This Network aims to bring together an international group of scholars from different disciplines (including architectural history, history, literature and music) with an interest in the cultures of Enlightenment, reform and radicalism to discuss the complex of ways in which the practice, theory and experience of architecture contributed to debates about modernity and urban experience in the decades around 1800. It will do so through lens of the life of Thomas Rickman (1776-1841), which provides a springboard for discussing many of the issues involved. His internationally influential work, 'An Attempt to Discriminate the Styles of Architecture' (Liverpool, 1817) was the first architectural 'best seller', through which the educated public were taught how to identify and discuss architectural styles. Through studying and writing about architecture, Rickman transformed his identity from depressed bankrupt exile to successful professional architect. Rickman was closely associated with reformist circles, his architectural research was informed by methods of classification learned from the natural sciences and he was a pioneer of new methods of construction, but as a successful practitioner he worked for a wide range of clients, from wealthy industrialists, to Anglican parishes, municipal corporations and Cambridge colleges. His career - and the associated buildings and archive - provides a connecting thread across this project, a springing point for addressing broader research questions and engaging the general public through a touring exhibition, website and associated workshops and walking tours devoted to his life and work. Many of today's debates about the contribution of buildings, both new and old, to societal wellbeing have their counterparts in eighteenth- and early nineteenth-century discourse and juxtaposing the two will contribute a historical dimension to discussion of modern planning and heritage policies. Through networking symposia in Liverpool and London, and research workshops with site visits to buildings in Liverpool, Bristol and Birmingham, the Network will address how, in addition to its existing role as the most prestigious public site of display, architecture became a site of social experiment, embodying decisive shifts in medical, penal and educational theory, to be tested through the impact of new building forms. These debates intertwined buildings and books in a virtual sphere but the public sphere also had a spatial dimension: the new libraries, news rooms and lecture theatres in which such debates were encountered and performed and the transformation of towns through public and private investment (actual and anticipated) through which modernity was imagined and experienced. These involved changing patterns of patronage, funding and building, contributing to the professionalisation of the architect and the emergence of general contracting. The Network aims to frame public discourse about architecture in relation to the transformation of the public sphere, both through changes in print culture and contemporary economic and social changes wrought by war, capitalisation, industrialisation and urbanisation. Through print and travel, this discourse had a global dimension and the Network will develop international connections in order to enable a globally comparative approach. Our objective is to build capacity for ongoing collaboration and future international comparative research.

The EPSRC Centre for Doctoral Training in Statistics and Machine Learning (StatML) will address the EPSRC research priority of the 'physical and mathematical sciences powerhouse' through an innovative cohort-based training program. StatML harnesses the combined strengths of Imperial and Oxford, two world-leading institutions in statistics and machine learning, in collaboration with a broad spectrum of industry partners, to nurture the next generation of leaders in this field. Our students will be at the forefront of advancing the core methodologies of data science and AI, crucial for unlocking the value inherent in data to benefit industry and society. They will be equipped with advanced research, technical, and practical skills, enabling them to make tangible real-world impacts. Our students will be ethical and responsible innovators, championing reproducible research and open science. Collaborating with students, charities and equality experts, StatML will also pioneer a comprehensive strategy to promote inclusivity, attract individuals from diverse backgrounds and eliminate biases. This will help diversify the UK's future statistics and machine learning workforce, essential for ensuring data science is used for public good. Data science and AI are now part of our everyday lives, transforming all sectors of the economy. To future-proof the UK's prosperity and security, it is essential to develop new methodology, specifically tailored to meet the big societal challenges of the future. The techniques underpinning such methods are founded in statistics and machine learning. Through close collaboration with a broad range of industry partners, our cohort-based training will support the UK in producing a critical mass of world-leading researchers with expertise in developing cutting-edge, impactful statistical and machine learning methodology and theory. It is well documented in government and learned society reports that the UK economy has an urgent need for these people. The significant level of industry support for our proposal also highlights the necessity of filling this gap in the UK data science ecosystem. StatML will learn from and build upon our previous successful experiences in cohort training of doctoral students (our existing StatML CDT funded in 2018, as well as other CDTs at Imperial and Oxford). Our students will continue to produce impactful, internationally leading research in statistics and machine learning (as evidenced by our students' impressive publication record and our world-leading research environment, as rated by the REF 2021 evaluation), while complementing this with a bespoke cohort-based Advanced Training program in Statistics and Machine Learning (StatML-AT). StatML-AT has been developed from our experience and in partnership with industry. It will be responsive to emerging technologies and equip our students with the practical skills required to transform how data is used. It will be delivered by our outstanding academics from both institutions alongside with industry leaders to ensure that students receive training in cutting edge technologies, along with the latest ideas in ethics, responsible innovation, sustainability and entrepreneurship. This will be complemented by industrial and academic placements to allow the students to develop their own international network and produce high-impact research. Together, StatML and its partners will train 90+ students over 5 cohorts. More than half of these will be funded from external sources, including 25+ by industry, representing excellent value for money. Our diverse cohorts will benefit from a unique and responsive training program combining academic excellence, industry engagement, and interdisciplinary culture. This will make StatML a vibrant research environment inspiring the next methodological advancements to transform the use of data and AI across industry and society.

We will work with young people to use digital technology to transform adolescent mental health and provide a safe, and supportive, digital environment to tackle the unmet need arising from mental health disorders in those aged 10-24 years old. We are facing a youth mental health crisis; in the UK, one in eight young people have a mental health disorder, and one in four young women aged 17-19 have significant depression or anxiety with half of those having self-harmed; non-suicidal self-harm has nearly tripled over the past 10 years, while suicide rates per 100,000 adolescents have almost doubled. However, less than a third of all young people with mental health disorders receive any treatment. Many mental health and wellbeing apps exist, but most have no evidence base and some could even be harmful. Meanwhile, few research-based digital interventions have been shown to have impact in the real world. The youth mental health crisis has coincided with huge changes in society with creation of the 'digital environment' where being online and using social media has become central to young people's lives. While social media can be a helpful place for accessing information, exchanging views and receiving support, it has also been linked with depression, suicide and self-harm. Yet not all young people are at risk of mental health problems with social media we don't yet understand why some young people are more vulnerable than others. The COVID-19 crisis has been associated with increased mental health problems and greater online activity in young people. While their need to access trusted support online is greater than ever, social media platforms are not designed to meet mental health needs of young people. Aims & objectives. We will work with young people in our Young Person Advisory Group to: 1. increase understanding of the relationship between digital risk, resilience and adolescent mental health. 2. develop and evaluate preventative and personalised digital interventions. We aim to: - identify risk and resilience factors related to troublesome online experiences and activities, to prevent or reduce the emergence of depression, anxiety, and self-harm in young people. - understand how individual differences affect digital engagement (e.g. with social media and games) and adolescent brain and psychosocial development. - build, adapt and pilot new a generation of personalised and adaptive digital interventions incorporating a mechanistic understanding of human support with a new digital platform for delivery and trials in adolescent mental health conditions. - develop and test a novel socially assistive robot to help regulate difficult emotions with a focus on adolescents who self-harm. - develop and test a new digital tool to help adolescents better manage impulsive and risky behaviour with a focus on reducing the risk of self-harm. Applications & benefits. This work will translate new knowledge into practical tools to support young people negotiate the digital world, develop resilience and protect their mental health. Our involvement of young people means that the outputs from the research will be suitable and meaningful. Young people will be actively involved shaping the research at all stages. Young people, their caregivers, teachers, clinicians and charities will benefit from a range of co-created apps and tools to manage youth mental health issues. Young people will benefit from research training offered as part of their involvement. Policy makers and academics will benefit from new understandings of risk and resilience in the digital world to support novel interventions and evidence-based policy. Our work will establish a new, ethical and responsible way of designing digital platforms and tools that supports young people's mental health. Our Mental Health & Digital Technology Policy Liaison Group and Partners Board will translate our research into a step-change in mental health outcomes.

Rivers emit ~2-3 Pg of carbon as the greenhouse gas carbon dioxide (CO2) to the atmosphere, each year. This is equivalent to 20% of annual anthropogenic CO2 emissions and an important component of the global carbon cycle. Methane (CH4) emissions from river networks are very poorly understood. CH4 is a potent greenhouse gas, 34 times stronger than CO2 over a 100-year timeframe. Rivers are estimated to emit ~27 Tg of CH4 each year, equivalent to 8% of anthropogenic CH4 emissions. However, these CH4 emissions vary greatly both spatially and over time. Rivers, acting as conduits for terrestrial greenhouse gases, can thus influence ongoing climate change. Landscape disturbance, either through human activity or climate change, can enhance river carbon emissions adding substantially to an already overloaded atmospheric carbon pool. This may represent a feedback to the global climate system as river carbon emissions can be enhanced by the impact of climate change on the terrestrial carbon cycle. Characterising the magnitude and source of river carbon emissions across globally representative ecosystems is therefore urgently needed for us to understand and predict current and future climate change. Carbon emissions from rivers are primarily derived from the landscapes they drain. But sources within these landscapes can vary depending on the ecosystem. Carbon sources can include recent atmospheric CO2 fixed into biomass via photosynthesis, carbon that has accumulated in organic soils over millennia such as in Arctic, temperate and tropical peatlands, and even ancient geological carbon derived from erosion and weathering. With such a diverse range of potential carbon sources across ecosystems, it is vital to establish a framework from which to determine whether the source of carbon observed in river networks matches what would be expected from normal landscape function, or if it represents signals of a disturbed carbon cycle. I.e. are older and slower carbon cycles becoming shorter and faster? Isotopes, especially radiocarbon (14C), are a powerful tool for identifying disturbed carbon cycles. Through a network of leading researchers, this project will bring together novel techniques and study sites to serve as a foundation for in-depth investigations into river carbon emissions around the globe. The project will utilise low-cost sensors for measuring the magnitude of river carbon emissions developed by the international Project Partners. These will be combined with in-depth isotopic investigations using novel techniques developed by the UK investigators. A network of existing study site and measurement infrastructure will be established covering a diverse range of ecosystems. The project will therefore provide a springboard from which to constrain the magnitude and source of river carbon emissions through direct observations at globally representative scales. Rivers can drain large landscape areas and as such their water chemistry represents an integrated signal of landscape carbon loss. This project will provide the techniques to tease apart these signals and determine if they represent natural or disturbed carbon cycling. The project will build a database of existing observations of these signals. In addition, we will use the interacting, complimentary techniques brought together in this project to carry out a scoping project to provide preliminary observations of the magnitude and source of carbon emissions from a subset of disturbed landscapes. CONFLUENCE will also include planning for an international meeting of researchers in relevant fields to grow the network of people, techniques and sites beyond the lifetime of this project. CONFLUENCE will be used as a launchpad for consortium funding to use this unprecedented infrastructure to make a step-change in observational capability of freshwater carbon emissions at spatial and temporal scales that individual research groups alone cannot achieve.

Over the past few months, we have laid the groundwork for the ReproHum project (summarised in the 'pre-project' column in the Work Plan document) with (i) a study of 20 years of human evaluation in NLG which reviewed and labelled 171 papers in detail, (ii) the development of a classification system for NLP evaluations, (iii) a proposal for a shared task for reproducibility of human evaluation in NLG, and (iv) a proposal for a workshop on human evaluation in NLP. We have built an international network of 20 research teams currently working on human evaluation who will actively contribute to this project (see Track Record section), making combined contributions in kind of over £80,000. This pre-project activity has created an advantageous starting position for the proposed work, and means we can 'hit the ground running' with the scientifically interesting core of the work. In this foundational project, our key goals are the development of a methodological framework for testing the reproducibility of human evaluations in NLP, and of a multi-lab paradigm for carrying out such tests in practice, carrying out the first study of this kind in NLP. We will (i) systematically diagnose the extent of the human evaluation reproducibility problem in NLP and survey related current work to address it (WP1); (ii) develop the theoretical and methodological underpinnings for reproducibility testing in NLP (WP2); (iii) test the suitability of the shared-task paradigm (uniformly popular across NLP fields) for reproducibility testing (WP3); (iv) create a design for multi-test reproducibility studies, and run the ReproHum study, an international large-scale multi-lab effort conducting 50+ individual, coordinated reproduction attempts on human evaluations in NLP from the past 10 years (WP4); and (v) nurture and build international consensus regarding how to address the reproducibility crisis, via technical meetings and growing our international network of researchers (WP5).