Conductive polymer nanocomposites have emerged as essential materials for wearable devices. In this study, we propose a novel approach that combines graph attention networks (GAT) with an improved global pooling strategy and incremental learning. We train the GAT model on homopolymer/carbon nanotube (CNT) nanocomposite data simulated by hybrid particle-field molecular dynamics (hPF-MD) method within the CNT concentration range of 1–8%. We further analyze the conductive network structure by integrating the resistor network approach with the GAT’s attention scores, revealing optimal connectivity at a 7% concentration. The comparative analysis of trained data and the reconstructed network, based on the attention scores, underscores the GAT model’s ability in learning network structural representations. This work not only validates the efficacy of the GAT model in property prediction and interpretable network structure analysis of polymer nanocomposites but also lays a cornerstone for the reverse engineering of polymer composites.
The hybrid particle–field molecular dynamics simulation method (MD-SCF) was applied to study the self-assembly of Pluronic PEO20-PPO70-PEO20 (P123) in water/ethanol/turpentine oil- mixed solvents. In particular, the micellization process of P123 at low concentration (less than 20%) in water/ethanol/turpentine oil-mixed solvents was investigated. The aggregation number, radius of gyration, and radial density profiles were calculated and compared with experimental data to characterize the structures of the micelles self-assembled from P123 in the mixed solvent. This study confirms that the larger-sized micelles are formed in the presence of ethanol, in addition to the turpentine oil-swollen micelles. Furthermore, the spherical micelles and vesicles were both observed in the self-assembly of P123 in the water/ethanol/turpentine oil-mixed solvent. The results of this work aid the understanding of the influence of ethanol and oil on P123 micellization, which will help with the design of effective copolymer-based formulations.