Materials Science

Machine Learning Optimization of Lignin Properties in Green Biorefineries



Novel biorefineries could transform lignin, an abundant biopolymer, from byproduct waste to high-value products for a sustainable society. Here we report the optimization of the AquaSolv omni biorefinery for lignin via Bayesian optimization, a machine learning framework for sample-efficient and guided data collection. This tool allows us to relate the biorefinery conditions like hydrothermal pretreatment reaction severity and temperature with multiple experimental outputs such as lignin structural features characterized using 2D nuclear magnetic resonance spectroscopy. By applying a Pareto front analysis to our models, we can find the processing conditions that simultaneously optimize the lignin yield and the amount of \bof{} linkages for the depolymerization of lignin into platform chemicals. Our study demonstrates the potential of machine learning to accelerate the development of sustainable chemical processing techniques for targeted applications and products.

Version notes

The purpose of our work is now presented in clearer fashion and the impact of our results is better highlighted. Furthermore, the terminology and descriptions of some of the machine learning concepts underlying our work has been made clearer. Lastly, we have updated the title.


Thumbnail image of article_lof22.pdf

Supplementary material

Thumbnail image of SI_lof22.pdf
Supporting Information: Machine Learning Optimization of Lignin Properties in Green Biorefineries
The supporting information contains a more technical introduction to BO and the concept of Pareto optimality. We also provide complementary results for the acquisition strategy comparisons and the model validation.