Chemical research is a field of work that demands change and can make better use of digitalisation. Data and AI offer opportunities in the sector, argues Peter Lambooij. As a lecturer and researcher, Lambooij is involved in the Growth Fund project 'The Revolution of Self-Directed Molecular Systems' together with a team of Fontys colleagues. In this project, the parties are working on a robotised laboratory for chemistry.
The Netherlands is a leader in chemical research. The sector is developing rapidly, with all kinds of processes being automated, among other things. At the same time, many experiments and analyses are still manual work.
'Many repetitive operations'
"Chemical research often consists of many repetitive actions, for example to map characteristics of a substance. You already see automation in this field in the form of specific chemistry 'factories'," says Teade Punter, lectorHigh Tech Embedded Software (HTES) and lecturer in ICT & Technology at Fontys Hogeschool ICT.
Punter continues: "A recent trend is the use of robots, which take over chemistry tasks. There is also AI that can determine the strategy of experiments. The combination of robots and AI make experiments much more flexible." Using hands-on research, the researchers aim to accelerate these trends.
Robotlab
Lambooij and Punter are working with other researchers and about four academic institutions and companies on a so-called robot lab. Automation using robotics and making the best use of data are central to this. Lambooij: "With fixed and mobile robots, we want to automate the lab extensively. With our partners, we think the real opportunities lie in the use of big chemistry data. Now, data on every conceivable substance remains partly untapped. Leveraging big data can help create a 'recommender system' for new chemical experiments."
AI can help in several areas. One example is diagramming, which researchers use to explain the arrangement of substances under different conditions. Think of variations on the classic classification of solid, liquid and gas. Manually mapping such a diagram is a very time-consuming process. An AI speeds up the process.
Getting results faster
In addition, based on the results of initial tests, AI can predict where the dividing lines are. It can then test specifically on these. This makes the process significantly more efficient and provides much faster results. A more advanced capability that the researchers foresee is having AI draw up new hypotheses for new experiments based on a large number of phase diagrams. Lambooij explains: "Think ChemGPT ('the cousin' of ChatGPT) to whom you ask how you should do experiments to develop environmentally friendly paint. But we are nowhere near that point. That's why this Growth Fund project runs for seven years."
The researchers initially focus on the domain and working methods of chemists, which they map in detail. This makes it possible to develop applications for the robot lab. Initial results are very promising. Lambooij says: "We are starting to speak the same language, and the example of AI as a predictor of diagrams creates confidence". The Fonty team also thinks it is important to create a learning platform in which teachers, companies and students can work together. Punter: "We also develop challenges for students, which are part of the larger project, but have the right scope for our students."
Duration of seven years
The project The Revolution of Self-Directed Molecular Systems is not new and has been running for some time. The project is supported in part by the National Growth Fund, which allocated 97.2 million euros last year. The project has a duration of seven years.
Author: Wouter Hoeffnagel
