$500,000 grant funds creation of institute to advance AI for materials sciencePosted on January 27, 2021
UNIVERSITY PARK, Pa. — A National Science Foundation (NSF) grant will help lay the foundation for an interdisciplinary institute that encourages the use of artificial intelligence-enabled materials discovery, design and synthesis, according to a team of researchers.
Funds from the $500,000 grant will be used to bring together an interdisciplinary team of researchers with complementary expertise in artificial intelligence (AI) and material science to lay the groundwork for an AI-Enabled Materials Discovery, Design, and Synthesis (AIMS) Institute, according to Vasant Honavar, professor, Edward Frymoyer Chair of Information Sciences and Technology at Penn State and an Institute for Computational and Data Sciences associate director and co-hire.
According to Honavar, AI offers an important suite of tool for scientists, across many domains. The focus of the NSF-funded project is on accelerating materials design and synthesis methods that would take years or even decades of effort through traditional means. Researchers often must resort to methodical, painstaking trial-and-error processes as they seek to make advances in materials design. By automating some of that work, AI and machine learning could help speed up discoveries, helping the scientists produce innovations that serve science and society.
The emergence of big data and advances in machine learning have dramatically accelerated some of the key steps in science, for example, fitting complex models to data and predictive modeling, said Honavar, an AI expert and the principal investigator on the grant.
“However, other key elements of the scientific process — such as generating hypotheses; designing, prioritizing and executing experiments; integrating data, models and simulations; and communicating across disciplines — remain largely untouched by the advances in artificial intelligence (AI),” said Honavar. “The focus of this project is to advance AI methods and tools that can dramatically accelerate scientific discovery, by augmenting, amplifying and extending human intellect and abilities.”
According to co-principal investigator Adri van Duin, professor of mechanical and nuclear engineering and ICDS associate, AI is increasingly helping scientists investigate natural phenomena, but the technology is also under-utilized in other aspects of the scientific process.
“AI offers researchers a powerful suite of tools for scientists that can help drive science by dramatically accelerating scientific discovery, in a number of domains, including materials discovery,” said van Duin, a material scientist and co-principal investigator on the grant.
Honavar added, “The resulting advances in AI-enabled materials discovery can help meet the demand for new materials for a number of critical applications, such as energy technologies. For example, batteries, solar cells, sensing — such as biosensors,” and next-generation computing, including quantum computing.”
Among the goals, the institute will serve as a catalyst to establish collaborations that will transcend institutional and organizational boundaries.
The next generation of workers who use AI must also be diverse, according to the institute’s leadership. Inclusion will be central to the institute’s aim to help create a diverse AI workforce, including women and underrepresented minorities, both students who plan to become AI researchers and developers, as well as professionals already working in the field.
The planning project will organize a seminar series, workshops and idea labs to further develop the vision, initiate interdisciplinary research at the nexus between AI and materials science, identify the AIMS infrastructure needs, develop education and outreach plans, establish cohesive partnerships and develop the requisite organizational structure and processes for realizing the AIMS vision.
Team members also include co-principal investigators: Dane Morgan, Harvey D. Spangler Professor of Engineering, University of Wisconsin-Madison; Elsa Olivetti, Esther and Harold E. Edgerton Associate Professor in Materials Science and Engineering; and Mehrdad Mahdavi, Dorothy Quiggle Career Development Assistant Professor of Computer Science & Engineering at Penn State; and over 20 researchers drawn from the participating institutions.
- Algorithm aims to alert consumers before they use illicit online pharmacies
- Scientists tap AI betting agents to help solve research reproducibility concerns
- Deep learning may help doctors choose better lung cancer treatments
- Using cues and actions to help people get along with artificial intelligence