KEYWORDS: chemistry, computer vision, image processing, manufacturing, productivity, process monitoring. Chemical and biochemical manufacturing are dominated by colour changes, both subtle and stark. Such phenomena are often reported by-eye but not routinely quantified, especially over time. This renewal of a research and leadership programme aims to empower any chemist with any camera to capture any visible trend from any high-value chemical process, all without having to disturb the process under study. Most industrial chemists are accustomed to extracting chemical monitoring information using invasive, probe-based technologies. These technologies are robust and trusted. However, no current technologies are seamlessly applicable to monitoring chemical processes in real-time on BOTH the high throughput lab scale (the 'teacup') AND process/plant scales (the 'swimming pool'). Instead, current process analytical technologies are oftentimes tied to one specific hardware platform, and each example of such probe-based hardware can only monitor one process at a time. Ultimately, this can produce bottlenecks in analysis, slowing chemical product development and deployment. To address this productivity and chemical data throughput challenge, there is a real drive from R&D budget holders to invest in digital-ready analytical technologies. Computer Vision is the science of digitally quantifying real-world colours and objects using cameras. With cameras and computer vision, and further development through this fellowship renewal, the hardware and software needed for more time-, cost-, and safety-effective monitoring of high-value chemical processes can be realised in an accessible and globally adoptable manner. The global investment for digitalisation of process analytical technology (PAT) in the chemical industry is expected to reach $31 billion by 2028, representing an annual growth rate of approximately 6% from the present $23.5 billion market (sources: Made Smarter Review, 2017. Frost & Sullivan, 2017, and 2022). Underpinning this trend, R&D managers across chemical manufacturing are driving the streamlined adoption of new digital-ready chemical technology, to improve productivity, process safety, and ability to exploit the adjacent evolution of artificial intelligence.

This project aims to create a new artificially intelligent continuous flow platform for the development of multistep chemical and biocatalysed reactions. Pharmaceuticals are complex molecules which require multiple transformations to synthesise from readily available starting materials. Traditionally they are produced via batch manufacturing, where after each step intermediates are stored in containers or shipped to other facilities around the world to complete the manufacturing process. This adds a significant amount of processing time, contributes to a large carbon footprint, and is at significant risk of supply chain disruptions. In contrast, continuous manufacturing addresses each of these challenges by enabling end-to-end production within the same facility. Catalysts are substances which are added to reactions which influence the rate and/or outcome of the reaction without been consumed. A well-designed catalyst will minimise the generation of waste by being highly selective, recyclable, and only required in very small quantities, often replacing the use of larger amounts of toxic reagents. Hence, it is economically and environmentally desirable to include multiple catalysed steps in a manufacturing process. Alone, the benefits of catalysis and continuous flow are becoming increasingly relevant due to the drive for decarbonisation, but in combination, they have the potential to truly transform the next generation of sustainable manufacturing. However, combining different types of catalysis into continuous flow processes remains highly challenging, due to poor compatibility between catalysts and the large number of variables that need to be optimised. In this project we will develop a fully autonomous and artificially intelligent multistep continuous flow platform, which is capable of simultaneously optimising interconnected catalytic reactions. New multipoint analysis and automated reconfiguration capabilities will enable the creation of individual feedback loops for each reaction, which will be driven by machine learning algorithms suitable for multiobjective and mixed variable systems. We will then demonstrate this approach for the optimisation of industrially relevant chemoenzymatic cascades in sustainable and mutually compatible reaction media (e.g., deep eutectic solvents), thus combining the versatile reactivity of chemocatalysis with the high selectivity of biocatalysis.

Our society is highly dependent on catalytic science which is central to major global challenges such as efficient conversion of energy, mitigation of greenhouse gases, destroying pollutants in the atmosphere and in water, and processing biomass which all rely intrinsically on catalysis. In addition, catalysis is a key technology for the chemical industry; it is estimated that catalytic science contributes to 90% of chemical manufacturing processes. Chemistry-using industries are is a major component of the UK's manufacturing output and vital part of the overall UK economy, generating in excess of £50 billion per annum. The ONS Annual Business Survey (2012) estimated chemical and pharma manufacturing to be worth £19 billion p.a. and predicted that by 2030, the UK chemical industry will have enabled the chemistry-using industries to increase their Gross Value Added contribution to the UK economy by 50%, from £195 billion to £300 billion. Understanding how catalyst work is notoriously difficult because of the low concentrations and transient nature of catalytically active species. In this project will develop new equipment based on state-of-the-art flow NMR methods that will enable the rapid development of new catalysts for academic research and industrial processes. Crucially the equipment we propose will allow high sensitivity and real-time monitoring of catalytic reactions under a wide range of realistic reaction conditions (e.g., concentrations, temperatures and pressures). This will provide a unique facility to study the scope, productivity, selectivity and deactivation of catalysts, which in turn will provide insight into mechanisms and allow us to develop new catalytic systems. The equipment will be utilized by academic and industrial scientists and engineers at the University of Bath and throughout the UK to understand and develop catalysts for a wide range of processes of academic and industrial relevance. Areas that will benefit from the equipment will include; catalysts for renewable polymers, catalysts for utilisation and valorisation of biomass, catalysts for sustainable energy, and catalysts for sustainable synthesis of pharmaceuticals and fine chemicals. The progress that will be enabled by the equipment will be exploited, particularly within the pharma and fine chemicals sectors, through collaboration with a wide variety of UK catalyst companies and chemical producers.

Chemistry is a key underpinning science for solving many global problems. The ability to make any molecule or material, in any quantity needed in a prescribed timescale, and in a sustainable way, is important for the discovery and supply of new medicines to cure diseases, agrochemicals for better crop yields/protection, as well as new electronic and smart materials to improve our daily lives. Traditionally, synthetic chemistry is performed manually in conventional glassware. This approach is becoming increasingly inadequate to keep pace with the demand for greater accuracy and reproducibility of reactions, needed to support further discovery and development, including scaling up processes for manufacturing. The future of synthetic chemistry will require the wider adoption of automated (or autonomous) reaction platforms to perform reactions, with full capture of reaction conditions and outcomes. The data generated will be valuable for the development of better reactions and better predictive tools that will facilitate faster translation to industrial applications. The chemical and pharmaceutical industry is a significant provider of jobs and creator of wealth for the UK. Data from the Chemical Industries Association (CIA) shows that the chemical industry has a total turnover of £40B, adding £14.4B of value to the UK economy every year, employs 140,000 people directly, and supports a further 0.5M jobs. The sector is highly innovation-intensive: much of its annual spend of £4B on investment in capital and R&D is based on synthetic chemistry with many SME's and CRO's establishing novel markets in Science Parks across the UK regions, particularly in the South East and North West. The demand for graduate recruits by the Chemicals and Pharmaceutical industries for the period 2015-2025 is projected to be between 50,000-77,000, driven by an aging workforce creating significant volumes of replacement jobs, augmented by the need to address skills shortages in key enabling technologies, particularly automation and data skills. This CDT will provide a new generation of molecular scientists that are conversant with the practical skills, associated data science and digital technology to acquire, analyse and utilise large data sets in their daily work. This will be achieved by incorporating cross-disciplinary skills from engineering, as well as computing, statistics, and informatics into chemistry graduate programs, which are largely lacking from existing doctoral training in synthetic chemistry. Capitalising upon significant strategic infrastructural and capital investment on cutting edge technology at Imperial College London made in recent years, this CDT also attracts very significant inputs from industrial partners, as well as Centres of Excellence in the US and Europe, to deliver a unique multi-faceted training programme to improve the skills, employability and productivity of the graduates for future academic and industrial roles.

Advanced economies are now confronted with a serious challenge that requires us to approach problem solving in a completely different way. As our global population continues to rise we must all consider several quite taxing philosophical questions, most pressingly we must address our addiction to economic growth, our expectation for longer, healthier lives and our insatiable need to collect more stuff! Societies demand for performance molecules, ranging from pharmaceuticals to fragrances or adhesives to lubricants, is growing year-on-year and the advent of competition in a globalised market place is generally forcing the market price downward, cutting margins and reducing the ability for some industry sectors to innovate. Atoms to Products (A2P) is an exciting opportunity to forge a new philosophy that could underpin the next phase of sustainable growth for the chemicals manufacturing industry in the UK and further afield. An overarching driving force in the development of A2P was the desire to apply the knowledge and learning of Green and Sustainable Chemistry to the creative phases embedded in the discovery and development of performance molecules that deliver function in applications as diverse as pharmaceuticals, agrochemicals and food. We propose a multi-disciplinary CDT in sustainable chemistry which aims to achieve a sustainable pipeline of performance molecules from design-to-delivery. A2P will create an Integrated Approach to Sustainable Chemistry, promoting a culture of waste minimisation, emphasising the development of a circular economy in terms of materials and matter replacing current modes of consumption and resource use. A2P represents a multidisciplinary group of 40 academic advisors spanning 7 academic disciplines, working together with a growing family of industrial partners spanning well-known multinationals including Unilever, GSK, AstraZeneca and Croda, and niche SMEs, including Promethean Particles, Sygnature and European Thermodynamics. Interestingly all partners have expressed a common desire to develop Smarter products using Better chemistry to enable Faster processing and Shorter manufacturing routes. A2P will drive innovation by: 1 fostering a multidisciplinary, cohort based approach to problem solving; 2 focussing on challenge areas identified by our A2P partners such that sub-groups of our cohort can become immersed in research at the "coal-face"; 3 embedding aspects of data-driven decision making in the day-to-day design and execution of high quality research either on paper or indeed in the lab; 4 nurturing a vibrant and supportive community that allows PhD candidates to think 'outside of the box' in a relatively risk- free way; 5 empowering the development of 'next generation' synthetic methods to drive efficiency, selectivity and productivity, underpinned my molecular modelling and the use of machine learning to extract additional value from experimental data; 6 developing sustainable processes that deliver efficiency and transition to scale-up from g to Kg, under-utilised approaches, including electrochemistry, will be investigated increase atom efficiency and reduce reliance on precious metals; 7 enabling efficient scale-up of new processes using flow-chemistry and 3-D printing technology to "print" the most efficient reactor system, thereby maximising throughput whilst efficiently managing mass transport and thermal factors; 8 applying robust reaction/process evaluation metrics such that comparative advantages can be quantified, providing evidence for real process decision making. Integration of outcomes from all A2P PhD projects, in combination with the expertise of all A2P partners, will deliver a major contribution to the health of the UK chemicals manufacturing industry. A2P will provide mentorship and training to the next generation of leaders securing innovation and future growth for this critical manufacturing sector.