Metal-organic frameworks (MOFs) are considered one of the most important materials for carbon capture and storage (CCS) due to the advantages of porosity, multifunction, diverse structure, and controllable chemical composition. With the continuous development of artificial intelligence (AI) technology, more and more machine learning models are used to identify MOFs with high performance within a massive search space. However, current works have yet to form a model that uses graph-structured data only, which can predict the adsorption properties of single and binary components. In this work, we proposed and developed a graph transformer, combined with convolution parallel networks, called GC-Trans. The model can accurately and efficiently predict the adsorption performance of MOFs under the single- and binary-component adsorption conditions using only the features of the crystal diagram as inputs. By extracting and fusing local and global feature information, the model has stronger expression and generalization abilities. Thus, we used it to screen the ARC-MOF database and analyze the MOF structures that meet the target requirements. Additionally, to demonstrate the transferability of the model, we applied transfer learning methods to predict the CO2/CH4 separations and CH4 uptake, both of which showed good predictive performance.
Keywords: adsorption performance; carbon dioxide capture; graph convolution networks; graph transformer; metal−organic frameworks; molecular simulation.