Machine learning (ML) is revolutionizing scientific applications—developing new drugs, understanding cancer, creating fusion energy, inventing smart materials, and more.

At LLNL, ML has permeated virtually all aspects of our research. Our teams develop, adapt, and apply the latest advances to some of the most complex problems while using the some of the world’s most powerful supercomputers and advanced experiments.

Whether the need is representation learning to bridge the gap between computational models and large-scale experiments, computer vision and inverse problems to understand everything from satellite imagers to airport security scans, or fundamental research on ML safety and interpretability to promote trust and understanding, our unique research environment couples fundamental ML research with high-impact scientific endeavors.

Multidisciplinary teams working closely together are pushing the limits of what is considered possible. Driven by some of society’s most important challenges and enabled by ML, the future of large-scale science is happening first at LLNL.

teal lines adorned with multicolored dots extending upward from a single point, all on a black background

Can We Trust LLMs?

In two papers from the 2024 International Conference on Machine Learning, Livermore researchers investigate how LLMs perform under measurable scrutiny.

four people at computer workstations in a dark blue server room

Model Failure and Resiliency

A paper from the 2024 International Conference on Machine Learning investigates how likely AI/ML models are to be inaccurate.

shield icon with a lock icon on an abstract blue background with rays of lines fanning out from the bottom of the shield

AI/ML Model Robustness

LLNL researchers study model robustness in a paper accepted to the 2024 International Conference on Machine Learning.

three panels showing scale up from nano to macro

Surprising Places You'll Find ML

Researchers explain why water filtration, wildfires, and carbon capture are becoming more solvable thanks to groundbreaking data science methodologies.

two people look on as a third tries a VR headset

DOE & LLNL at Inaugural AI Expo

The Special Competitive Studies Project's AI Expo showcased groundbreaking initiatives in AI and emerging technologies.

composite image of supercomputer, NIF structure, and shot images

HPC, AI, CogSim, and Fusion Ignition

The “crystal ball” that provided increased pre-shot confidence in a breakthrough involved a combination of methods combining physics-based simulation with ML.