Structure divide-and-conquer: dual graph representation for accurate ionic transport barrier prediction of inorganic compounds

作者：Zhengwei Yang, Linhan Wu, Bing He, Maxim Avdeev, Siqi Shi, Yue Liu · 发表于：npj Computational Materials · 年份：2026 · DOI：10.1038/s41524-026-02058-1 · 被引用次数：2 · 研究领域：Machine Learning in Materials Science、Computational Drug Discovery Methods、Advanced Graph Neural Networks

Despite the effectiveness of most graph-based representation methods in capturing the crystal geometry characteristics, they fall short in intuitively describing phenomena such as ionic transport behavior which are often determined by the atom-unoccupied regions in the mobile sublattice (namely interstitial network). Here, we develop a Structure Divide-and-Conquer Graph Representation method based on graph neural network (SDCGNN dk ), for unveiling structure-activity relationships of transport barriers by incorporating Domain Knowledge (e.g., site energy information, thresholds for ion accessibility, etc.), where crystal geometry and interstitial network topology are combined to construct a dual-structure crystal graph. For driving the proposed model, we construct a graph-based dataset for the prediction of activation energy ( \({E}_{a}\) ), i.e., the energy barrier hindering ionic transport, covering over 18,000 ionic compounds from the Inorganic Crystal Structure Database (ICSD), including Li + , Na + , K + , Ag + , Cu (2,3)+ , Mg 2+ , Zn 2+ , Ca 2+ , Al 3+ , F − , and O 2− . SDCGNN dk achieves high prediction performance of \({E}_{{\rm{a}}}\) with R 2 of 91.30%, outperforming conventional GNNs by more than 20% on average and offering insights into structure-activity relationships by quantifying the contributions of crystal geometry and interstitial network characteristics to transport barriers. This work provides an accurate graph representation and GNN framework, demonstr...