$19.4M for an 'AI oracle' to solve complex physics problems
U-M leads new DOE-funded computational center focused on next-generation hypersonic flight
University of Michigan
How much faster could engineering progress with an artificial intelligence oracle that could answer any physics question?
Such a machine is the big picture aim of the newly formed Center for Prediction, Reasoning and Intelligence for Multiphysics Exploration, or C-PRIME, led by the University of Michigan and funded by the U.S. Department of Energy's National Nuclear Security Administration.
While physics is governed by many known equations, it’s hard to get from those equations to answers about how real-world objects will behave—for instance, the swirls of fuel and air inside a complex engine or the precise wind resistance over the surface of a vehicle. In theory, it’s all knowable, building up from the molecular level, but the calculations are too big to actually perform.
While an AI approach can't attack that problem directly, an AI agent could build physics models based on known equations that it uses to generate trustworthy data. It could then use that data to produce simplified yet accurate models for specific physics problems, which would feed into engineering design of complex devices.
"The notion is that we, as humans, should provide certain concepts we trust—Newton's laws or E=mc^2. The machine then composes more complex ideas from these basic building blocks," said Venkat Raman, director of C-PRIME and the James Arthur Nicholls Collegiate Professor of Engineering.
"Because we trust these building blocks, we can—to a large extent—trust engineering concepts that are composed from them."
However, formally establishing this trust, known as verification and validation, is in itself a complex challenge, which is at the core of the project. The sequences of simulations designed by the AI agents will run on some of the world's largest supercomputers to discover the inner workings of propulsion systems behind hypersonic flight—five times faster than the speed of sound. The team will focus on rotating detonation combustors, which are becoming a critical technology for hypersonic flight.
Rotating detonation combustors can be used for propulsion—in rockets, air-breathing engines or satellite thrusters—or energy conversion, such as in gas turbines that generate electricity. They have the potential to be very efficient, roughly 25% better than conventional combustion, but maintaining their burn is a nuanced endeavor. A series of explosions run around a ring, and the resulting shockwave compresses and ignites the fuel-air mixture at each fuel injection point in sequence.
"AI and hypersonics are critical to national security and U.S. scientific leadership, and we're committed to developing technologies and talent to move both fields forward," said Karen A. Thole, the Robert J. Vlasic Dean of Engineering. "This federal investment enables our researchers to bring together expertise in physics, computer simulation, AI and machine learning to push the boundaries of what's possible and develop tomorrow's AI-savvy workforce in the process."
Student researchers on the project will draw on the University of Michigan’s Ph.D. in Scientific Computing—the nation’s first, established in 1988—administered by the Michigan Institute for Computational Discovery and Engineering, or MICDE.
The project is divided into five research thrusts:
Physics and data: This effort covers foundational physics, developing models and honing them with experiments that fill holes in the existing data, with a focus on how materials mix and react. Led by Eric Johnsen, center co-director, professor of mechanical engineering and director of the scientific computing Ph.D. program.
Verification, validation and uncertainty quantification: With the goal of ensuring the accuracy and reliability of the computer models, this thrust digs into how assumptions and simplifications in the physics models affect predictions. Led by Alex Gorodetsky, associate professor of aerospace engineering.
Exascale supercomputing architecture: This effort optimizes the models to take full advantage of powerful supercomputers and lays groundwork for building next-generation supercomputers optimized for AI. Led by Reetuparna Das, professor of computer science and engineering.
Machine learning: This team will develop machine-learning-based tools that will accelerate computation of complex physics, using data generated by autonomously acting AI agents. Led by Karthik Duraisamy, professor of aerospace engineering and director of MICDE.
AI-based integration: Based on "physics composition"—the formal approach for integrating different physics equations—this team will build the AI agents responsible for coding and simulation. Raman leads this thrust.
In addition, specially designed laboratory experiments will test the accuracy of the AI-based combustor design, to be conducted at U-M by Mirko Gamba, professor of aerospace engineering, and Carolyn Kuranz, professor of nuclear engineering and radiological sciences.
"Through our research, and the education of the next generation of researchers, we have the opportunity to shape the field on a large scale," Johnsen said. "In particular, we need to ensure that our trainees—undergraduate and graduate students and postdoctoral researchers—understand how to leverage AI resources in their research because their success after they leave Michigan will depend on how well they do this."
David Etim, federal program manager in the National Nuclear Security Administration's Office of Advanced Simulation and Computing and Institutional Research & Development, spoke highly of the new center, which is part of the fourth phase of NNSA's Predictive Science Academic Alliance Program.
"This center with its focus on AI-driven solutions for complex physics problems aligns perfectly with PSAAP's mission to advance high-fidelity predictive simulations," Etim said. "We eagerly anticipate the groundbreaking contributions C-PRIME will make in areas critical to national security, particularly in next-generation hypersonic flight and exascale computing, further strengthening the program's impact."
C-PRIME builds on U-M's prominent leadership in computational science and engineering, which is anchored by MICDE. U-M is also home to a $15 million Strategic Partnership and Accelerated Research Collaboration with Los Alamos National Lab, which is coordinated by MICDE and brings together Los Alamos staff scientists and U-M researchers. Additionally, the university is partnering with LANL on a $1.25 billion facility for high-performance computing and AI research in Michigan.
C-PRIME includes a total of 13 co-investigators from U-M across four departments, as well as a co-investigator from Princeton University. Researchers at Sandia, Los Alamos and Lawrence Livermore national laboratories will be collaborating with the center.
Raman is also a professor of aerospace engineering and mechanical engineering. Thole is also a professor of mechanical engineering and aerospace engineering. Duraisamy is also a professor of mechanical engineering and nuclear engineering and radiological sciences.
AI turns printer into a partner in tissue engineering
University Medical Center Utrecht
image:
Sammy Florczak and Riccardo Levato in the volumetric printing lab.
view moreCredit: Ivar Pel/UMC Utrecht
Organ donors can save lives, for example those of patients with kidney failure. Unfortunately, there are too few donors, and the waiting lists are long. 3D bioprinting of (parts of) organs may offer a solution to this shortage in the future. But printing living tissues, bioprinting, is extremely complex and challenging.
The team of Riccardo Levato at UMC Utrecht and Utrecht University is now taking an important step toward printing implantable tissues. Using computer vision, a branch of artificial intelligence (AI), they’ve developed a 3D printer that doesn’t just print, it also sees and even co-designs. Their innovation was published today in Nature. With this innovation, they tackle one of the biggest challenges in 3D bioprinting: improving both the survival and functionality of cells in printed living tissue. But how exactly does that work?
We usually associate 3D printing with building structures layer by layer. But there are other forms, such as volumetric bioprinting. This technique creates a complete structure in a single step, using a light-sensitive gel that solidifies when exposed to cell-friendly laser light. The advantage? It is incredibly fast, taking just seconds, and much gentler on living cells. To produce a high-quality print, it is crucial to understand what’s inside the printing material, so that the printed object is built as optimal as possible. The new technology, called GRACE, makes that possible. It opens up new possibilities for bioprinting functional tissues, and brings us closer to repairing tissues, testing new drugs, and even replacing entire organs.
Why do we need GRACE?
What is 3D-bioprinting?
In 3D bioprinting, researchers use living cells to create functional tissues and organs. Instead of printing with plastic, they print with living cells. This comes with great challenges. Cells are fragile and wouldn’t survive a regular 3D printing process. That’s why Riccardo Levato’s team developed a special bio-ink, a mix of living cells and nourishing gels that protect the cells during the printing process.
Volumetric bioprinting
With the advancements in bio-inks, layer-by-layer 3D bioprinting became possible. But this method is still time-consuming and puts a lot of stress on the cells. Researchers from Utrecht came up with a solution: volumetric bioprinting.
Volumetric bioprinting is faster and gentler on cells. Using cell friendly laser light, a 3D structure is created all at once. “To build a structure, we project a series of light patterns into a spinning tube filled with light-sensitive gel and cells,” Riccardo Levato explains. “Where the light beams converge, the material solidifies. This creates a full 3D object in one go, without having to touch the cells.” To do this, it is crucial to know exactly where the cells are in the gel. GRACE now makes that possible.
Innovating with laser light
Sammy Florczak, a PhD student in Riccardo’s lab, worked on the development of GRACE, short for Generative, Adaptive, Context-Aware 3D printing. He built a new device in a specialized lab, using advanced laser technologies. Before entering, a red light signaling “LASER” shows whether it’s safe to go in. Laser light plays a crucial role, not just in the printing step, but also in the added imaging step that sets this new technology apart. GRACE combines volumetric bioprinting with this advanced laser-based light-sheet imaging. But what can we do with that?
Smart blood vessels around living cells
One of the biggest challenges in 3D bioprinting is creating functional blood vessels. Blood vessels are essential to provide oxygen and nutrients to the cells, and thus printing these blood vessels at the correct place is key to creating viable tissues. Yet, in conventional printing methods, a 3D design is made before knowing where the cells are located in the light sensitive gel and thus where the blood vessels must be printed. With GRACE, the printer ‘sees’ where the cells are located and, within seconds, designs a network of blood vessels around those cells as effectively as possible.
From blueprint to customization
“In the past, printing always depended on the designer’s blueprint. Now, GRACE contributes to the design itself,” Sammy explains. “The printer ‘sees’ what kind of cells are in the material, and where they are. Then, using AI tools, it creates a matching design for the object to be printed. This new printer essentially has its own ‘eyes’ – the laser-based imaging- and ‘brain’ – the new AI software. That level of customization leads to tissues that survive and function better.”
More than just blood vessels
GRACE can do more than create adaptive blood vessels networks. The technology can also align multiple printing steps automatically. Take a piece of printed bone tissue, for example, that later needs a layer of cartilage added. Normally, that is a complex process with a lot of manual work. GRACE scans the existing tissue and automatically designs and prints a second layer that fits perfectly on top. All at the high printing speed of volumetric bioprinting, creating cm3-sized objects within seconds.
Automatically correcting for obstacles
Another challenge in bioprinting is that light can sometimes be blocked, for example by previously printed parts of the structure. This can create shadows and flaws in the final product. GRACE can solve this too. By scanning the surface of any obstacles, the system automatically adjusts the light projection. This makes the print more precise and consistent. Moreover, this allows pre-made objects to be inserted into the printing vial. Think for example of a stent in which you could print blood vessel cells or objects that can release medicines.
Just the beginning
Bioprinting is highly promising, but significant work is still needed to translate this technology to the clinic. Riccardo underlines that further research is needed to determine how printed cells can mature to replicate the functionality of native tissues. Even considering the challenges ahead, Riccardo is not afraid to dream big. “This first work on GRACE is just the beginning. We are now working on increasing the amount of cells that can be printed, so that other tissues like heart and liver can also be printed. Moreover, we would like to make this technique openly accessible to other labs, so other could apply it to their printing method.”
https://www.youtube.com/watch?v=hA0zzosxMy4&t=5s
Journal
Nature
Article Title
Adaptive and context-aware volumetric printing
Article Publication Date
3-Sep-2025
No comments:
Post a Comment