Data-Driven Materials Discovery

Unleashing AI to accelerate materials discovery.

Advances in data science and machine learning are revolutionizing materials science and engineering research. By integrating artificial intelligence with high-throughput experimentation and computation, our research teams are transforming materials discovery and development, reducing development cycles from decades to months.

Areas of AI-Driven Innovation:

Next-Generation Computing Technologies: Optimizing materials with unprecedented electronic and optical properties.
Sustainable Infrastructure and Environmental Solutions: Leveraging AI to model material performance in extreme environments and analyze microplastic behavior.
New Materials Discovery: Utilizing machine learning to streamline the synthesis and analysis of materials, speeding up the discovery process.
High-Throughput Materials Screening: Combining combinatorial thin-film synthesis and characterization with efficient descriptor filtering simulations to rapidly identify and improve ionic materials for energy technologies.

FEATURED RESEARCH:

AI-Enhanced Peptide Conductivity

Professor Charles Schroeder’s team combines experimental data and advanced computational techniques to reveal how folded molecular structures enhance electron transport in peptides. These insights pave the way for designing highly efficient molecular electronic devices.

“This discovery provides a new understanding of how electrons flow through peptides with more complex structures while offering new avenues to design and develop more efficient molecular electronic devices."

Charles Schroeder, James Economy Professor

Read Full Story