Evolutionary computing and optimisation
Optimisation is the search for better, more efficient solutions to benchmark and real-world problems. The optimisation research group focusses on developing new algorithms for discovering these solutions, based on the latest artificial intelligence research.
Our work is focussed on evolutionary algorithms, genetic programming, hyperheuristics, swarm intelligence and multi- and many- objective versions of these.
Particular research topics include new algorithm development, optimisation under uncertainty, interactive evolution and the use of surrogates in optimisation.
- Key contact: Professor Ed Keedwell - Associate Professor (Research Lead)
- Professor Richard Everson - Professor of Machine Learning
- Professor Jonathan Fieldsend - Associate Professor
- Dr Ke Li - Lecturer in Data Analytics
- Dr Alberto Moraglio - Lecturer
This 3-year, EPSRC-funded project will focus on developing interactive evolution approaches for use in the water industry in the UK and internationally. Interactive evolution uses human expertise in combination with automated techniques to develop solutions to problems that are feasible both from a mathematical and human perspective.
By combining optimisation algorithms with visual analytics, machine learning and human expertise, the project aims to deliver better, more usable solutions to industry and a greater understanding of the role that the user can play in the optimisation process.
The project has eight industrial partners including water companies, utilities consultants and visualisation specialists.
Professor Dragan Savic (Engineering)
Computational fluid dynamics (CFD) is fundamental to modern engineering design, from aircraft and cars to household appliances. It allows the behaviour of fluids to be computationally simulated and new designs to be evaluated. However, each CFD evaluation can take a long time, possibly hours or days.
This 3-year EPSRC-funded project aims to accelerate the optimisation process by substituting computationally simpler, dynamically generated 'surrogate' models in place of full CFD evaluation - learning appropriate surrogates from a relatively few well-chosen full evaluations, with multiple competing quality criteria for the final designs.
Our diverse range of industrial collaborations will ensure research is driven by realistic industrial problems and builds on existing industrial experience.
Professor Richard Everson (project lead)
Professor Gavin Tabor (Engineering)
This 3-year, EPSRC-funded project sits on the interface of computer science, mathematics and biology, and is focused on developing and applying state-of-the-art methods from computer science to parameter optimisation problems from systems biology.
Many processes critical for plant growth and reproduction are regulated by the circadian clock (e.g. photosynthesis and flowering time), however, as models have grown in complexity, so have the parameters to optimise. In the long term, the ability to optimise plant models of increasing complexity may help predict how the viability of economically important crop species will be affected by future temperature shifts resulting from climate change.
- Read more on the EPSRC grant webpage
Professor Jonathan Fieldsend (project lead)
Dr Ozgur Akman (Mathematics)
This 3-year, EPSRC-funded project seeks to exploit the increasing ability of bioengineers to develop novel stimuli-responsive gene networks - inspired by the genetic diversity of biological species - and embed these systems in functional materials.
Advances over the last decade have obviated the need for traditional gene cloning, meaning that almost any DNA sequence, natural or synthetic, can be chemically synthesised and assembled quickly. This offers an unparalleled opportunity to explore the relationship between DNA sequence and function.
The computer science component at Exeter is concerned with guiding the automated design of experiments needed in this work.
Dr Thomas Howard (Newcastle University, project lead)
Dr David Fulton (Newcastle University)
Professor John Love (Biosciences)
This 5-year, £3million EPSRC-funded project will provide a national 64-bit ARM-based High-Performance Computing (HPC) service through a consortium of the GW4 Alliance of the universities of Bristol, Bath, Cardiff and Exeter, in partnership with Cray and the Met Office.
The system will be one of the world's first to be based on Broadcom's Vulcan server-class chip.
Additionally, the project aims to provide a service to enable algorithm development and the porting and optimisation of scientific codes in readiness for ARM64 machines. This is a crucial part of any architectural evaluation, as rigorous architecture-to-architecture comparisons are only possible when optimisation levels across the architectures are similar.
Professor Simon McIntosh-Smith (University of Bristol, project lead)
Dr Ozgur Akman (Mathematics)
Dr Paul Calleja (University of Cambridge)
Professor James Davenport (University of Bath)
Professor Mark Parsons (University of Edinburgh)
Professor Roger Whitaker (Cardiff University)
Professor Beth Wingate (Mathematics)
Wind storms can cause great damage to property and infrastructure. The windstorm footprint is an important summary of the hazard, of great relevance to the insurance industry and to infrastructure providers.
Windstorm footprints are conventionally estimated from meteorological data and numerical weather model analyses. However there are several interesting, less structured data sources (video feeds, social media data, amateur meteorological observations) that could contribute to their estimation, and more importantly will raise the spatial resolution of estimates.
These will be investigated as part of this 4-year NERC-funded project which will develop and compare statistical process modelling and machine learning approaches to the problem.
- View details of the BigFoot NERC grant
Professor Peter Challenor (Mathematics, project lead)
Dr Theo Economou (Mathematics)
Professor David Stephenson (Mathematics)