About – HT-MAX | Center on High-throughput Materials Discovery for Extremes

HT-MAX brings AI and innovation to the discovery of ceramics and other brittle materials

Developing and discovering new materials can have revolutionary impacts on defense, energy, and other sectors that utilize materials in extreme environments. Traditional approaches to materials discovery take time and resources, with significant delays due to trial-and-error experimentation and human error. The HT-MAX program is designed to accelerate traditional decades-long material discovery processes to a matter of years, months, or weeks.

By combining artificial intelligence, machine learning, and robotic automation technologies, HT-MAX researchers aim to discover novel hard/brittle materials with tailored properties for use in extreme environments. Desired properties include improved ductility, hardness, and strength when materials are exposed to elevated strain rates, pressures, temperatures, and heating rates.

HT-MAX builds upon earlier iterations of a “materials-by-design” approach, which integrates modeling, characterization, processing, and data management. However, this new HT-MAX framework also addresses varying levels of throughput and fidelity. Each mode of strategic sampling, from low throughput (ample sampling) to high throughput (limited, strategic sampling), relies on a firm foundation of data and AI-driven design.

"Birds-eye view of HT-MAX: Integrated modeling, testing, and characterization, leveraging data- and AI-driven approaches to design new materials." A series of rings showing the relationships between synthesis & processing, testing & characterization, and modeling, all with a data and AI-driven design core. The rings show that a high-throughput approach utilizes ample sampling, is idealized, and results in low-fidelity data. A low-throughput approach uses very limited sampling, is application-relevant, and results in high-fidelity data.

To learn more about the work being done in HT-MAX, visit our Google Scholar page.

Acknowledgement Statement

Research was sponsored by the Army Research Laboratory and was accomplished under Cooperative Agreement Number W911NF-22-2-0121. The views and conclusions contained in this document are those of the authors and should not be interpreted as representing the official policies, either expressed or implied, of the Army Research Laboratory or the U.S. Government. The U.S. Government is authorized to reproduce and distribute reprints for Government purposes notwithstanding any copyright notation herein.