Near-real time estimation of damage to buildings and infrastructure, referred to as damage nowcasting in this study, is crucial for empowering emergency responders to make informed decisions regarding evacuation orders and infrastructure repair priorities during disaster response and recovery. Here, we introduce FloodDamageCast, a machine learning (ML) framework tailored for property flood damage nowcasting. The framework leverages heterogeneous data to predict residential flood damage at a resolution of 500 meters by 500 meters within Harris County, Texas, during the 2017 Hurricane Harvey. To deal with data imbalance, FloodDamageCast incorporates a generative adversarial networks-based data augmentation coupled with an efficient machine learning model. The results demonstrate the framework's ability to identify high-damage spatial areas that would be overlooked by baseline models. Insights gleaned from flood damage nowcasting can assist emergency responders to more efficiently identify repair needs, allocate resources, and streamline on-the-ground inspections, thereby saving both time and effort. Keywords: Flood damage nowcasting Data augmentation Generative adversarial network Light gradient-boosting machine Imbalance learning 1 Introduction Flood hazards wreak havoc on urban areas, resulting in both physical destruction and loss of life in densely populated regions. In the United States alone, annual insurance claims have hovered around $1 billion per year over the past four decades [1]. This financial burden is expected to persist and potentially worsen due to the escalating frequency and intensity of flood events resulting from climate change [2, 3]. Rapid damage assessment of flooded areas is essential for swift response and recovery of affected communities. Emergency responders and public officials rely primarily on visual inspection to evaluate flood damage, incurring significantly delaying the recovery process. Expediting the flood damage assessment process is instrumental to accelerating post-disaster recovery efforts and bolstering community resilience against flood hazards, Currently, the main approach for estimating flood damage is based on specifying inundation depths then utilizing historical flood depth damage curves [4, 5]. The applicability of this approach for flood damage nowcasting, however, would be limited due to significant computation effort needed to model inundation depths using hydrological models based on the principles of hydrodynamics [6, 7, 8, 9].

A project to develop breakthrough artificial intelligence technology for the anti-fraud sector is one of a number of new projects set to receive funding to enable the UK accountancy, insurance and legal services industries to transform how they operate. The artificial intelligence software, being developed by Intelligent Voice Ltd, Strenuus Ltd. and the University of East London will combine AI and voice recognition technology to detect and interpret emotion and linguistics to assess the credibility of insurance claims. The project is one of 40 backed by £13 million in Government investment to support collaborative industry and research projects to develop the next-generation of professional services. Artificial intelligence and data are transforming industries across the world.We are combining our unique heritage in AI with our world beating professional services to put the UK at the forefront of these cutting-edge technologies and their application. We want to ensure businesses and consumers benefit from the application of AI - from providing quicker access to legal advice for customers, to tackling fraudulent insurance claims, these projects illustrate our modern Industrial Strategy in action.

The rise in average sea level is predicted to double by 2100, putting hundreds of cities and millions of people at ever greater risk from the devastating effects of flooding. In 2016, flood damage in the Paris region cost an estimated €1 billion, so for this and many other cities, finding new and better ways to protect the property, infrastructure, and lives of their citizens is a race against time. Supported by the AXA Research Fund, Dr. Vazken Andréassian is working to improve the forecasting of floods in order to build more resilient cities. His research is using a wide range of data to better calibrate flood models to more accurately simulate the impact a flood wave will have on a city. This provides the basis of an early warning system for when and where flooding will happen, providing people with the most valuable defence against flood damage – time to act.

WE'VE long had eyes in the sky. But now a handful of start-ups are using these satellites to monitor everything from flood damage to crop yield with greater frequency and detail than ever before. Efforts to keep tabs on Earth from above began with NASA's Landsat programme, which started in 1973. It currently has two satellites in orbit imaging the whole of Earth's surface every 16 days. The resolution is high enough to capture major roads, but not individual houses.