Congratulations to Gian-Marco Rignanese on receiving a Synergy Grant from the European Research Council (ERC)

Congratulations to Gian-Marco Rignanese on receiving a Synergy Grant from the European Research Council (ERC).  He was selected to develop the GEMPROMISE project—Generative machine learning for combined process control and materials design—with two other Principal Investigators from the Swiss Federal Institute of Technology in Lausanne (EPFL) and the French National Center for Scientific Research (CNRS).  Thanks to ERC Synergy grants, in total, 66 research teams, bringing together 239 scientists, will receive a total of €684 million in European Research Council Synergy Grants to tackle some of the most challenging scientific questions across a broad range of fields.

Discover more about GEMPROMISE project :

Today, generative artificial intelligence enables the design of entirely new atomic or molecular structures that meet specified objectives while obeying physical and chemical constraints. Yet current models only generate the composition or arrangement of atoms; they do not provide details on how to synthesize the material—temperature, pressure, incubation time, and so forth. The newly funded GEMPROMISE project—backed by an ERC Synergy grant—is set to bridge this gap. The consortium brings together three complementary experts: Gian Marco Rignanese, Cyril Aymonier (a CNRS chemist based in Bordeaux), and Pierre Vandergheynst, a generative‑AI specialist from EPFL Lausanne who earned his PhD at UCLouvain.

Together they aim to move beyond simple prediction. Their model will also suggest the optimal synthesis parameters for producing each new material. GEMPROMISE will establish a bottom‑up, sustainable, and scalable method for producing synthetic layered silicates with controllable band gaps. Once established, this approach can be extended to other processes, structures, properties, and hence applications. In the long run, this approach could transform materials science—from a trial‑and‑error process to one that is predictive, rapid, and sustainable. The expected outcomes include higher‑performance, environmentally friendly technologies in key sectors such as energy and electronics.