A-Z Index | Phone Book | Careers
image10 copy

Metagenomic Clustering Powered by Supercomputers

Berkeley Lab and JGI researchers took one of the most popular clustering approaches in modern biology—Markov Clustering algorithm—and modified it to run efficiently and at scale on supercomputers at NERSC.


Power Grid Cybersecurity

An innovative R&D project led by Berkeley Lab researchers is combining cybersecurity, machine learning and commercially available power system sensor technology to better protect the electric power grid.

Screen Shot 2017 08 17 at 10.52.46 AM 1 1

Strongly-Lensed Supernovae

By controlling the effects of "micolensing" with HPCs, astrophysicists believe they'll find 1000 strongly lensed Type Ia supernovae in real-time from LSST data--20 times more than previously expected and help resolve a cosmological controversy.

cells slideCAM hp

“Minimalist Machine Learning” Algorithms

Berkeley Lab mathematicians have developed highly efficient neural networks for analyzing experimental scientific images from limited training data.