Virtual laboratory combining atmospheric models and measurements elected Centre of Excellence

The new Centre of Excellence led by is called Virtual laboratory for molecule-level reactions and phase changes.

The research measures and models atmospheric molecules that can condense into particles. that gases from plants, for example, can form fine particles, which in turn condense the droplets in clouds.

AI makes for novel modelling of molecule measurements

The research at the virtual laboratory uses both methods from physics and chemistry, as well as machine learning competence.

– The main idea is to build a compilation of virtual instruments and models. With the help of machine learning and artificial intelligence, we can combine the measurements from different instruments and emulate the function of the models – everything that happens before we have a measurement and understand what it means, Vehkamäki says.

By comparison we can find out which measurements or calculations need to be made in more detail. Foresight is important, since both measurements and computer calculations at the molecular level take time and money, and they shouldn't be undertaken unless we are sure they will be useful.

– Some computer runs have taken up to six years. The instruments are also expensive, so we must use them appropriately. Our goal is to measure and model more efficiently, says Vehkamäki.

The project includes developers of AI methods, such as Associate Professor and researcher in machine-learning material physics, Associate Professor Patrick Rincke from Aalto University.

PhD students and Post-Doc researchers will also be employed in the project.

– Each will have two supervisors with different competence profiles. This is how to educate multi-disciplinary researchers from the start, says Vehkamäki.

Expertise is born from understanding each other and different worlds

This is still a pilot for a new kind of research method. Such new ideas require years of development because there are no ready solutions; they have to be developed from scratch.

– It is better to develop our research methods ourselves, because we cannot expect others to develop AI that can be applied to our research problems, says Vehkamäki.

The potential for combining the measurements is seldom utilized in the research, though this could help us discover new methods for our work.

– A research method not currently in use might give us more exact results, but we cannot know that for sure until we can compare findings in a controlled manner, says Vehkamäki.

She wants to remind us that the exploration of frontline research directions can never be fully controlled, but rather, new opportunities appear through trial and error.

– As we grow together, we discover new and innovative solutions. The funding from the Academy enables us to test new ideas and develop together in the long term, says Vehkamäki.

In addition to Vehkamäki, Arkke Eskola, Juha Kangasluoma, Theo Kurtén, Kai Puolamäki and Mikko Sipilä are also members in the CoE from the University of Helsinki. .