Sputtering is a crucial technology in fields such as electric propulsion, materials processing, and semiconductors. Modelization of sputtering is significant for improving thruster design and designing material processing control algorithms. This paper uses the Hierarchical Clustering Algorithm (HCA) to perform cluster analysis on 17 descriptors related to sputtering. These descriptors are divided into four fundamental groups, with representative descriptors being the mass of the incident ion, the formation energy of the incident ion, the mass of the target, and the formation energy of the target. The paper further discusses the possible physical processes and significance involved in the classification process, including cascade collisions, energy transfer, and other processes. Finally, based on the analysis of the above descriptors, several neural network models are constructed for the regression of sputtering threshold Eth, maximum sputtering energy Emax, and maximum yield SYmax. In the regression model based on 267 samples, the four descriptor attributes showed higher accuracy compared to the 17 descriptors (R2 evaluation) in the same neural network structure, with the 5×5 neural network structure achieving the highest accuracy, having an R2 of 0.92. Additionally, a simple sputtering test data also demonstrated the generalization ability of the 5×5 neural network model, the error in maximum sputtering yield is less than 5%.