(306c) Leveraging Small Data for Faster and Better Catalysis

Although 90% of all chemical processes are catalytic in nature, the development of new catalytic systems is a time-intensive and expensive challenge. Complex optimization efforts are commonly required to enhance catalytic performance while avoiding harsh reaction conditions, high costs, and other limitations that hinder their implementation and commercialization.

Data-driven machine-learning (ML) offers the possibility to dramatically reduce the resources needed for reaction optimization through supervised-learning models that predict reaction performance, catalytic behavior, and optimal reaction conditions. However, most ML algorithms require large datasets (i.e. 100’s-1000’s of points) to provide accurate predictions, while experimental data collection is expensive in human and material resources. The challenge of building large datasets can be averted with Bayesian Optimization frameworks that guide experimental campaigns through informed and smart decisions. Predictions are thus based on carefully selected training data, which ultimately reduces the number of experiments required to achieve reliable understanding of variable effects and reaction behavior.

We introduce a modified Bayesian Optimization approach that accelerates the design and implementation of intelligent experimental campaigns for faster and better catalytic transformations. Working at the intersection of ML and chemistry, we created SuntheticsML, an online, user-friendly, ML platform that leverages very small data (starting with only 5 data points) to enable the development of new catalytic processes, materials, and formulations up to 15 times faster without the need of coding or ML skills. A tool that is already available to scientists in academia and industry for better chemistry.

The insights from this work innovate on the future of catalysis and reaction optimization while lowering the barrier to the implementation of new catalytic technologies. SuntheticsML accelerates traditional optimization campaigns, harnessing the power of ML and small data to fast-track innovation, sustainability, and digitalization in the chemical industry, further reducing development waste, emissions, and resource consumption by up to 95%.