Current industry standards for design, which have long favored computer simulation over physical experimentation, remain remarkably slow. This new software brings down computational costs, allowing for more and better scientific experimentation.
The U.S. Department of Energy’s (DOE) Argonne National Laboratory and Parallel Works, Inc., a Chicago-based HPC software platform company, have won the 2022 Federal Laboratory Consortium’s (FLC) National Award for Excellence in Technology Transfer for their joint effort to bring Argonne’s R&D 100 award-winning Machine Learning–Genetic Algorithm (ML-GA) design optimization software to commercialization.
This latest win comes after the duo was awarded the 2021 FLC Midwest Regional honor for this same achievement. It is now their third major coup: Argonne won an award of $750,000 three years ago from the DOE’s Vehicle Technologies Office, within the Office of Energy Efficiency and Renewable Energy, through the Technology Commercialization Fund program to integrate novel features into ML-GA and make it more efficient and portable.
“It is a great honor to receive this amazing recognition from FLC as one of the most impactful technology commercialization efforts led by the Department of Energy national laboratories,” said Pinaki Pal, a research scientist in Argonne’s Center for Advanced Propulsion and Power (CAPP), who led the effort for the laboratory. The Argonne research team also included a former postdoctoral appointee, Opeoluwa Owoyele.
The work remains of critical importance as current industry standards for design, which have long favored computer simulation over physical experimentation, remain remarkably slow.
“The ML-GA technology will enormously shrink industrial design/manufacturing cycles and costs associated with the development of advanced energy-efficient products with superior performance, durability, and lower environmental impact. This will, in turn, accelerate their market delivery and deployment,” Pal said. “These major benefits will have substantial economic as well as societal impacts in the United States.”
This time-saving method also brings down computational costs, allowing for more and better scientific experimentation.
“We are thrilled to now be honored at the national level by our peers through the FLC,” said Greg Halder, former scientist and current Innovation and Commercialization manager at Argonne. “This technology transfer was achieved rather quickly, moving from Argonne’s software discovery to commercial adoption in just a few years.”
The technology will radically change design: The difference between ML-GA and more traditional methods is that Argonne’s software learns more intelligently and robustly from significantly smaller datasets by combining multiple machine learning algorithms (within an automated “super learner” framework) and using an AI technique called active learning. These capabilities enable ML-GA to rapidly evaluate large design spaces in a data-efficient manner.
Scientists run simulations in small batches — called iterations — and train the Super Learner ML surrogate model on the simulation data. This surrogate model serves as a replacement for the simulation itself within a genetic algorithm optimization pipeline. The overall runtime is greatly reduced by this much faster surrogate model, which computes the objective functions very quickly.
ML-GA was recently licensed by Parallel Works, which was founded in 2015 by Michael Wilde, Matthew Shaxted and Michela Wilde.
The company has close ties to the laboratory: It leverages open source HPC workflow automation technology developed by the laboratory with UChicago and the University of Illinois. Michael Wilde, a former Argonne scientist, was on entrepreneurial leave from the laboratory during the formative-bootstrapping phases of Parallel Works.
“We are honored by this recognition of our collaboration with Argonne National Laboratory, which enables cutting-edge machine learning work to be focused on the science and engineering problems of American and global industry,” Wilde said. “We expect that commercial use will in turn provide benefits back to researchers in the national laboratory system as the technology is advanced and made easier to use.”
The company is also working with government and industry researchers to evaluate its use in oceanographic exploration, weather prediction and life science discovery.
“It is exciting to receive this prestigious award,” said Shaxted, president of the company. “We are grateful for the support of the DOE’s Technology Commercialization Fund which expedites the industry adoption of promising technologies born out of research within national laboratories, leading to economic growth.”
Suresh Sunderrajan, Argonne’s associate laboratory director for Advanced Energy Technologies, agrees.
“This second FLC award shows the significance of this achievement,” said Sunderrajan, “The enhanced ML-GA software is a great example of how Argonne works with industry to solve commercially-relevant problems.”
The winners of the 2022 FLC National Awards will be celebrated at an upcoming National Meeting to be held virtually on June 21-23.
The FLC was organized in 1974. More than 300 federal laboratories, facilities and research centers and their parent agencies make up the FLC community today.
The Office of Energy Efficiency and Renewable Energy’s (EERE) mission is to accelerate the research, development, demonstration, and deployment of technologies and solutions to equitably transition America to net-zero greenhouse gas emissions economy-wide by no later than 2050, and ensure the clean energy economy benefits all Americans, creating good paying jobs for the American people — especially workers and communities impacted by the energy transition and those historically underserved by the energy system and overburdened by pollution.
Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.
The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://energy.gov/science.
