AI and Materials Simulations (AIMS) Laboratory

Integrating molecular modeling, data science, and AI to accelerate materials discovery

Welcome to the AI and Materials Simulations (AIMS) Laboratory at North Carolina State University, where we develop and deploy AI workflows and multiscale molecular modeling methods for predictive and data-efficient materials understanding and design.

We develop and apply multiscale molecular simulation approaches, spanning density functional theory (DFT), all-atom molecular dynamics (MD), and coarse-grained and mesoscale methods (CGMD, DPD), to fundamentally understand structure–property–function relationships, emergent behavior, and dynamic processes in complex materials systems across relevant length and time scales.

We design AI-driven workflows for materials discovery and optimization, together with rigorous data integration and data-fusion methodologies grounded in statistics and computer science. These approaches are specifically aimed at extracting actionable insight from small, sparse, heterogeneous, and multimodal datasets, and are transferable across application domains, from materials science to water quality and phosphorus sustainability.

Research topics in the AIMS Lab span soft and biomimetic materials, polymer and nanocomposites, and biological systems. We investigate self-assembly, chemical and environmental stability, mechanical and optical properties, transport phenomena, and dynamic responses, with an emphasis on connecting molecular-scale mechanisms to macroscopic function.

A central mission of AIMS is education and workforce development. We train scientists and engineers to operate fluently at the intersection of materials science and engineering, physics, chemistry, statistics, and computer science, preparing them to lead in AI-enabled materials research, self-driving laboratories, and data-centric engineering innovation.

Biomimetic Materials

Self-assembly of DNA and RNA-based nanomaterials with responsive properties;
Design of organized nanochannel materials from biomolecular magnetic organic frameworks; In silico design of reflectin-inspired mechanimorphic
materials; Biomimetic materials design for phosphorous sustainability; Enzyme engineering and biocatalyst interactions with gases; Controlled properties of cellulose nanocrystals-based materials

Nanomaterials and nanoparticles

Development of new molecular modeling approaches for studies of magnetic and metal nanoparticles; Magnetic alignment of multi-functional nanoparticles as a function of environment; Properties of polymer nanocomposites; Design of nanoparticle-based materials for environmental clean-up

AI and Data Science

Leveraging data-science techniques to analyze and extract valuable insights from heterogeneous and multi-technique data characterization data; Development of approaches for materials data integration; Convergence Informatics for phosphorous sustainability; Approaches for handling small data: data imputation and augmentation Generative AI for data retrieval