(562g) Machine Learning-Aided Ionic Liquid Design for PET Degradation

Every year, more than 350 million tons of plastic waste are generated globally, but only a small percentage (9%) is recycled. The rest of this non-degradable waste ends up in landfills and causes water and land pollution. To address this pressing issue, there is an urgent need to upcycle plastic waste into value-added bioproducts. Polyethylene terephthalate (PET) is one of the largest sources of plastic waste, accounting for more than 20% of total plastic waste production. The conversion of PET to useful bioproducts has been intensively studied, and one promising solution is to use ionic liquids as catalysts for converting PET into Bis(2-Hydroxyethyl) terephthalate (BHET) through glycolysis. However, finding a cost-effective and efficient ionic liquid for PET valorization is still challenging. The vast array of available ionic liquids can make experimental screening and parameter optimization a daunting task toward multiple objectives in performance, cost, and environmental impact. To tackle this issue, we present a data-driven approach using machine learning techniques to efficiently design and screen ionic liquids for PET glycolysis. We have compiled a database of approximately 600 ionic liquids and deep eutectic solvents for PET glycolysis based on literature data. By analyzing a range of reaction information such as catalyst, solvent, temperature, time, and size, our machine learning model predicts the performance of different ionic liquids on PET glycolysis. Through this approach, we identified the best performing and cost-effective ionic liquid, a zinc chloride (ZnCl2)-choline chloride (ChCl) based deep eutectic solvent, which demonstrated promising performance and low cost compared to previous studies, and this finding was validated through the experiments. Overall, this method provides an efficient and systematic way to identify ionic liquids for PET glycolysis and can contribute to the development of sustainable plastic waste management strategies.