Predicting Active Sites in Photocatalytic Degradation Process Using an Interpretable Molecular-Image Combined Convolutional Neural Network

Machine-learning models have great potential to accelerate the design and performance assessment of photocatalysts, leveraging their unique advantages in detecting patterns and making predictions based on data. However, most machine-learning models are "black-box" models due to lack of interpretability. This paper describes the development of an interpretable neural-network model on the performance of photocatalytic degradation of organic contaminants by TiO2. The molecular structures of the organic contaminants are represented by molecular images, which are subsequently encoded by feeding into a special convolutional neural network (CNN), EfficientNet, to extract the critical structural features. The extracted features in addition to five other experimental variables were input to a neural network that was subsequently trained to predict the photodegradation reaction rates of the organic contaminants by TiO2. The results show that this machine-learning (ML) model attains a higher accuracy to predict the photocatalytic degradation rate of organic contaminants than a previously developed machine-learning model that used molecular fingerprint encoding. In addition, the most relevant regions in the molecular image affecting the photocatalytic rates can be extracted with gradient-weighted class activation mapping (Grad-CAM). This interpretable machine-learning model, leveraging the graphic interpretability of CNN model, allows us to highlight regions of the molecular structure serving as the active sites of water contaminants during the photocatalytic degradation process. This provides an important piece of information to understand the influence of molecular structures on the photocatalytic degradation process.