In recent years, the United States has struggled with supply shortages of critical materials needed to discover and manufacture advanced materials. Widespread delays have affected sectors ranging from defense to industrial technology.
High dependence on foreign sources highlights vulnerabilities in the global materials supply chain, creating obstacles to the development of new materials, innovative manufacturing solutions, and commercialization.
With these challenges in mind, Lenore Dye, professor of chemical engineering and associate dean for undergraduate administration in the Ira A. Fulton College of Engineering at Arizona State University, is building an interdisciplinary team to optimize the use of artificial intelligence tools and machines. leading. Learning models in basic materials research.
The project is a collaboration between University of Missouri researchers and microelectronic materials manufacturer Brewer Sciences.
“This collaboration is a perfect example of why Arizona State University is committed to conducting research of public value,” said ASU President Michael Crow. “Embracing the use of AI and machine learning as a mechanism to advance research in ways that lead to significant advances in manufacturing processes is the kind of impact we have on our work at ASU. It’s great progress and we’re excited to be part of the team that makes it happen.”
“The University of Missouri is proud to be a part of the University of Missouri,” said Moon Choi, president of the University of Missouri. “We are thrilled that our world-class faculty researchers will be partnering with our distinguished colleagues at ASU and Brewer Science on innovative AI and materials science research. This innovative collaboration will address critical needs in our nation. and continue our tremendous momentum.”
Dai is the principal investigator on a new contract with the U.S. Army Corps of Engineers’ Engineer Research and Development Center (ERDC) to accelerate materials design and process optimization with artificial intelligence and machine learning.
ERDC leaders highlight how AI and machine learning will transform materials science research and innovation and emphasize the importance of new collaborations.
“We are excited to begin this new partnership between Arizona State University, the University of Missouri, Brewer Science, and ERDC,” said Robert Moser, director of ERDC’s Information Technology Laboratory. “The nexus of materials science and artificial intelligence is an important one that can shape a variety of interesting applications for ERDC and the Army, and we look forward to seeing the results from this impactful research and team of experts. ”
“Artificial intelligence and machine learning will enable us to quickly analyze complex scientific data to find materials with exactly the properties we need, creating new We’re excited because this project not only uses advanced AI technology, but also brings together expertise from Arizona State University, the University of Missouri, and brewing science. Masu. This partnership will accelerate innovation in materials science by improving AI and machine learning skills for materials optimization and laboratory automation. ”
This project will focus on using AI and machine learning to enhance the development of new materials and optimize manufacturing processes. Use large-scale language models (LLMs) to drive the design and discovery of new materials systems, generating hypotheses and integrating new, experimentally validated computational tools for materials discovery, design, and manufacturing. I will support you.
“AI tools such as LLMs like ChatGPT can be used to accelerate scientific research and cover a wide range of knowledge that is difficult to obtain by a single person. However, LLMs have high error rates and are prone to illusions. and other issues,” says Dai. “One of our goals is to develop rapid and fine-tuned methodologies and software modules to significantly reduce these errors.”
Additionally, the team will conduct experiments to carefully investigate whether a particular learning architecture is appropriate to capture physical causal relationships across key chemical, microstructural and physical features in the material design and development process. Integrate new and validated machine learning models.
“The research that Professor Dye and her team are working on highlights innovative uses of AI in ways that are important to industry and society at large,” said ASU’s Senior Professor of Engineering, Computing and Technology. said Kyle Squires, associate provost and dean of the Fulton School. “These tools will help researchers accelerate the discovery process, create more agile manufacturing processes, and ultimately deliver innovations that transform society.”
Mr. Dai emphasized the vast scope of the project and how collaboration across multiple institutions and sectors will expand its potential.
“It is important to recognize the scope and potential this project has as a result of collaboration with a variety of interdisciplinary faculty within the University of Missouri, Beer Science, and the Fulton School,” Dye says. “This creates an environment that engages large audiences and creates incredible impact across institutions, private organizations, and government sectors.”
