Module manager: Prof. Richard Bourne
Email: r.a.bourne@leeds.ac.uk
Taught: Semester 2 (Jan to Jun) View Timetable
Year running 2025/26
A background in Chemistry equivalent to year 2 undergraduate level or selection of Foundations of Chemistry optional module in Semester 1
This module is not approved as an Elective
In a world facing environmental challenges and the need for resource efficiency, process optimisation has never been more critical. Autonomous systems are revolutionising industries by enabling smarter, more sustainable decision-making through advanced data-driven approaches. In this course, students will explore key optimisation strategies, including Design of Experiments (DoE) and machine learning, to enhance the performance of complex processes. Through a combination of theoretical insights and practical applications, students will develop the digital expertise to critically evaluate and analyse cutting-edge technologies. Workshops will provide opportunities to engage with real-world examples, equipping students to apply these skills effectively. By mastering these methods, students will be prepared to address pressing global challenges and lead in the development of innovative, sustainable solutions.
To enable students to perform data-driven optimisations of reactions and mapping of chemical space by leveraging advanced methodologies, such as machine learning, and to critically evaluate the viability and potential impact of emerging technologies.
On successful completion of the module students will have demonstrated the following learning outcomes relevant to the subject:
1) Understand the limitations of current practices in process optimisation and recognise areas where autonomous and data-driven approaches offer improvements.
2) Have a broad knowledge and critical awareness of developments at the forefront of digital chemistry, with a focus on cheminformatics, autonomous systems and emerging optimisation technologies.
3) Be able to critically evaluate technical literature, cheminformatics techniques, data-driven methodologies, and other information sources relevant to process optimisation and advanced technologies.
4) Recognise the limitations of standard commercial software for process optimisation and identify requirements for advanced techniques or the integration of specialist expertise.
5) Understand how to combine and adapt different aspects of systems thinking to address complex and novel processes, particularly through autonomous and data-driven optimisation.
6) Have a clear understanding of the limits of current technologies and the potential impact of new and emerging tools, particularly those driven by advances in data science and artificial intelligence.
7) Demonstrate the ability to benchmark the performance of different optimisation approaches, critically evaluating their effectiveness and suitability for solving complex chemistry problems in process optimisation.
8) Develop a critical awareness of the wider digital chemistry discipline, including the ethical and environmental implications of deploying autonomous and data-driven optimisation approaches.
9) Understand the challenges and opportunities presented by emerging technologies and demonstrate the ability to assess their feasibility and impact on complex chemical systems.
Skills Learning Outcomes
On successful completion of the module students will have demonstrated the following skills :
A) Develop proficiency in using coding environments to implement, benchmark, and compare the performance of various optimisation algorithms and cheminformatic techniques across a range of chemistry problems.
B) Identify and critically evaluate the viability and potential impact of emerging technologies in lab automation, including their ethical, environmental, and technical implications.
C) Effectively communicate advances in process optimisation and automation to non-expert audiences, using clear, concise, and accessible language while maintaining scientific accuracy.
The module will cover three aspects of current ML-based technology developments in chemistry:
(1) Process optimisation: design of experiments, response surface modelling (using software packages), ML modelling, algorithms for optimisation (e.g., Bayesian) and integration with autonomous experimental platforms.
(2) Cheminformatic models for prediction: data preparation and feature engineering, model selection and validation techniques, interpretability and generalisation.
(3) Research-led advances: gain an overall understanding of state-of-the-art developments in ML for chemistry reported within academic literature.
Methods of assessment
The assessment details for this module will be provided at the start of the academic year
| Delivery type | Number | Length hours | Student hours |
|---|---|---|---|
| Computer Class | 6 | 2 | 12 |
| Lecture | 10 | 1 | 10 |
| Seminar | 6 | 2 | 12 |
| Private study hours | 116 | ||
| Total Contact hours | 34 | ||
| Total hours (100hr per 10 credits) | 150 | ||
Discussion during synchronous sessions, via online resources, open office hours.
Guidance during group work occur within synchronous group sessions.
There is no reading list for this module
Last updated: 30/04/2025
Errors, omissions, failed links etc should be notified to the Catalogue Team