University of Dayton Research Institute

Electrical impedance tomography (EIT) is a nondestructive evaluation method that spatially maps the conductivity distribution within a given domain based on voltage measurements taken on the boundary. It has shown promise as a potential tool for in-situ monitoring of composite aerospace components. However, the current formulation of EIT is unable to distinguish between damage, strain, and environmental effects such as temperature and humidity changes. To address this problem, we propose a source separation algorithm that treats the unknown conductivity distribution as the sum of two sources with different spatial statistics. We demonstrate the method on simulated EIT data of an open-hole specimen loaded in tension with damage.

Many material systems exhibit complex spatial and temporal interactions across multiple length scales and modalities that govern macroscopic behavior. Although Machine Learning (ML) is widely used in materials science to predict this behavior, most approaches still rely on handcrafted descriptors or aggregated representations that overlook spatial organization, limiting insight into governing mechanisms. We introduce Materials Spatial Intelligence (MSI), a framework inspired by spatial intelligence that learns directly from multimodal spatial observations of material systems. MSI encodes high-resolution microstructural and deformation data into shared latent representations that preserve spatial relationships while supporting property prediction, interpretation, and optimization. By combining multimodal representation learning, MSI identifies the key features governing mechanical behavior and property trade-offs in structural alloys. Beyond prediction, MSI enables feature-driven microstructure optimization and mechanism discovery. More broadly, MSI establishes a foundation for applying spatial intelligence to materials science, leveraging interpretable ML systems to accelerate scientific discovery and materiel design