly-over reconnaissance missions and field reports. The proposed work focuses on the integration of predictive models with new “big-data” streams such as satellites, distributed sensors, drones and crowd-sensing, in order to get disaster impact estimates with greatly increased accuracy and precision. New approaches for model-based machine learning, geostatics and Bayesian statistics will be used to analyse and transform these data into effective decision-support tools for disaster response and recovery planning. This second research component is linked to the first, since it is through the study of post-disaster consequences that new indicators of pre-disaster vulnerability can be identified.