AI aims to develop custom-made materials

ERC Synergy Grant for the ODDITY Collaborative Project: Together with researchers from Oxford and Jülich, Prof. Pascal Friederich aims to use artificial intelligence to accelerate the search for molecules for functional materials

The European Research Council (ERC) is funding the ODDITY project—a research initiative led by Professor Pascal Friederich of the Karlsruhe Institute of Technology (KIT) in collaboration with partners at the Forschungszentrum Jülich and the University of Oxford. The researchers are combining artificial intelligence (AI), molecular chemistry, and autonomous laboratories to develop specific molecular structures as a target. This is expected to significantly accelerate the search for new materials for applications such as photovoltaics. The ERC is providing 9.7 million euros in funding for the project over six years.

Technological progress depends largely on the materials available. The development of photovoltaics, light sensors, and electronic components requires materials that meet several requirements simultaneously: among other things, they must possess certain optical and electrical properties and be both stable and easy to process. One example is the ultra-thin layers in solar cells that absorb light and transport electrical charges.

A Modular System for Molecules

A material’s capabilities are determined primarily by its molecular structure. The ODDITY (On-Demand Discovery by Molecular Ingenuity) project takes a systematic approach to identifying, from among more than a trillion possible molecular structures, those that specifically meet certain requirements. The European Research Council is now funding this project with a Synergy Grant. “The ERC Synergy Grant recognizes a research approach that has the potential to fundamentally transform the development of new materials. The ODDITY project brings together scientific excellence in the divisions of artificial intelligence, chemistry, and materials research and impressively demonstrates the strength of international collaboration,” says Professor Oliver Kraft, Vice President for Research, Teaching, and Academic Affairs at KIT.

“Using AI, we are combining accelerated chemical synthesis with reversible reactions,” says Professor Pascal Friederich of KIT’s Institute of Nanotechnology (INT). Like in a modular system, molecules are to be assembled from chemical building blocks within a few seconds or minutes, then disassembled and recombined. Their properties are also to be investigated at this pace. “With high experimental throughput, we aim to shorten the search for suitable materials from years to weeks,” says Friederich.

AI Controls Experiments

To this end, Friederich and his research group are developing AI models designed to identify suitable molecular structures based on desired material properties—structures that can actually be synthesized chemically. “The plan is to integrate data from computer simulations, laboratory measurements, and component testing. Our target is to use machine learning to determine which building blocks to select and how to assemble them to obtain a molecule with specific properties,” explains the researcher. Generative AI is also intended to suggest new chemical building blocks, thereby expanding the range of possible materials. “The AI models help us find promising molecules without having to examine every possible combination individually. They also help us decide which experiment makes sense to conduct next. The results are then fed back into the models.”

Close Collaboration with Oxford and Jülich

Friederich secured the ERC Synergy Grant at KIT in collaboration with teams in Oxford and Jülich. Jülich collaborated closely with Friedrich-Alexander University Erlangen-Nuremberg at the Helmholtz Institute Erlangen-Nuremberg for Renewable Energies (HI ERN).

The researchers contribute their respective expertise in molecular chemistry and automated materials analysis. The team led by Professor Iain McCulloch at the University of Oxford is developing the chemical processes used to assemble and modify molecules—including reversible reactions that make it possible to recover and reuse building blocks. The team led by Professor Christoph Brabec at Forschungszentrum Jülich is contributing autonomous laboratory platforms. These are used to produce and characterize thin films, as well as to test components using an ultra-high-throughput process.

ERC Synergy Grant

The European Research Council (ERC) supports promising research teams through Synergy Grants. The funded projects must be feasible only through collaboration among the participating scientists and are intended to lead to discoveries at the interfaces between established disciplines as well as to significant advances at the frontiers of knowledge. The ERC is allocating a total of 500 million euros for the 2026 call for proposals. A total of 957 proposals were submitted, of which 48 will receive funding.