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. Finding the best design is nonetheless very challenging because of the vast number of designs that might be explored. Computational optimisation is a crucial technique for modern science, commerce and industry. It allows the parameters of a computational model to be automatically adjusted to maximise some benefit and can reveal truly innovative solutions. For example, the shape of an aircraft might be optimised to maximise the computed lift/drag ratio. A very successful suite of methods to tackle optimisation problems are known as evolutionary algorithms, so-called because they are inspired by the way evolutionary mechanisms in nature optimise the fitness of organisms. These algorithms work by iteratively proposing new solutions (shapes of the aircraft) for evaluation based upon recombinations and/or variations of previously evaluated solutions and, by retaining good solutions and discarding poorly performing solutions, a population of optimised solutions is evolved. An obstacle to the use of evolutionary algorithms on very complex problems with many parameters arises if each evaluation of a new solution takes a long time, possibly hours or days as is often the case with complex CFD simulations. The great number of solutions (typically several thousands) that must be evaluated in the course of an evolutionary optimisation renders the whole optimisation infeasible. This research aims to accelerate the optimisation process by substituting computationally simpler, dynamically generated "surrogate" models in place of full CFD evaluation. The challenge is to automatically learn appropriate surrogates from a relatively few well-chosen full evaluations. Our work aims to bridge the gap between the surrogate models that work well when there are only a few design parameters to be optimised, but which fail for large industry-sized problems. Our approach has several inter-related aspects. An attractive, but challenging, avenue is to speed up the computational model. The key here is that many of these models are iterative, repeating the same process over and over again until an accurate result is obtained. We will investigate exploiting partial information in the early iterations to predict the accurate result and also the use of rough early results in place of the accurate one for the evolutionary search. The other main thrust of this research is to use advanced machine learning methods to learn from the full evaluations how the design parameters relate to the objectives being evaluated. Here we will tackle the computational difficulties associated with many design parameters by investigating new machine learning methods to discover which of the many parameters are the relevant at any stage of the optimisation. Related to this is the development of "active learning" methods in which the surrogate model itself chooses which are the most informative solutions for full evaluation. A synergistic approach to integrate the use of partial information, advanced machine learning and active learning will be created to tackle large-scale optimisations. An important component of the work is our close collaboration with partners engaged in real-world CFD. We will work with the UK Aerospace Technology Institute and QinetiQ on complex aerodynamic optimisation, with Hydro International on cyclone separation and with Ricardo on diesel particle tracking. This diverse range of collaborations will ensure research is driven by realistic industrial problems and builds on existing industrial experience. The successful outcome of this work will be new surrogate-assisted evolutionary algorithms which are proven to speed up the optimisation of full-scale industrial CFD problems.

The UK water sector is experiencing a period of profound change with both public and private sector actors seeking evidence-based responses to a host of emerging global, regional and national challenges which are driven by demographic, climatic, and land use changes as well as regulatory pressures for more efficient delivery of services. Although the UK Water Industry is keen to embrace the challenge and well placed to innovate, it lacks the financial resources to support longer term skills and knowledge generation. A new cadre of engineers is required for the water industry to not only make our society more sustainable and profitable but to develop a new suite of goods and services for a rapidly urbanising world. EPSRC Centres for Doctoral Training provide an ideal mechanism with which to remediate the emerging shortfall in advanced engineering skills within the sector. In particular, the training of next-generation engineering leaders for the sector requires a subtle balance between industrial and academic contributions; calling for a funding mechanism which privileges industrial need but provides for significant academic inputs to training and research. The STREAM initiative draws together five of the UK's leading water research and training groups to secure the future supply of advanced engineering professionals in this area of vital importance to the UK. Led by the Centre for Water Science at Cranfield University, the consortium also draws on expertise from the Universities of Sheffield and Bradford, Imperial College London, Newcastle University, and the University of Exeter. STREAM offers Engineering Doctorate and PhD awards through a programme which incorporates; (i) acquisition of advanced technical skills through attendance at masters level training courses, (ii) tuition in the competencies and abilities expected of senior engineers, and (iii) doctoral level research projects. Our EngD students spend at least 75% of their time working in industry or on industry specified research problems. Example research topics to be addressed by the scheme's students include; delivering drinking water quality and protecting public health; reducing carbon footprint; reducing water demand; improving service resilience and reliability; protecting natural water bodies; reducing sewer flooding, developing and implementing strategies for Integrated Water Management, and delivering new approaches to characterising, communicating and mitigating risk and uncertainty. Fifteen studentships per year for five years will be offered with each position being sponsored by an industrial partner from the water sector. A series of common attendance events will underpin programme and group identity. These include, (i) an initial three-month taught programme based at Cranfield University, (ii) an open invitation STREAM symposium and (iii) a Challenge Week to take place each summer including transferrable skills training and guest lectures from leading industrialists and scientists. Outreach activities will extend participation in the programme, pursue collaboration with associated initiatives, promote 'brand awareness' of the EngD qualification, and engage with a wide range of stakeholder groups (including the public) to promote engagement with and understanding of STREAM activities. Strategic direction for the programme will be formulated through an Industry Advisory Board comprising representatives from professional bodies, employers, and regulators. This body will provide strategic guidance informed by sector needs, review the operational aspects of the taught and research components as a quality control, and conduct foresight studies of relevant research areas. A small International Steering Committee will ensure global relevance for the programme. The total cost of the STREAM programme is £9m, £2.8m of which is being invested by industry and £1.8m by the five collaborating universities. Just under £4.4m is being requested from EPSRC

Globally, one in four cities is facing water stress, and the projected demand for water in 2050 is set to increase by 55%. These are significant and difficult problems to overcome, however this also provides huge opportunity for us to reconsider how our water systems are built, operated and governed. Placing an inspirational student experience at the centre of our delivery model, the Water Resilience for Infrastructure and Cities (WRIC) Centre for Doctoral Training (CDT) will nurture a new generation of research leaders to provide the multi-disciplinary, disruptive thinking to enhance the resilience of new and existing water infrastructure. In this context the WRIC CDT will seek to improve the resilience of water infrastructure which conveys and treats water and wastewater as well as the impacts of water on other infrastructure systems which provide vital public services in urban environments. The need for the CDT is simple: Water infrastructure is fundamental to our society and economy in providing benefit from water as a vital resource and in managing risks from water hazards, such as wastewater, floods, droughts, and environmental pollution. Recent water infrastructure failures caused by climate change have provided strong reminders of our need to manage these assets against the forces of nature. The need for resilient water systems has never been greater and more recognised in the context of our industrial infrastructure networks and facilities for water supply, wastewater treatment and urban drainage. Similarly, safeguarding critical infrastructure in key sectors such as transport, energy and waste from the impacts of water has never been more important. Combined, resilience in these systems is vitally important for public health and safety. Industry, regulators and government all recognise the huge skills gap. Therefore there is an imperative need for highly skilled graduates who can transcend disciplines and deliver innovative solutions to contemporary water infrastructure challenges. Centred around unique and world leading water infrastructure facilities, and building on an internationally renowned research consortium (Cranfield University, The University of Sheffield and Newcastle University), this CDT will produce scientists and engineers to deliver the innovative and disruptive thinking for a resilient water infrastructure future. This will be achieved through delivery of an inspirational and relevant and end user-led training programme for researchers. The CDT will be delivered in cohorts, with deeply embedded horizontal and vertical training and integration within, and between, cohorts to provide a common learning and skills development environment. Enhanced training will be spread across the consortium, using integrated delivery, bespoke training and giving students a set of unique experiences and skills. Our partners are drawn from a range of leading sector and professional organisations and have been selected to provide targeted contributions and added value to the CDT. Together we have worked with our project partners to co-create the strategic vision for WRIC, particularly with respect to the training needs and challenges to be addressed for development of resilience engineers. Their commitment is evidenced by significant financial backing with direct (>£2.4million) and indirect (>£1.6million) monetary contributions, agreement to sit on advisory boards, access to facilities and data, and contributions on our taught programme.