Multi-Variable Multi-Metric Optimisation of Self-Assembled Photocatalytic CO2 Reduction Performance using Machine Learning Algorithms
The sunlight-driven reduction of CO2 into fuels and platform chemicals is a promising approach to enable a circular economy. However, established optimisation approaches are poorly suited to multi-variable multi-metric photocatalytic systems because they aim to optimise one performance metric while sacrificing the others and thereby limit overall system performance. Herein, we address this multi-metric challenge by defining a metric for holistic system performance that takes all figures of merit into account, and employ a machine learning algorithm to efficiently guide our experiments through the large parameter matrix to make holistic optimisation accessible for human experimentalists. As a test platform, we employ a five-component system that self-assembles into photocatalytic micelles for CO2-to-CO reduction, which we experimentally optimised to simultaneously improve yield, quantum yield, turnover number, and frequency while maintaining high selectivity. Leveraging the dataset with machine learning algorithms allows quantification of each parameter’s effect on overall system performance. The buffer concentration is unexpectedly revealed as the dominating parameter for optimal performance, and is nearly four times more important than the catalyst concentration. The expanded use and standardisation of this methodology to define and optimise holistic performance will accelerate progress in different areas of catalysis by providing unprecedented insights into performance bottlenecks, enhancing comparability, and taking results beyond comparison of subjective figures of merit.