Discovering intrinsic catalytic reaction mechanisms: using machine learning to 'crack' rate expressions

Developing high-efficiency and sustainable catalysts is one of the research priorities that lies at the interface between chemistry and chemical engineering. For most industrial reactions involving multiple phases, rate expressions such as the Langmuir-Hinshelwood equation have been the centre of long-standing kinetic models to quantitatively characterise heterogeneous catalysis. Although the apparent kinetics of heterogeneous catalysis can be estimated using these expressions for industrial applications, the intrinsic reaction kinetics are still not well understood. This not only limits the fundamental understanding of the catalytic reaction phenomena, but also mitigates the possibility of a tailored-made design of new catalysts. By merging data analytics and kinetic understanding, this project will discover the intrinsic catalytic reaction mechanism by exploiting recent advances from the machine learning community to analyse and decompose the empirical parameters and structures of rate expressions. Furthermore, aided by these new understandings, this project will design a methodology to develop tailored-made catalysts with desired properties for specific applications. It will be important to focus on well-established simple reactions, where many data already exist in the literature to give a good head start. Simple reactions will allow more emphasis on intrinsic catalyst properties, particularly when exploring multifunctional catalysts. Based on a recent Perspectives article in Green Chemistry [1], amide reduction appears to be a suitable candidate to benefit from the above approach. To design a highly active heterogeneous catalyst for the selective hydrogenation of multifunctional amides is a considerable challenge. Successful PhD candidates will have the opportunity to learn both machine learning and mathematical programming techniques as well as a range of highly sophisticated experimental skills.
[1] Green Chem, 2018, 20, 5082

Academic impact:
Recent advances in data science and digital technology have a disruptive effect on the way synthetic chemistry is practiced. Competence in computing and data analysis has become increasingly important in preparing chemistry students for careers in industry and academic research.

The CDT cohort will receive interdisciplinary training in an excellent research environment, supported by state-of-the-art bespoke facilities, in areas that are currently under-represented in UK Chemistry graduate programmes. The CDT assembles a team of 74 Academics across several disciplines (Chemistry, Chemical Engineering, Bioengineering, Maths and Computing, and pharmaceutical manufacturing sciences), further supported by 16 industrial stakeholders, to deliver the interdisciplinary training necessary to transform synthetic chemistry into a data-centric science, including: the latest developments in lab automation, the use of new reaction platforms, greater incorporation of in-situ analytics to build an understanding of the fundamental reaction pathways, as well as scaling-up for manufacturing.

All of the research data generated by the CDT will be captured (by the use of a common Electronic Lab Notebook) and made openly accessible after an embargo period. Over time, this will provide a valuable resource for the future development of synthetic chemistry.

Industrial and Economic Impact:
Synthetic chemistry is a critical scientific discipline that underpins the UK's manufacturing industry. The Chemicals and Pharmaceutical industries are projected to generate a demand for up to 77,000 graduate recruits between 2015-2025. As the manufacturing industry becomes more digitised (Industry 4.0), training needs to evolve to deliver a new generation of highly-skilled workers to protect the manufacturing sector in the UK. By expanding the traditional skill sets of a synthetic chemist, we will produce highly-qualified personnel who are more resilient to future challenges. This CDT will produce synthetic chemists with skills in automation and data-management skills that are highly prized by employers, which will maintain the UK's world-leading expertise and competitiveness and encourage inward investment.

This CDT will improve the job-readiness of our graduate students, by embedding industrial partners in our training programme, including the delivery of training material, lecture courses, case studies, and offers of industrial placements. Students will be able to exercise their broadened fundamental knowledge to a wide range of applied and industrial problems and enhance their job prospects.

Societal:
The World's population was estimated to be 7.4 billion in August 2016; the UN estimated that it will further increase to 11.2 billion in the year 2100. This population growth will inevitably place pressure on the world's finite natural resources. Novel molecules with improved effectiveness and safety will supersede current pharmaceuticals, agrochemicals, and fine chemicals used in the fabrication of new materials.

Recent news highlights the need for certain materials (such as plastics) to be manufactured and recycled in a sustainable manner, and yet their commercial viability of next-generation manufacturing processes will depend on their cost-effectiveness and the speed which they can be developed. The CDT graduates will act as ambassadors of the chemical science, engaging directly with the Learned Societies, local council, general public (including educational activities), as well as politicians and policymakers, to champion the importance of the chemical science in solving global challenges.