Digital Twins for Disaster Early Warning Systems

Project ID: 2228cd1388 (You will need this ID for your application)

UCL Lead department: Institute for Risk and Disaster Reduction (IRDR)

Project Summary:

Early warning systems as a crucial part of disaster risk management aim at enabling vulnerable communities or systems to take timely actions and mitigate disaster risks in advance of the imminent hazardous event/s. Current early warning systems are based on conventional rule-based modelling usually focusing on one or a few components and elements at risk, probabilistic scenarios and impact assessments largely using static predictions and manually derived information. However, such systems require complex and dynamic modelling. A Digital Twin is a digital equivalent to a real-life object, process, or system of which it mirrors its behaviour and states over its lifetime in a virtual space. Using Digital Twins as a central means for early warning systems enables decision-makers to manage early warning-based operations from a holistic point of view employing real-time digital information. This allows them to act immediately in case of deviations and to simulate effects of interventions and decisions based on real-life data. The main objective of this project is to conceptualise, design and develop digital twins-based disaster early warning systems that dynamically learn from (near) real-time data and predict impacts for effective and timely early actions.

You will work with different organizations, including governments, remote sensing data providers, local authorities, and current early warning system providers to collect data and test your developed model. You will develop AI-based methods to process the sensor-based data. You will conceptualise, design and develop digital twins-based disaster early warning systems. Who we are looking for: • You have a Master of Science degree, preferably in Computer Science, Geo-Informatics, Disaster Risk Management, or related fields. • You are fluent in python, machine learning, and deep-learning tools. • You have knowledge of disaster and risk reduction. • Expertise in data science and statistics (e.g., big data analysis, Internet of Things) is an advantage.