Back to Top
Skip to main content
NETL Research Enabling Critical Climate Modeling on Next-Generation Artificial Intelligence Computer System
An in-motion photograph of code being zoomed in on.

NETL researchers are helping the National Center for Atmospheric Research (NCAR) unlock the potential of an advanced artificial intelligence (AI) computing resource to perform critical climate modeling that could lead to better climate change predictions.

NCAR will conduct the research using Carnegie Mellon University’s cutting-edge Neocortex high-performance computing resource, which features the Cerebras CS-2 system, a ground-breaking AI computational resource powered by the world’s largest computer chip — the wafer scale engine (WSE).

NETL researchers have been collaborating with Cerebras Systems Inc. over the last two years on unique modeling capabilities using the WSE, and have been developing a user interface that allows users to easily write programs on the WSE for scientific modeling.

“The Wafer Scale Engine — Field Equation Application Programming Interface, or WFA for short, we developed has a very simple user interface, which lowers the barrier to entry on this hardware and provides both programming flexibility and extremely high performance. With our help, we hope to provide a seamless experience for the team,” said Dirk Van Essendelft, Ph.D., who leads NETL’s WSE capability research. “Climate modeling is a form of computational fluid dynamics modeling, which is what we’ve been working towards modeling with the WSE at NETL. So, I think we are well positioned to help NCAR Furthermore, this collaboration could open the door to future collaborative work.”

Such a collaboration would leverage NETL’s work harnessing the power of the WSE to solve what are known as field equations. Solving these equations is critical to the understanding of electrodynamics, geomechanics, computational fluid dynamics and other areas that could aid climate modeling.

“Our current WSE capabilities are geared toward solving problems related to decarbonization technologies, and the same capabilities could be applied to achieving NCAR’s goals using our WFA,” Van Essendelft said. “This is a great opportunity for NETL to develop valuable relationships with other researchers, universities and the local supercomputing community on the frontier of AI research while enriching our own capabilities.

Neocortex is a resource of the Pittsburgh Supercomputing Center, a joint computational research center with CMU and the University of Pittsburgh. Established in 1986, PSC is supported by several federal agencies, the Commonwealth of Pennsylvania and private industry and is a leading partner in Extreme Science and Engineering Discovery Environment, the National Science Foundation cyber infrastructure program.

NCAR was established by the National Science Foundation in 1960 to provide the university community with world-class facilities and services that were beyond the reach of any individual institution.

NETL is a U.S. Department of Energy national laboratory that drives innovation and delivers technological solutions for an environmentally sustainable and prosperous energy future. By leveraging its world-class talent and research facilities, NETL is ensuring affordable, abundant and reliable energy that drives a robust economy and national security, while developing technologies to manage carbon across the full life cycle, enabling environmental sustainability for all Americans.