Virginia Tech Faculty Receives National Artificial Intelligence Research Resource Pilot Awards Virginia Tech News

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Anuj Karpatne's project “Lake-GPT: Building a Foundation Model for Aquatic Sciences” is one of the first 35 to be supported by the National Artificial Intelligence Research Resource (NAIRR) pilot program with Computational Time, a US-based researcher. is an important milestone in connecting and teachers to the computational, data and training resources needed to advance artificial intelligence (AI).

The NAIRR Pilot Awards – a collaborative effort led by the National Science Foundation in collaboration with other US federal agencies – are the result of President Joe Biden's landmark executive order on the safe, secure and reliable development and use of AI, and recognize researchers and Provide access to students. Access to key AI resources and data.

Kruptane, an associate professor in the Department of Computer Science and core faculty of the Singhani Center for Artificial Intelligence and Data Analytics, was among 10 award recipients who were addressed at a ceremony hosted by the Office of Science and Technology Policy at the White House. was invited to AI Research Frontier is announcing the launch of the NAIRR pilot program on May 6. Carpetne was one of two recipients invited to give lengthy talks on their NAIRR projects at the National Competitiveness for AI Expo in Washington, DC, hosted by the Special Competitiveness Studies Project.

The second group of NAIRR pilot awardees, announced in late May, includes Debswapna Bhattacharya, associate professor of computer science, and Xuan Wang, assistant professor of computer science and core faculty at the Singhani Center.

All NAIRR pilot awardees are supported for six months and have access to advanced computing systems funded by the National Science Foundation or supported by the Department of Energy for their AI research. goes Carpetney is using the AI ​​capability of the Summit supercomputer at Oak Ridge National Laboratory to model water quality in lakes and reservoirs across the United States. Bhattacharya is using the Texas Advanced Computing Center's graphic processing units (GPUs) to supercharge foundational AI models for epidemic prediction, and Wang is using the Pittsburgh Supercomputing Center's Neocortex as a dedicated resource.

Building a new class of foundation models in hydrology

Carpentne's research is exploring how advances in large-scale foundational models like ChatGPT can influence similar advances at the AI ​​research frontier to enable scientific revolutions in domains where the nature of data is at their core. may be quite different from industrial counterparts involving text and image data at the scale of the Internet. .

In the NAIRR project, Karpatne and his team are developing a new class of foundational models in aquatic science, called Lake-GPT, using new developments in the emerging field of water modeling in lakes and reservoirs. To model a variety of quality-related processes. Environmental knowledge-guided machine learning.

He said this differs from mainstream approaches to building “black box” AI models that rely entirely on observations in data to take advantage of the wealth of scientific knowledge available across many domains in diverse formats. can be raised, including conservation laws such as aquatic sciences. of mass and energy.

“As climate change and increasing demand for water continue to put pressure on our already fragile water resources, we are witnessing growing crises of water availability and quality in many parts of the world,” Carpetne said. ” “Understanding how to best respond to current crises requires exploring scenarios of change in both water use and climate change so that we can protect our precious water resources while meeting society's needs. can direct further action.”

Carpetney is collaborating with lake scientists and ecologists from Virginia Tech and other universities:

  • Kellan Carey, Professor of Freshwater Ecosystem Science and Roger Moore and Mohd Khatam Moore Faculty Fellow, Department of Biological Sciences
  • Mary Lofton, Postdoctoral Associate, Department of Biological Sciences
  • Paul Hanson, Distinguished Research Professor at the University of Wisconsin-Madison's Center for Limnology and lead principal investigator of a National Science Foundation Macrosystems Biology grant that supported the research.
  • Bennett McAfee, Ph.D. The student was advised by Hanson.
  • Abhilash Neog, Ph.D. The student was advised by Corrupt.
  • Student advised by Sapida Fatemi Khorasgan, Ph.D.
  • Arca Dao, a PhD graduate from Carpetne's group, is currently a Distinguished Staff Fellow at Oak Ridge National Laboratory.

“We hope that our research will not only enable a new type of model in hydrology that predicts water quality in lakes and reservoirs, but also the emerging characteristics of lake processes and macrosystem scales. But it will also enable the discovery of their interaction, said Kriptne, leading to the advancement of scientific knowledge.

WhatsApp Group Join Now
Telegram Group Join Now
Instagram Group Join Now

Leave a Comment