High-energy-density (HED) science lets us understand the universe and new states of matter, and may be the key to virtually unlimited clean energy. ML researchers at CASC are combining some of the most sophisticated computational models, largest supercomputers, and leading-edge experimental data to create a unified framework of HED science.

We leverage the latest developments in representation learning, multimodal forward and inverse modeling, and human interpretable analysis. Join us in the quest for new discoveries in astrophysics, fusion, plasma physics, dynamic materials, and more. Learn more about an openĀ postdoc research position on a HED science project.

latent space error graphed

Topological Data Analysis

We evaluate data-driven models in scientific applications such as HED physics and computational biology.

unlabeled bar chart showing four colors

Parallelizing Training of DNNs

A novel tournament method trains traditional and generative adversarial networks for inertial confinement fusion.

composite image of NIF target bay and supercomputer

DL-Based Surrogate Models

Surrogate models supported by neural networks could lead to new insights in complicated physics problems.

Harsh Bhatia

Meet a Data Viz Expert

Harsh Bhatia, PhD, was a Lawrence Graduate Scholar and an LLNL postdoctoral researcher before joining CASC full time in 2017.