Sequential sampling methods for difficult problems Developing methods to address difficult problems by sampling from the random trajectories of collections of interacting 'particles'
Nature inspired routing for resilient networked systems Learning from resilient ecosystems in nature to inform the design of real-time traffic routing and long-term transport infrastructure
A machine learning revolution in disaster response When a natural disaster strikes, emergency responders and aid agencies need all the intelligence they can get. Turing researchers have combined crowd-sourcing, machine learning and neural networks to rapidly reveal the many dimensions of disasters, and deployed the technology in the aftermath of Hurricane Dorian
London air quality Developing machine learning algorithms and data science platforms to understand and improve air quality over London
Computational statistical inference for engineering and security (CoSInES) Creating a step change in the use of statistical methodology, motivated by challenges in modelling, computation, and statistical algorithms
Robust inference for air quality monitoring Developing new computational and statistical tools to better understand and predict urban air quality
Critical infrastructures as a control system Developing smart data communication protocols to achieve robustness and resilience of complex critical infrastructures
Data-driven nuclear management Developing data-driven decision support systems to enable faster, more effective decision making for nuclear engineering operations
Data-driven experiment design Developing new statistical tools to select the most informative biological laboratory experiments to perform, to maximise learning and minimise research costs