(288d) Combining Flow Processing with Machine Learning Accelerated for Accelerated Development and Scaling of New Materials. Case Study: Nanozno Antibacterial Coatings

New material innovation is limited by the time, expertise and cost of development. In the face of rapidly growing crises like pandemics, resource scarcity and climate change, we require new methods and methodologies to create and scale-up new technologies. In this work, we introduce an accelerated platform for material development, featuring advanced machine learning methods, continuous microreactors and automation. As a case study, this platform was used to develop highly antimicrobial zinc oxide materials for coatings, with simultaneously optimized yield and performance. Continuous, high-shear microreactors and tangential flow filtration were employed at the lab-scale to enhance space time yields and scalability via number-up and scale-out, and culminating in ~ kg/day scale production. Decision-making was accelerated with the use of a multi-objective optimization algorithm for experimental design, allowing fast exploration of many variables without lengthy factorial designs and heuristic scale-up techniques. Furthermore, this platform was used to probe relationships between material characteristics (such as morphology and crystallinity), application performance and process parameters, showcasing the capability of this platform to make new discoveries and mechanistic insights. This approach features broad applicability to a range of materials and industries, including energy storage, pharmaceuticals and catalysis.