Drexel Joins New NSF Institute Using Data Tools to Support Materials Science Research
Drexel University’s Metadata Research Center in the College of Computing & Informatics is one of 10 research partners that will be part of a new $15 million National Science Foundation effort to harness the power of data science and artificial intelligence to guide materials science research.
The last two decades have seen an acceleration of research into new materials with exceptional capabilities. From graphene, to carbon nanotubes, to Drexel’s own contribution, MXenes, scientists are discovering new ways to create chemically stable materials that perform exceptionally well at functions like storing energy, filtering water and air and transmitting radio waves. But with seemingly endless promise, comes the challenge of narrowing down the true paths toward progress.
The goal of the NSF Institute for Data Driven Dynamical Research (ID4) is bringing together the experimentally validated best approaches and tools to design and study these materials and structures.
“The volume of data generated ever day by materials science researchers offers unprecedented opportunity for new discoveries and shared approaches, but the data is too massive to tackle alone,” said Jane Greenberg, PhD, Alice B. Kroeger Professor in the College of Computing & Informatics and director of Drexel’s Metadata Research Center (MRC). “The collaborative, multidisciplinary approach that this institute is taking represents a paradigm shift from traditional materials research efforts.”
Led by the Colorado School of Mines, the Institute will focus on new representations and learning architectures that capture the time evolution of complex materials, efficient exploration of time-dependent design spaces and new visual analytics tools to incorporate human feedback into the design process.
“Drexel University’s Metadata Research Center will lead in advancing the functionalities for ontological systems in materials science. Ontologies, as structured knowledge systems, support automatic reasoning and can enhance AI applications. Drexel researchers will advance the HIVE-4-MAT ontology integration application by applying information extraction methods to mint richer knowledge structures to support predictive analytics.” Greenberg said.
In addition to the Colorado School of Mines and Drexel’s Metadata Research Center, research groups from Harvard University, Northeastern University, Northwestern University, Tufts University, the University of Illinois at Urbana-Champaign, the University of Central Florida, Washington University-St. Louis, and industry partner Kebotix, Inc. will be working together to develop algorithms and mechanisms that will give researchers better tools for predicting and understanding the behavior of new materials.
“We are extremely proud of the Metadata Research Center’s participation in this groundbreaking NSF Institute, and, thanks to the exceptional leadership of Dr. Jane Greenberg, their involvement reflects their continued, invaluable contributions to data science innovations,” said Yi Deng, PhD, Isaac L. Auerbach Professor and dean of the College of Computing & Informatics.
The MRC has been a leader in innovating solutions for pressing information and data-oriented challenges across scientific, social and humanistic domains since its founding in 2004. In addition to directing the MRC, Greenberg serves as the project lead for the NSF Harnessing the Data Revolution project “Accelerating the Discovery of Electronic Materials through Human-Computer Active Search,” which is the foundational grant for the new Institute.
Greenberg’s group will also support the Data Driven Dynamical Design Institute’s goal of helping researchers accurately and efficiently share knowledge and new discoveries across disciplines. As an active participant in the national and global Research Data Alliance and a member of the NSF Northeast Big Data Innovation Hub, the MRC will collaborate with these organizations to implement FAIR Data Principles across the Institute and share these data-sharing approaches more broadly with the research data community.
The Data Driven Dynamical Design Institute is one of five new Harnessing Data Revolution Institutes, funded by a $75 million NSF program to enable new modes of data-driven discovery that will explore fundamental questions at the frontiers of science and engineering.