
Project Description
This project focuses on the conceptualisation, design, and development of disaster early warning systems (EWS) powered by digital twins (DTs). DTs are digital replicas of real-world systems that mirror their behaviour in real time, enabling precise, dynamic, and data-driven modelling. By addressing the limitations of traditional EWS, which often rely on static predictions and rule-based modelling, DTs offer an innovative approach to disaster risk management.
EWS play a critical role in mitigating disaster risks by facilitating timely actions before hazards occur. However, effective disaster risk assessments must account for dynamic and interdependent parameters, particularly for geohazards like landslides. These hazards are influenced by triggers such as rainfall, ground saturation, and slope instability, requiring sophisticated systems capable of real-time monitoring and prediction. Integrating real-time environmental data with DTs can enhance the understanding of trigger thresholds, model potential impacts, and simulate mitigation strategies.
By leveraging DTs, this project aims to deliver real-time, holistic insights to decision-makers, enabling them to respond promptly to deviations and simulate intervention outcomes. This dynamic approach strengthens disaster preparedness and response, ensuring early actions are more precise, impactful, and effective.
Project Specific Training
The student will receive comprehensive project-specific training through a blend of methods, ensuring a well-rounded skill set. This includes:
1. Digital Twin Development: Hands-on training in creating and deploying digital twins, provided by the supervisory team through one-to-one guidance and workshops.
2. Data Analysis and Integration: Instruction in processing real-time geospatial and environmental data, provided by the supervisory team and external courses on advanced data analytics and simulation techniques.
3. AI and Machine Learning: Training in the application of AI and machine learning for predictive modelling and real-time data analysis, delivered through tutorials and provided by the supervisory team and collaboration with AI experts.
4. Geohazard Modelling: Training in geohazard prediction and risk assessment, with access to specialised tools and software, delivered via tutorials and mentorship from domain experts, using supervisors’ network with British Geological Survey experts.
5. Interdisciplinary Collaboration: Opportunities to engage with internal and external partners, such as UCL warning research centre, and environmental monitoring agencies, for practical exposure to disaster risk management practices.
6. Scientific Communication: Support in developing skills for writing high-impact publications, presenting at conferences, and engaging with stakeholders, guided by the supervisory team.
This combination of tailored mentorship, technical skill development, and real-world application will equip the student to excel in geohazard research and disaster early warning systems, AI-driven disaster management innovation, and machine learning applications in risk prediction.
Potential Career Trajectory
This project offers diverse career opportunities both in academia and industry.
Academia:
– Researcher or Academic: Specialising in geohazard prediction, AI, and digital twins, with potential roles in universities and research institutions.
– Postdoctoral Researcher: Focusing on advanced geohazard modelling and AI applications.
Industry:
– Disaster Risk Management Specialist: Working with government or NGOs on disaster preparedness and early warning systems.
– Environmental Data Scientist: Applying AI and machine learning in environmental monitoring and predictive analytics.
– Technology Development: Contributing to companies developing digital twins, AI, or geospatial systems for disaster and geohazard management.
Access and Inclusion Statement
This project does not require extensive fieldwork or overseas travel, but it may involve some data collection or collaboration with external partners, which could require occasional travel. The project also relies heavily on access to digital tools, software, and advanced simulation platforms, which should be accessible to all applicants, including those with disabilities.
Potential Challenges and Reasonable Adjustments:
1- Fieldwork or Travel: While travel requirements are minimal, if they arise, reasonable adjustments can include virtual collaboration or remote data collection where feasible, as well as providing financial or logistical support for travel if needed. For those with caring responsibilities, flexible working hours and the option to work from home can be arranged.
2- Physical Accessibility: If any aspect of the project requires physical presence in specific locations, such as attending conferences or external meetings, adjustments like virtual attendance or alternative participation methods can be explored.
3- Digital Tools and Software: The project requires using advanced digital platforms. If an applicant has accessibility needs related to these tools, reasonable accommodations such as accessible software, screen readers, or assistive technologies will be provided.
Project supervisor/s
Saman Ghaffarian
Department of Risk and Disaster Reduction
UCL
s.ghaffarian@ucl.ac.uk
https://profiles.ucl.ac.uk/89003-saman-ghaffarian
Ilan Kelman
Department of Risk and Disaster Reduction
UCL
i.kelman@ucl.ac.uk
https://profiles.ucl.ac.uk/40787
Supervision balance
70:30
