Public Funding for Previsico Limited

Following initial supervision of climate related financial risks, The Bank of England requires UK banks and insurers to stress test their assets and liquidities against climate risks biennially; the next stress test is planned for summer 2023\. Participating insurers will need to respond to questions around their strategic responses to the three CBES scenarios. Central to these are the abilities of banks to have sufficient reserves for climate shocks. Estimating damage from flooding has always been reliant on understanding the depth and duration of events. Use of depth-damage curves has become industry standard for finance and insurance modelling. However, before an event, no system has been able to supply such data as existing technologies only show areas at risk based on generic event simulations. By simulating predicted depth times of floods ahead of events, Previsico has created the ability to produce pre-event automated loss estimations, for the first time, globally. Specifically, loss estimates for surface water and small watercourse flooding provide critical insights for the financial sector to support decision making, driving climate resilience. Further, loss estimates delivered alongside real-time risk assessments for assets can 1) help insurers reserve enough capital in advance of events so that they are able to pay-out their customer's claims in a timely and cost-effective manner and 2) support improved flood response capabilities for both the financial sector and associated stakeholders, helping deliver direct and indirect savings to assets and critical infrastructure, and mitigate impacts on the wider economy by supporting business continuity. During Phase 1, a MVP - representing the combination of flood forecasts and nowcasts and forecasted losses on a single dashboard and email - was developed, tested and then demonstrated in a non-production environment. Phase 2 will correspond to the operationalisation, live trialling and then refinement of the developed MVP in partnership with financial sector partners/clients with different specialisms and therefore, applications/uses for the technology. Specifically, the developed MVP will be extensively trialled across the UK, with stakeholder feedback on the form and functionality of the developed MVP collected. Furthermore, and through focused feedback sessions with selected partners, feedback on algorithm performance will be sought and used to significantly improve the accuracy of outputs, the granularity of forecasting losses, and the way forecasts are communicated. An integral part of this work will be accessing the partners portfolios of loss data to back-test past events, comparing their claims experience against Previsico's loss predictions.

Hazard warning systems are being increasingly employed globally, though these fail to account for surface water flooding -- the greatest flood risk of all -- or flooding from ordinary water courses. Previsico currently delivers to asset owners a warning and forecast service for surface water flooding at 25m resolution using its proprietary live hydrodynamic modelling software. Flood forecasts are generated every three hours and are produced using the latest rainfall nowcasts and forecasts. The service issues property-level alerts so assets can be moved to safety, and organisations can improve their flood response. It is the first technology on the market to offer flood warnings that cover surface water and ordinary water course floods. It is also continuously improving, generating high-confidence, property-level real-time predictions. However, whilst warnings are important for mitigating physical impacts and losses, they can be better tailored for coordinating the responses of insurers, re-insurers, and the wider finance sector. Of particular note, the accuracy of catastrophe claim reserves that depends on correct and timely loss estimates can directly affect the solvency and stability of a company. Loss estimation tools combining flood nowcasting and forecasting for perils that are rarely accounted for (e.g. surface water and ordinary water course flooding) are urgently needed to help insurers and reinsurers make reserving decisions with confidence. Such tools can further support hedge funds in issuing catastrophe bonds covering areas at low risk of flooding. For example, if predicted losses are negligible, catastrophe bonds are not triggered and the hedge funds are not liable for pay-out to their clients, increasing profits. Timely financial loss estimates delivered in a timely fashion can be crucial for helping financial and insurance industries weather climate shocks. This project will develop a loss estimation algorithm parameterised using Previsico's world-leading forecast- and nowcast-derived flood extent and depth data and asset exposure and vulnerability data to produce financial risk forecasts and nowcasts. These will in turn be delivered to customers via Previsico's flood dashboard and alongside asset alerts and flood intelligence, will support emergency response coordination, helping deliver direct and indirect savings to assets and critical infrastructure, and mitigation of impacts on the wider economy by supporting business continuity. To ensure the developed product meets the needs of end users, Swiss Re Corporate solutions will support this project by: - Supporting product design with relevant knowledge, insights, and feedback. - Providing opportunities for testing the proposed solution with customers.

Previsico's vision, having spun-out from the University in Jan 2019, is to transform what was an innovative research project into a global early warning enterprise, saving lives and livelihoods. We will globally revolutionise the way insurers engage with their policyholders during a flood. Our innovation delivers high confidence, real-time flood predictions and impact analytics at the street level, tailored to the needs of a range of global customers. It is the first technology to offer highly-scalable flood nowcasting and forecasting products around the clock at high frequency, capturing every flood with high accuracy. The technology is capable of real-time flood predictions for all types of flooding including river, coastal and surface water. We have developed a commercially viable national flood forecasting solution. Our work will transform an inefficient, painful and costly flood response, mitigation and insurance claims system into a proactive process where insurers effortlessly supporting their customers through the entire lifecycle of a flood. This will help minimise the impact of flooding on insurance companies, governments and the communities affected by flooding. It will also help reduce the pain of extended and agonising claims processes as the insurer will receive the information they need from the customer to mobilise resources and fast-track claims. Our work has been built on extensive global research and market validation and is underpinned by a strong set of achievable milestones. We have a dynamic team, combining decades of experience in flood modelling, risk communication, software development and customer support. Project, technical and other risks have been identified and each has management action plans to mitigate and minimise the risk's impact. The plan evidences the demand across the insurance industry and substantial economic impact. The project will transform a forecasting system into a globally used solution for early warning of hazards which will save lives and livelihoods.

"FloodMap Live is a project which uses a combination of technological innovations to deliver continuous high confidence flood predictions at the street level, tailored to the needs of our customers. It is the first technology to offer highly-scalable flood nowcasting and forecasting products around the clock at high frequency, capturing every short-duration flood with high accuracy. This project addresses a major gap in flood predictions, saving lives and livelihoods. Our innovations include: * **Combined flood nowcasting and forecasting:** FloodMap Live utilises real-time weather nowcasts (<6 hours ahead) and forecasts (\>6 hours ahead) for flood predictions. These are regularly updated and calibrated to deliver the most up-to-date predictions. * **Street-level resolution:** The system delivers high resolution products using FloodMap -- a leading academic software for flood inundation modelling. It has been widely used in many applications, including recently in New York City, Shanghai and Bangkok. These applications recorded high levels of accuracy using ground-truthed validation data. * **Real-time analytics and impact modelling:** Through years of research and development with key partners, we are establishing bespoke analytics and impact models to support our customers. * **Tailored visualisations:** The outputs of FloodMap Live can be delivered as a data feed, tailored alerts or visualisations over large spatial and temporal domains. These are continuously being developed together with our customers. There is a growing need for cross-border early warning systems to strengthen the preparedness phases of disaster risk management. Our project will help improve the UK population, economy, exports industry and the quality of our aid delivery abroad."