Recently, a research team led by Prof. Yong Wang from Zhejiang University, China, created a data augmented convolutional neural network ML framework called GLCNN, which combines"global + local" features. This framework can capture the original fine structures without complicated encoding methods by transforming catalytic surfaces and adsorption sites into two-dimensional grids and one-dimensional descriptors, respectively.
The addition of data augmentation can expand the dataset and alleviate overfitting caused by insufficiency of chemical datasets. The GLCNN framework accurately predicted and distinguished the adsorption energies of OH on a set of analogous carbon-based transition metal single-atom catalysts with a mean absolute error of less than 0.1 eV, ranking the best result of popular models trained on large datasets so far.
Unlike conventional CNN and descriptor-based ones with one-sided feature extraction, this fine-structure sensitive ML framework can extract the key factors that affect catalytic performance from both geometric and chemical/electronic features, such as symmetry and coordination elements, through unbiased interpretable analysis.and symmetry element of adsorption sites are crucial, and the importance of metals is stronger than their coordination environment.
As the layers deepen, GLCNN gradually seeks the direction of feature extraction based on basic catalytic knowledge, extracting more abstract high-dimensional features that are conducive to adsorption energy prediction. This provides a feasible solution for high-precision HT screening of heterogeneous catalyst with a broad physical and chemical space.Yuzhuo Chen et al, Fine-structure sensitive deep learning framework for predicting catalytic properties with high precision,