Continuous Flow Chemistry and AI/ML Autonomous Driven Experiments

There is a lot of interest in artificial intelligence and machine learning (AI/ML) in materials. They have appended the ability to rapidly optimize synthetic routes, manufacturing methods, and characterization of properties. Digital twins with simulation (DFT, FEA, Multiphysics) and using neural networks with algorithms enable the application of logic-derived design, including regression analysis, which can go beyond Bayesian and statistical methods. This supersedes an otherwise trial-and-error approach in the synthesis, fabrication, and characterization of soft matter. This talk demonstrates continuous flow reaction chemistry and polymerization to optimize unit operation and the possibility of autonomous design and synthesis with real-time ML. There is a high possibility that a combination of P, V, T, and flow rate control enables new methods of copolymerization and the ability to use kinetics as a handle for optimized macromolecular properties and design for controlled yield and faster optimization. The automation for online monitoring is possible with improved instrumentation and the development of a feedback loop learning for possible deep learning (DL) development. With AI/ML, it is possible to optimize both the formulation and advanced manufacturing methods. The next stop is autonomous systems, but proving that human-on-the-loop is still the norm.