Massive amounts of real-world data are needed to model complex systems. Collecting and organizing the right data takes time, and lots of it.
Researchers from the University of Arizona and University of New Mexico were awarded $4.6 million from the National Science Foundation to develop a data storage platform that incorporates an artificial intelligence agent to scour metadata for published research on virtually any topic and deliver results in minutes.
UNM’s Tyson Swetnam, associate professor of computer science, heads the project, called Multidisciplinary Environment for Scientific Advancement, or MESA. U of A collaborators include David Ebert, chief AI and data science officer; Barney Maccabe, professor and associate dean of research in the College of Information Science; and Lei Cao, assistant professor of computer science.
“We’re helping define the national infrastructure for AI-enabled scientific research,” said Ebert, also Computer Science Engineering Endowed Innovation Chair and professor in the School of Electrical, Computing and Software Engineering.
MESA is part of the NSF’s $83 million national investment in integrated data systems and services, focused on supporting researchers to discover, access, share and analyze large volumes of scientific data.
U of A will receive $2.1 million over two years to develop MESA’s user interface and a cloud-based storage apparatus that hosts datasets from NSF-funded national research labs. AI agents built into the platform search raw data, images and videos to find files most relevant to users’ requests.
“It will help researchers be more effective, make discoveries more efficiently and optimize their workflows,” said Ebert.
Unlimited answers in one place
MESA’s materials span several fields. The prototype’s initial datasets cover environmental science, black hole analysis on the Event Horizon Telescope and next-generation cellular networks.
Among the many datasets MESA will host is Jingdi Chen’s simulation data for network slicing algorithms to increase speed on 5G and 6G cellular networks.
“We don’t have a standard dataset to test these algorithms,” said Chen, an assistant professor in the U of A School of Electrical, Computing, and Software Engineering. “We have to prepare and gather our own dataset from industry collaborators.”
Slicing refers to how networks proportionally allot bandwidth, latency and security – depending on user needs – for faster loading. For example, while both use cellular networks, smartphones require different resource allotments than, say, autonomous vehicles.
Chen also trains the algorithms to detect cyberattacks before they can do harm.
“These two use cases require lots of real-world data,” she said.
With MESA’s AI-enabled data collection, researchers such as Chen will have at their fingertips the data they need to simulate systems and processes for scientific advancement.