System, device and method for material subgraph model

Abstract

A system and a method are disclosed for material property prediction using subgraph modeling. A method may utilize artificial intelligence (AI)-based material subgraph models, including the decomposition of the molecular structure of materials, to generate graphs of subgraphs, and implement subgraph modeling to scale AI-based models for use with large and / or complex molecules and enhance the material property predictions. Aspects can involve utilizing the enhanced material property predictions to improve the overall performance of display related products. For instance, by using material property predictions with greater accuracy from subgraph modeling, materials deemed most suitable and / or efficient may be used to manufacture a display device. The method may include generating subgraphs comprising a molecular substructure of a material, and applying an AI-based model to the subgraphs to generate a material property prediction based on the molecular substructure of the material.

Images