Hard optimisation problems are ubiquitous across the breadth of science, engineering and economics. For example, in water system planning and management, water companies are often interested in optimising several system performance measures of their infrastructures in order to provide sustainable and resilient water/wastewater services that are able to cope with and recover from disruption, as well as wider challenges brought by climate change and population increase. As a classic discipline, significant advances in both theory and algorithms have been achieved in optimisation. However, almost all traditional optimisation solvers, ranging from classic methods to nature-inspired computational intelligence techniques, ignore some important facts: (i) real-world optimisation problems seldom exist in isolation; and (ii) artificial systems are designed to tackle a large number of problems over their lifetime, many of which are repetitive or inherently related. Instead, optimisation is run as a 'one-off' process, i.e. it is started from scratch by assuming zero prior knowledge each time. Therefore, knowledge/experience from solving different (but possibly related) optimisation exercises (either previously completed or currently underway), which can be useful for enhancing the target optimisation task at hand, will be wasted. Although the Bayesian optimisation considers incorporating some decision maker's knowledge as a prior, the gathered experience during the optimisation process is discarded afterwards. In this case, we cannot expect any automatic growth of their capability with experience. This practice is counter-intuitive from the cognitive perspective where humans routinely grow from a novice to domain experts by gradually accumulating problem-solving experience and making use of existing knowledge to tackle new unseen tasks. In machine learning, leveraging knowledge gained from related source tasks to improve the learning of the new task is known as transfer learning, an emerging field that considerable success has been witnessed in a wide range of application domains. There have been some attempts on applying transfer learning in evolutionary computation, but they do not consider the optimisation as a closed-loop system. Moreover, the recurrent patterns within problem-solving exercises have been discarded after optimisation, thus experience cannot be accumulated over time. The proposed research will develop a revolutionary general-purpose optimiser (as known as transfer optimisation system) that will be able to learn knowledge/experience from previous optimisation process and then autonomously and selectively transfer such knowledge to new unseen optimisation tasks. The transfer optimisation system places adaptive automation at the heart of the development process and explores novel synergies at the crossroads of several disciplines including nature-inspired computation, machine learning, human-computer interaction and high-performance parallel computing. The outputs will bring automation in industry, including an optimised/shortened production cycle, reduced resource consumption and more balanced and innovative products, which have great potentials to result in economic savings and an increase of turnover. The proposed methods will be rigorously evaluated by the industrial partners, first in water industry and will be expanded to a boarder range of sectors which put the optimisation at the heart of their regular production/management process (e.g. renewable energy, healthcare, automotive, appliance and medicine manufacturers).

Water companies across the UK (and world) regularly inspect their sewers to prioritise maintenance and ensure the effective operation of their network. Failure to do so can result in incidents, including the discharge of untreated sewage to the environment, pipe collapse or even the formation of sewer blocking fatbergs. The importance of minimising these events is reinforced by the UKWIR objective to achieve zero uncontrolled sewer discharges by 2050. In most cases these occurrences are prevented using CCTV surveying and resolved with an early intervention. However, surveys are time consuming and expensive. Moreover, these reports are often inconsistent and inaccurate, largely due to human error and the subjective nature of fault codes. This project aims to augment the existing annotation and reporting process, with the overall ambition of fully automating the full CCTV surveying process. This proposed combination of AI and robotics will revolutionise sewer surveying and maintenance, improving the speed accuracy and efficiency of the entire practice. In turn this should result in the completion of more surveys and a much higher chance of pre-empting sewer failure. Currently SWW and the UoE are completing a KTP project, to internally implement the prototype fault detection method, investigated during the preceding PhD. The two-year partnership (due to complete in November 2020), has developed and trained the detection system on SWW's archive of CCTV footage and implementing this as a decision support tool. This is capable of highlighting faults and estimating their general type from recorded CCTV footage; extremely useful for the quick analysis of previously unused video that lacks annotation. Alongside technical developments, the project has built a network of collaborators (including iTouch and the WRc), whilst being widely publicised at both academic and industry events. Although the KTP has achieved its goal of bringing a functional tool to SWW, it is clear that the technology has potential for so much more, driving up efficiency and accuracy over current practices. The three key goals of the project are: (1) Develop the annotation capabilities of the technology to achieve the full standards outlined in the MSCC. (2) Implement the developed software so as to assist and perform live reporting. (3) Record and annotate previously unreported pipe features. The proposed project offers the opportunity to not only develop this research into a fully flourished technology for both UK and international use, but provides the resources and foundations for future image processing and machine learning research within SWW and the water industry as a whole. This research would continue to contribute solutions to national and global initiatives, aligning with the UN sustainable development goal ('protecting important sites for terrestrial and freshwater biodiversity'), UKWIR's Big Questions ('How do we achieve zero uncontrolled discharges from sewers by 2050?') and the UK industrial Strategy ('Increase sector productivity utilising AI'). Whether this takes the form of future visual inspection techniques or automation and support of other operational functions, the work would continue to drive efficiencies and improve performance using cutting edge computer science techniques.

Despite improved recycling infrastructure and public awareness, the UK still sends a staggering 17 million tonnes of municipal solid waste into landfill every year. This leads to the build up of leachate, the liquid which drains from a landfill site. Leachate contains trace chemicals, which can have strong contaminating effects on the environment, and therefore effective treatment methods are required. More to the point, however, ambitions for waste management should go beyond protection of human health and the environment, with conservation of energy and recovery of natural resources high on the agenda. This translational project aims to demonstrate an integrated process for leachate treat went and resource recovery. It involves three innovations: a novel physical pre-treatment, enhanced treatment with adaptively evolved microbial consortia and resource recovery through efficient biomass harvesting, and hence, contributing to the UK circular economy. The outcomes cut across several NERC research priority themes e.g. 'sustainable use of natural resources' and 'environment, pollution and human health.' Leachate can vary considerably in composition, depending on the age and type of waste within the landfill, containing both dissolved and suspended organic and inorganic material. Viridor Waste Management Ltd is the third largest waste management organisation in the UK, owning over 40 sites. Approximately half the sites use foul sewers to carry contaminated wastewater to a sewage works for treatment, the rest is either transported using tankers or released to surface waters. The total annual leachate production is 1,056,716 m3 and the operational costs vary between £4-£10 per m3 (e.g. disposal costs, energy or chemicals used). The previous work includes isolation of natural microbial consortia from leachate, novel harvesting method development and estimation of potential resources recovered. The main translational activities in this project are to design and build a pilot scale photobioreactor that is fitted with all the innovations from previous NERC and non-NERC funded research. This will be installed by Varicon Solutions, TUOS Research Technician and staff at Viridor at a local landfill site (Erin). Pre-processed leachate will be fed into the photobioreactor and growth and operating parameters carefully monitored. The data will be used in a techno economic assessment for Viridor but also other end-users. An easy-to-use Resource Recovery calculator will also be created. The process will be filmed in time-lapse and used to make a video for marketing, knowledge exchange and educational purposes. Both the video and photobioreactor system will be demonstrated at a relevant Trade Show in late 2017/early 2018. The ultimate aim is to demonstrate the progress of the NERC funded research up technology readiness levels with industrial, societal and environmental impact, together with economic benefits for the project partner and wider waste management community.

The uplands of Exmoor National Park receive a considerable proportion of the annual rainfall that supplies water to >500,000 consumers in the River Exe catchment. This area also contains large tracts of degraded peatland that were damaged by drainage and peat cutting in the 19th and 20th centuries. South West Water plc manage the water resources of the Exe Catchment and are investing in mire restoration for the purpose of improving the quality and quantity of water supplies. Amongst the numerous benefits of mire rewetting is the potential to alter the balance of trace gas exchange with the atmosphere to cause a net reduction in Global Warming Potential (GWP). Landowners at present do not receive financial reward for converting degraded moorland back to a natural wet state. They receive no monetary benefit for improvements in water quality or quantity, nor are they paid for enhancing rates of soil carbon sequestration or a net reduction of greenhouse gas emissions. The motivation for this study is South West Water plc's need to quantify net changes in GWP and improvements in water quantity and quality due to rewetting of upland mires for the purpose of securing funds to reward landowners that make areas of degraded peatland available for restoration. A project operated by the Environment Agency and Exeter University (and funded by South West Water plc) is underway to address the water supply and quality questions. The Bristol Open CASE PhD student will study cycling of the infrared absorbing gases carbon dioxide, methane and nitrous oxide in the same two headwater catchments that have been instrumented for the water study. The aim of this project is to quantify atmospheric and fluvial fluxes of these key greenhouse gases before and after ditch-blocking to determine the net impact of mire rewetting on GWP. An important aspect of the study will be to estimate errors and uncertainties in the flux data, more specifically, the timeline for establishing biogeochemical equilibrium in the soils after rewetting and the range of inter-annual variation in pre-restoration baseline fluxes. The former issue will be addressed using changes in the stable isotope composition of methane which varies with trophic and aeration status in peatlands and can be used to monitor the restoration of soil biogeochemical function. During the study, flux measurements will be made at stations in adjacent unrestored catchments to assess inter-annual variability in pre-restoration baseline fluxes because it will be possible to measure only one year of surface and fluvial fluxes before ditch-blocking begins in the test catchments. The PhD student will work with staff at South West Water plc to establish a monetary value (based upon trading of CO2 equivalents) for net changes in GWP. Pending the final outcomes of this study, the information may be used by the CASE Partner to negotiate monetary rewards for landowners in the 2015-2020 water price limits set by the Water Services Regulation Authority (Ofwat). The motivation is to establish a long-term system of incentives that will encourage more landowners to allow areas of degraded peatland to be restored for the wider benefit of society.

This research will directly benefit society in the UK and abroad by increasing the effectiveness of water companies. The aim of the fellowship is to establish new research avenues for innovation in the field of urban water engineering and to bring novel practical solutions to the water-related challenges, in particular climate change, existing in the UK and worldwide. The proposal addresses the EPSRC/LWEC fundamental question "How can our cities, their hinterlands, linking infrastructure, rural surround and the regions they are in, be transformed to be resilient, sustainable, more economically viable and generally better places to live?". To answer this challenging question the research will investigate the impact of environmental change on drinking water distribution systems (DWDS) with the aim of generating new knowledge and tools that will improve the way drinking water is supplied in our cities, in a sustainable and economically viable way. As a consequence of climate change water sources used for water supply will be more contaminated and limited, the temperature of the water will increase and long-term changes in water demand will affect pipe hydraulics. All these changes will significantly affect biological and physico-chemical processes taking place in DWDS and will force water companies to modify the way they deliver water via DWDS. The fellowship will support the essential first steps in a new research line where my aim is to integrate microbiology, genetics and water engineering to explore in detail hidden aspects of DWDS in order to develop a whole system understanding. At present, the monitoring strategies for drinking water involve detecting microorganisms in water from taps using "old-fashioned" culture methods. However, the microbial composition of water is not representative of the biofilms (microbial assemblages) attached to pipes and culture-dependent methods underestimate the real microbial diversity in DWDS. Biofilms have great importance since they contain most of the microbial biomass in DWDS and they influence water quality and safety by, for example, hosting pathogens, promoting pipe corrosion and changes in water taste and colour. Consequently, there is an urgent need for research on how microorganisms will respond to environmental change within DWDS and how this will impact on DWDS performance and on drinking water safety and quality. Since DWDS are not sterile (i.e. completely free from microorganisms), research is also needed to identify which parameters support the presence of "friendly microorganisms" capable of maintaining the good performance of DWDS but also discouraging harmful microorganisms from surviving in the pipes. To answer these questions the research will assess different climate change situations in DWDS tested under controlled laboratory conditions including: increase in water temperature, increase in water nitrogen and phosphorus and extreme hydraulic fluctuations. Analysis of DNA/RNA from experimental samples will be used to uncover the link between microbial diversity (who is there?) and function (what are they doing?), and will help to identify genes involved in a range of processes including resistance to disinfection and pathogenic potential. Biological and environmental data will be integrated using hydro/bioinformatic methods with the ultimate aim of developing novel monitoring and management tools: 1) a new risk assessment framework; and 2) Biological Early Warning Systems (BEWS). The efficiency of these tools will be tested using real data from UK water companies and European partners. Dissemination of findings to industry, academics and the general public will be supported by the Pennine Water Group and through the Sheffield Water Centre. The fellowship will facilitate the development of my career as a world leader in urban water research by creating a new platform for innovation in molecular microbiology and hydraulic engineering.