Accelerating the Design of Photocatalytic Surfaces for Antimicrobial Application: Machine Learning Based on a Sparse Dataset

Nowadays, most experiments to synthesize and test photocatalytic antimicrobial materials are based on trial error. More often than not, the mechanism of action activity is unknown for a large spectrum microorganisms. Here, we propose scheme speed up design optimization surfaces tailored give balanced production reactive oxygen species (ROS) upon illumination. Using an experiment-to-machine-learning applied limited experimental dataset, built model that can predict applications over wide range material compositions. This machine-learning-assisted strategy offers opportunity reduce cost, labor, time, precursors consumed during Our may significantly accelerate large-scale deployment photocatalysts as promising route mitigate fomite transmission pathogens (bacteria, viruses, fungi) in hospital settings public places.