Bereiche | Tage | Auswahl | Suche | Aktualisierungen | Downloads | Hilfe

CPP: Fachverband Chemische Physik und Polymerphysik

CPP 38: Biopolymers, Biomaterials and Bioinspired Functional Materials I (joint session CPP/BP)

CPP 38.2: Vortrag

Mittwoch, 11. März 2026, 15:30–15:45, ZEU/0255

Inferring Structure-Property Relationships with Artificial Intelligence: A Lignin Case Study — •Matthias Stosiek and Patrick Rinke — Department of Physics, Atomistic Modelling Center, Munich Data Science Institute, Technical University of Munich

The potential of lignin as an abundant, underutilized biopolymer is increasingly being realized. A key challenge for the targeted production of lignins remains the poorly understood relation between lignin properties and its complex structure. Artificial intelligence (AI) methods could reveal such structure-function relationships but remain elusive in biomaterials research.

95 structurally diverse lignins are extracted from birch wood combining the Aqua Solv Omni (AqSO) biorefinery process and AI-guided data acquisition [1, 2]. Each lignin sample is characterized with 2D NMR spectroscopy and complemented with measurements of key lignin properties such as antioxidant activity.

To establish structure-function relationships, we correlate regions of the NMR spectra with corresponding property measurements. With a feature importance analysis, we identify structural relevant features for each property and provide a chemical interpretation. For instance, we find that more β-O-4 bonds lead to lower surface tension in water indicating a more linear lignin structure. Our structure-inference approach is designed to be general and applicable to a wide range of materials and characterization data.

[1] D. Diment et al., ChemSusChem, e202401711 (2024). [2] M. Alopaeus, M. Stosiek et al., Sci Data 12, 996 (2025).

Keywords: Lignin-Carbohydrate-Complexes; Nuclear Magnetic Resonance; Structure-Property Relationship; Machine Learning; Artificial Intelligence