UVA researchers use AI to simulate extreme physics events in seconds

University of Virginia researchers are using artificial intelligence to analyze extreme physics events—from rocket explosions to airbag deployments—that are too rare, dangerous, or fast to study with traditional methods. Led by associate professor Stephen Baek, the research team has developed AI algorithms that can predict these high-stakes phenomena in seconds on a laptop, replacing supercomputer simulations that previously took days to complete.

The core challenge: Traditional machine learning excels at finding patterns in large datasets but struggles with rare, extreme events that are statistical outliers yet critical for safety and performance.

• “If I predict tomorrow will be sunny, I’ll be right 99% of the time,” Baek explained. “But I’ll miss the tornado.”
• These extreme physics events include rocket fuel explosions, baseball pitcher arm torque, car airbag reliability, and hypersonic flight conditions.

How it works: The AI models compensate for limited data by building algorithms that respect the laws of physics and can predict unpredictable events.

• The team has developed algorithms that can predict extreme phenomena like energetic material initiation or hypersonic airflow in seconds on a GPU-enabled laptop.
• Previously, such predictions required days of processing time on supercomputers.

Real-world applications: The technology spans multiple industries where extreme conditions must be precisely understood and controlled.

• Automotive safety: Car airbag explosive charges must reliably detonate during crashes but remain stable under heat, cold, and moisture conditions.
• Sports science: Teams create digital “twins” of elite athletes like Shohei Ohtani and Aaron Judge to optimize performance and prevent injuries through biomechanical simulations.
• Aerospace: Engineers use the models for rocket design and controlled blast applications where materials must be stable during transport but responsive when triggered.

Material discovery breakthrough: AI is accelerating the development of new materials that don’t yet exist through rapid simulation and testing.

• Pharmaceutical companies run AI simulations to combine molecules and test potential treatments.
• Manufacturers like 3M and DuPont apply similar techniques to design new composites and polymers.
• “We’re seeing the discovery cycle for new materials shrink dramatically,” Baek said. “AI is shortening the runway from idea to product.”

What they’re saying: Baek believes this represents just the beginning of AI’s impact on extreme physics research.

• “In many cases, you simply cannot run the experiment in real life. It’s too dangerous, too expensive or too fast to capture. AI simulations give us that window.”
• “Ten years from now, I think we’ll look back and realize how much of the world around us was shaped by AI-assisted extreme physics.”

The big picture: The research demonstrates how AI can make the impossible routine by enabling scientists to study phenomena that were previously too dangerous or expensive to investigate, potentially transforming industries from aerospace to medicine over the next decade.