A Comprehensive and Versatile Multimodal Deep Learning Approach for Predicting Diverse Properties of Advanced Materials
This work addresses the challenge of predicting diverse properties for advanced materials, particularly in computational materials science, though it appears incremental as it builds on existing multimodal deep learning methods.
The researchers tackled the problem of predicting physical properties of complex acrylic polymer composites by developing a multimodal deep learning framework that merges physical and chemical data, successfully predicting 913,680 property data points across 114,210 composition conditions. This approach handles an 18-dimensional complexity, which is unprecedented for materials with undefined structures.
We present a multimodal deep learning (MDL) framework for predicting physical properties of a 10-dimensional acrylic polymer composite material by merging physical attributes and chemical data. Our MDL model comprises four modules, including three generative deep learning models for material structure characterization and a fourth model for property prediction. Our approach handles an 18-dimensional complexity, with 10 compositional inputs and 8 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. We propose a framework to analyze the high-dimensional information space for inverse material design, demonstrating flexibility and adaptability to various materials and scales, provided sufficient data is available. This study advances future research on different materials and the development of more sophisticated models, drawing us closer to the ultimate goal of predicting all properties of all materials.