Skip to main content

News

Berkeley Lab AI Learns Classic Physics to Scale Quantum Simulations

A multi-part technical diagram showing the architecture and function of the Sigma-Attention AI model. The left side shows a vertical flowchart titled "Encoder-only Transformer" with interconnected boxes labeled with AI processes like Multi-Head Attention and Feed Forward, leading to a final output labeled with a Sigma symbol. The top middle shows a chart titled "Dataset regime" that plots interaction strength against system size, shading three areas labeled MBPT for weak coupling, ED for intermediate coupling, and SCE for strong coupling. The top right features a line graph titled "Green's function prediction" displaying multiple U-shaped curves. Along the bottom, text reading "Generalizable self-energy learning across regime" sits next to a small, simple dot-and-line grid labeled "Small system." An arrow containing the AI model's Sigma symbol points from this small grid to a significantly larger grid labeled "Large system."

Mathematical Innovation Advances Complex Simulations for Science’s Toughest Problems

A two-part diagram illustrating a mathematical framework for simplifying complex models. The top diagram shows a V-shaped path of blue arrows enclosing a horizontal line that extends from a point labeled '0' towards an infinity symbol. Small circles along the line represent key numbers describing a system's dynamics. The blue path illustrates a calculation where orange and green segments at the far right can be ignored, allowing scientists to focus on the system's essential features for faster results. The bottom diagram shows a horizontal line with colored tick marks representing a random process visiting different states over time. Above the line, red brackets group larger sets of states into repeating loops, or cycles. Below the line, blue brackets highlight more specific cycles. This illustrates how analyzing these cycles can simplify and speed up complex simulations.

New AI Model Advances Long-Term, Multi-Scale Prediction of Complex Physical Systems

Four-panel visualizations for three different physical systems are arranged in three rows, labeled (a), (b), and (c). Each row corresponds to a specific system: (a) plasma turbulence (MHD), (b) fluid flow (Navier-Stokes), and (c) shallow-water dynamics. Within each row, the panels display (from left to right): the ground truth state, the StFT-F model prediction, the spatial distribution of prediction error (residual), and the predicted uncertainty. Colorbars beside each panel indicate the value ranges, with red and blue representing positive and negative values. The visualizations show that areas with higher errors generally coincide with regions of higher predicted uncertainty.

California Streamin’: Jefferson Lab, ESnet Achieve Coast-to-Coast Feed of Real-Time Physics Data

Map showing path of data from Virgina to Caifornia

Tropical Cyclones Intensifying Due to Warming Atmosphere

Tropical cyclones occurring near coastal areas are getting more intense, according to climate models. (Credit: NASA)

Science Highlight: Specialized Hardware Helps Researchers Quickly Process Sparse Matrices

The ASA architecture can be used to accelerate sparse accumulation for GraphBLAS to deliver much faster performance and energy efficiency for those operations.

Gravitational Form Factors Illuminate Substructure of the Proton

For the first time, researchers have a better understanding of how gluons (left side) and quarks (right side) form the substructure of protons and other hadrons. (Credit: Kent Leech for Lawrence Berkeley National Laboratory, Creative Services Office)

Science Highlight: Perlmutter Supports CO2 Fixation for Carbon-Negative Building Materials

Locking greenhouse gases into carbon nanofibers (CNFs) could turn buildings into carbon-storage devices.

Simulating Plasma, NERSC Systems Enable Efficient Microchip Production

Machine Learning Yields More Efficient Hydrogen Combustion Reactivity Modeling

Cori and Perlmutter Support New Understanding of Reaction Behind Salt-Based Nuclear Reactors

A simulation snapshot of a typical structure of ZnCl3•2, showing the metal ion in red and the Cl– ions in white

Perlmutter Supports First Gravitational Lensing System Modeled on GPUs

On the left, a white square delineates a set of illuminated objects in space: four white lights in a cross shape surrounding a central yellow light. On the right, a magnified inset image of the same image.
Computing Sciences logo

Connect

Our Organization