Project R-15952

GIMLi: Green artificial-Intelligence based Modelling of Lignin for sustainable bio-based chemistry of the future (Research)

In a world facing the effects of climate change at an ever increasing pace, the need for circular and sustainable industry has become indisputable. For polymer chemistry, this means there is a growing need for renewable and sustainable aromatic building blocks. Lignin, the second most abundant biopolymer, has the potential to meet this need, though its integration in materials design remains time consuming due to the diversity in lignin structure and properties. Through the study of an atomic scale digital twin, much needed understanding of the properties of lignin polymers will be provided, to accelerate industrial deployment. Quantum chemical (QC) modelling provides the most accurate results, be it at a tremendous computational cost and thus ecological impact. Instead an AI model is developed, trained on QC data to provide the highest quality, allowing for low cost modelling of lignin properties. The model is applied to study two prominent facets in lignin industry: solvation and reaction rates. Calculated temperature dependent reaction rates provide insight into depolymerisation and functionalisation, both essential steps for lignin valorisation. Solvation on the other hand, plays an important role both in the purification and depolymerisation processes. The resulting AI model allows future polymer chemists to design more rational and focussed strategies for both lignin depolymerisation as well as synthesis strategies to create sustainable products.

01 November 2025 - 31 October 2029