The UK, Ireland, Canada and France have all declared climate emergencies. Climate change has never had a more prominent in the public eye. With legal commitments to reduce greenhouse gas emissions by at least 80% by 2050 relative to 1990 levels, it has never been more important to do everything we can to reduce energy demand. The promise in this project is to help provide new methods for analysing the 'data deluge' of energy and building system data (from IoT devices) that can help unlock energy efficiencies and identify the benefits of energy efficiency measures despite noisy and heterogeneous data; and make it cheap, repeatable and routine to do this on an ongoing basis. Key to our approach are novel statistical and mixed-method techniques working closely with our project partners and their data to demonstrate the feasibility of these benefits. Our ultimate goal is to make it possible to translate the savings found in one context to another (e.g. another similar building, or even similar business). This would enable the 'digital replication' of energy efficiency savings, and even an almost viral spread of the knowledge and technique across sectors---with massive potential. Currently for many organisations, making sense of this rich source of information defies the human resource available to analyse and profit from the potential insights available. Such analysis is currently the domain of specialist consultancy providers due to the significant cost, time and know-how required to identify opportunities in the data. This restricts the penetration of data-driven monitoring and energy reduction strategies, and the opportunities for knowledge transfer across different locations and businesses. This project will clear this analysis bottleneck. The approach builds on foundations in modern data science, applying cutting edge techniques to automatically identify problems at particular sites and recommend interventions based on cross-site comparisons. The principle objective is to enable commercial sites to reduce their energy demand and keep it low without requiring energy analysts to manually investigate each site individually, at further expense. Core to our approach are next-generation statistics and machine learning methods applied to a unique corpus of fine-grained energy and process data sourced from our partners (BT, Tesco, Lancaster University Facilities (a town sized campus), and energy management consultancy and cloud energy analytics provider, BEST). This will enable us to apply cutting edge statistical techniques to a very significant data set in this domain for the first time. More specifically, our main aims are to: 1. develop automated techniques for supporting analysis, identifying and recommending energy savings strategies, based on the application of statistical and machine learning techniques to fine-grained energy data; 2. derive knowledge of how, where and when energy is used, to identify opportunities to reduce and shift demand by comparing differences in energy use over time within and between premises; 3. support regular and repeated analysis, towards a continual improvement in energy reduction over time. 4. provide open source, permissively licensed implementations for enabling uptake, even beyound our project partners and their partner networks. Our publication and publicity strategies will maximise exposure of our project results to various stakeholder groups including academia, practitioners, and key industry stakeholders.

In the UK retail outlets are the biggest emitters of CO2 within the commercial property sector. Many retail business are striving to reduce their carbon footprints, with many having ambitious targets for carbon neutrality over the next few years. This feasibility study aims to identify new ways to dramtically reduce end use energy demand within the retail sector. The novelty of the proposed work lies both in its scope and the technologies that it will develop. Rather than attributing energy use and human comfort directly to spatial design, building services, energy controls, company energy policy or human behaviour, this research will explore the intersection of all of these influences within a 'mixed reality' retail environment. This would take the form of an interactive 'gaming' model as a portable 'box' with a tangible user interface deployed in store. It would allow users to 'visualise' energy use and its consequences as part of a broader energy engagement strategy. The box would comprise a scale model of a physical store layout and a set of coded intervention cards that would allow participants to interact with the physical model on the table as well as in the virtual model - the blend between physical and virtual interactions establishes a mixed reality design platform (MRDP). Real time data from existing store sensors can feed directly into the virtual model to inform and respond to scenario testing as users interact with the model. Store staff and customers would be able to engage with the model proactively or passively via a mix of physical, virtual and display modules. This serious gaming environment will provide a stimulating and interactive way of sharing ideas and co-creating new solutions. Most importantly, the MRDP transforms what is normally an intangible numerical database (numbers collected by performance sensors) into an interactive and immersive experience to allow for continual testing and refinement with the opportunity of users co-creating novel approaches to reducing energy use while maintaining a positive shopping experience. The learning that accrues through this serious gaming activity would inform future strategies for reducing energy demand whilst simultaneously attending to other performance criteria (e.g. internal air quality, thermal comfort and the customer experience). The mobility and placement of the MRDP allows the retail floor or back of house area to become a platform for learning and drives a more open relationship with stakeholders. Our principal research partner is Tesco PLC, the UK's largest retailer with revenue of over £55 Billion. Tesco have an ambitious commitment to become a zero carbon business by 2050, and as part of this they aim to reduce carbon emissions in store by 50% over the next 4 years. This research would support their objectives by developing an exciting method of accelerating their progress towards their corporate goal and will help position the organisation at the vanguard of current technology and thinking in the energy demand reduction space.

The "Internet of Food Things" will create an interdisciplinary network that defragments and expands the UK's food digital economy. Food and drink is the largest manufacturing sector of the UK economy. The food supply chain from farm to consumer generates £108bn GVA per year and employs 3.9m people. In addition, food has highly significant social and environmental impacts. Obesity alone, including downstream health impacts such as diabetes, heart disease etc, costs the UK economy £49bn per annum. There are still c. 1,000,000 cases of food poisoning per year costing £1.5bn p.a.. Food generates up to 30% of the UK's road freight, but 10MT of food, generating 20MTCO2e of GHG emissions, are wasted each year. Digital technology has the potential to transform the food chain, for example, opportunities (that map onto the EPSRC DE Network strategy) include but are not limited to; - New business models via distributed ledger technology (DLT) to underpin the traceability of food. The recent Holmes report identified food as one of the key seven UK industry sectors most likely to benefit from DLTs. - The creation of a "data trust" for the food sector to underpin data sharing, trust and interoperability within complex supply chains. - Wide scale application of the internet of things (IoT) for the service community, for example, the use of IoT by domestic users (refrigerators, cooking devices etc) to improve health outcomes and reduce waste. - The development of new digital labelling protocols that assist with consumer use of food as well as supply chain optimisation, - The use of novel digital technologies (e.g. artificial intelligence) to reduce food waste by optimising whole supply chains from manufacturer to consumer. Hitherto these opportunities have not or are only partially realised. There is an urgent need to defragment the digitally inspired academic community and connect it to food industry practitioners. Although the digital focus is in within EPSRC's remit (IoT, blockchain, data trusts, interoperability issues), we will multiply impact by including interdisciplinary contributions from food science and technology practitioners, policy makers, engineers, management specialists and colleagues in social and behavioural sciences. The network will include academia, industry and consumer interests. The industry interest covers the whole food and digital innovation chain including food manufacturers (e.g. Food and Drink Federation, EPSRC Food CIM), IoT and digital specialists (Siemens and IMS Evolve), the HVM Catapult and regulators such as the Food Standards Agency and GS1 the international agency that sets data standards (bar codes) for retail. Consumers will be represented through out, but the inclusion of food retailers within the consortium provides access to unrivalled data sets demonstrating behaviours. The DE network will facilitate a number of key actions, including a marketing, social media and work shop / conference campaign that yields a large scale (up to 500 persons) network who have mutual interests within the food digital domain. We will host one main conference per year and in addition 3 facilitated workshops p.a. to deep dive key questions within the food domain. We will fund a range of pilot studies (£350K applied) and detailed reviews to underpin horizon scanning. All the research challenges will be co created with industry. We expect that the network will facilitate onward research funding and catalyse interest in the food digital economy. In addition to network activities, we will deliver a comprehensive pathway to impact that engages professional practitioners as well as the general public and schools.

Lancaster University, together with a formidable consortium of industrial and third-sector partners, proposes a Centre for Doctoral Training (CDT) aimed at cultivating international research leaders in Statistics and Operational Research (STOR) through a programme in which real-world challenge is the catalyst for cutting-edge methodological advancement. Our partners face a challenging reality: the demand for highly-trained STOR data specialists consistently exceeds the available supply. This situation is exacerbated by the ever-growing significance of data in both the economy and society. Our proposal directly addresses this pressing demand, focussing on the priority area "meeting a user-need". The newly envisioned Centre builds upon the strengths and knowledge derived from an existing, internationally recognised EPSRC CDT. Expanding upon this foundation and with the input of an enlarged partner network, including blue-chip companies, SMEs, and third-sector organisations, we propose a Centre poised to recruit and train 70 students across five cohorts. This program will harness industrial and charitable challenges as inspirational springboards for conducting the highest calibre research. The new programme will innovate by * Developing a new MRes programme co-designed and delivered with our partners; * Including a comprehensive training programme on advanced, reproducible programming for STOR, co-ordinated by the Centre's dedicated, industry-funded, Research Software Engineer; * Embedding industrial and third-sector collaboration throughout the student experience; * Hosting seeded research clusters: vibrant, cross-cohort, cross-sector retreats to explore and develop early-stage challenges emerging from the shared interests of STOR-i and its partners; * Developing an ambitious doctoral exchange programme with highly regarded international university partners, comprising student exchanges, co-supervision and shared training activities. Our partners play an integral role in the Centre's plans, with 80% of doctoral projects adopting a CASE-like approach, receiving co-funding and co-supervision from industrial partners. All other students will engage in industrial research internships. Additionally, partners will lead problem-solving events, data immersion experiences, and contribute to Continuing Professional Development (CPD) activities such as leadership talks, fireside chats, and advanced programming training. The partnership is deeply committed to ensuring the broader impact of STOR-i as a national resource. To this end, the Centre will establish a suite of funded activities open to all UK STOR doctoral students. These include an annual STOR summer school with an emphasis on leadership skills, advanced programming, and a data dive focused on charitable endeavours. Additionally, students will have access to masterclasses and research visits. STOR-i will deliver a wide range of benefits and scientific outcomes to the end-user community, underpinned by three fundamental pillars: 1. People: Our CDT will inject 70 highly talented, diverse PhD graduates into the field, armed with the technical, interpersonal, and leadership skills essential for flourishing careers in STOR across a range of sectors. These graduates will serve as catalysts for innovation, driving cutting-edge research, and enhancing the UK's economic competitiveness. 2. Knowledge: The CDT will generate a wealth of cutting-edge research, disseminated in top STOR journals, and presented at major international conferences. This research will tackle substantial real-world challenges, yielding fresh insights and breakthroughs in STOR. 3. Impact: Our CDT will make a tangible difference in society and the economy by producing (i) case studies and (ii) a repository of documented and reproducible software, available to the public. This will facilitate widespread adoption of our research, leading to meaningful societal and economic impact.

By 2050 it is estimated that the global population will exceed 9 billion. This is expected to result in a 100% increase in demand for food. The world needs more high-quality protein, produced in a responsible manner. This challenge is addressed by UN Sustainable Development Goals SDG2 (Zero hunger) and SDG12 (Responsible Consumption and Production). Expansion of marine fish aquaculture has been highlighted as a key route to increase food production. It is also an important area for the blue economy with high potential for new jobs and revenue. In the UK, marine aquaculture is worth over £2 billion to the economy, supports 2300 jobs and has ambitions to double production by 2030. But climate change is a threat as fish production is highly sensitive to the environment. Climate change assessments are often only available for large areas, e.g. global or regional, and do not capture the local conditions that influence fish production. They focus on long-term decadal averages which miss the daily environmental variability and multiple stressors that fish experience. Impacts on growth, health and welfare of the farmed fish are determined by these environment-biological complexities at farm level, and are also influenced by production strategies and industry decisions which may be based on social or economic factors. Robust, industry-relevant, climate impact assessment must include the complexities, relationships and trade-offs between different natural processes and human interventions. Thus, a more comprehensive approach which uses systems thinking to capture the interlinking interdisciplinary components is urgently needed. Precision aquaculture, where vast amounts of data are collected and analysed, offers a framework to provide the detail required to understand the complex farm system, evaluate how the environment is changing and assess implications for future production. In this FLF, I will deliver a rigorous scientific framework for assessing impact of climate change on marine aquaculture using systems thinking and precision-based information. I will create an approach which integrates detailed knowledge of what is happening in the complex farm system now, with future projections of climate change and potential stakeholder response. This will involve collecting high resolution data, analysing complex datasets, developing farm-level models, simulating future climate scenarios, and determining the adaptive capacity of the sector. I will work closely with my network of key industry partners, research organisations, regulators and policy makers to maximise translation and transfer of knowledge and approaches to industry and associated stakeholders. Atlantic salmon (Salmo salar) aquaculture in the Northeast Atlantic (Scotland and Norway) is used as a case study. Salmon leads marine fish production, with over 2 million tonnes produced each year, the equivalent of 17.5 billion meals. Norway and Scotland are responsible for 60% of production. The latitudinal range of farms extends across the thermal tolerance of the salmon, from temperate conditions in Scotland and south Norway, to arctic conditions in the north of Norway. This allows assessment of the spatio-temporal heterogeneity of climate change and a thorough analysis of how impact may vary between locations and different responses required. Beyond aquaculture, the positioning of marine fish farms offers an exceptional opportunity to gain deeper insight into the rate, magnitude and variability of climate change in coastal areas. This FLF will deliver vital new knowledge, data and approaches to understand how the environment is changing. This research is highly interdisciplinary, covering aspects of climate, environmental, biological and social science. The innovative techniques and transformative approaches will allow aquaculture to respond to the climate emergency, enhance blue economy opportunities and maximise its contribution to global food security.