A multimodal deep‐learning (MDL) framework is presented for predicting physical properties of a ten‐dimensional acrylic polymer composite material by merging physical attributes and chemical data. The MDL model comprises four modules, including three generative deep‐learning models for material structure characterization and a fourth model for property prediction. The approach handles an 18‐dimensional complexity, with ten compositional inputs and eight property outputs, successfully predicting 913 680 property data points across 114 210 composition conditions. This level of complexity is unprecedented in computational materials science, particularly for materials with undefined structures. A framework is proposed to analyze the high‐dimensional information space for inverse material design, demonstrating flexibility and adaptability to various materials and scales, provided sufficient data are available. This study advances future research on different materials and the development of more sophisticated models, drawing the authors closer to the ultimate goal of predicting all properties of all materials.

A comprehensive characterization of various carbon nanotube (CNT) yarns provides insight for producing high-performance CNT yarns as well as a useful guide to select the proper yarn for a specific application. Herein we systematically investigate the correlations between the physical properties of six CNT yarns produced by three spinning methods, and their structures and the properties of the constituent CNTs. The electrical conductivity increases in all yarns regardless of the spinning method as the effective length of the constituent CNTs and the density of the yarns increase. On the other hand, the tensile strength shows a much stronger dependence on the packing density of the yarns than the CNT effective length, indicating the relative importance of the interfacial interaction. The contribution of each physical parameter to the yarn properties are quantitatively analyzed by partial least square regression.

Artificial intelligence relying on structure-property databases is an emerging powerful tool to discover new materials with targeted properties. However, this approach cannot be easily applied to tangible structures, such as plastic composites and fabrics, because of their high structural complexity. Here, we propose a deep learning computational framework that can implement virtual experiments on tangible structures. Structural representations of complex carbon nanotube films were conducted by multiple generative adversarial networks of scanning electron microscope images at four levels of magnifications, enabling a deep learning prediction of multiple properties such as electrical conductivity and surface area. 1716 virtual experiments were completed within an hour, a task that would take years for real experiments. The data can be used as a versatile database for material science, in analogy to databases of molecules and solids used in cheminformatics. Useful examples are the investigation of correlations between electrical conductivity, specific surface area, wall number phase diagrams, economic performance, and inversely designed supercapacitors.