Topic: Data Science

In this year's Data Science Challenge with UC Merced, 21 students developed machine learning models capable of differentiating potentially explosive materials from other types of molecules.

News Item

Surrogate models supported by neural networks could lead to new insights in complicated physics problems such as inertial confinement fusion.

News Item

A team led by an LLNL computer scientist proposes a deep learning approach aimed at improving the reliability of classifier models for predicting disease types from diagnostic images.

News Item

LLNL scientists have taken a step forward in the design of future materials with improved performance by analyzing its microstructure using artificial intelligence.

News Item

To help accelerate discovery of therapeutic antibodies or antiviral drugs for SARS-CoV-2, LLNL has launched a searchable data portal to share its COVID-19 research with scientists and the public.

News Item

LLNL's Jay Thiagarajan joins the Data Skeptic podcast to discuss his recent paper "Calibrating Healthcare AI: Towards Reliable and Interpretable Deep Predictive Models." The episode runs 35:50.

News Item

An LLNL team developed ML tools that extract and structure information from the text and figures of nanomaterials articles using NLP, image analysis, computer vision, and visualization techniques.

News Item

In this video from the Stanford HPC Conference, Katie Lewis presents "The Incorporation of Machine Learning into Scientific Simulations at Lawrence Livermore National Laboratory."

News Item

LLNL researchers have identified an initial set of therapeutic antibody sequences, designed in a few weeks using machine learning and supercomputing, aimed at binding and neutralizing SARS-CoV-2.

News Item

On the Hidden in Plain Sight podcast, LLNL director Bill Goldstein explains how the Lab crunches data to shape the future.

News Item

Held in early March, the WiDS Livermore event featured four technical talks from LLNL data scientists.

News Item

The early-March event was the third annual WiDS Livermore event, featuring speakers, a career panel, mentoring, and a livestream.

News Item

LLNL has infrastructure, unique research capabilities, and a dedicated team of scientists and engineers supporting the fight against COVID-19.

News Item

LLNL scientists are contributing to the global fight against COVID-19 by combining AI/ML, bioinformatics, and supercomputing to help discover candidates for new antibodies and pharmaceutical drugs.

News Item

The university and LLNL lay the groundwork for a direct pipeline between the two, opening a door to research collaborations as well as job and internship opportunities for students and alumni.

News Item

Rafael Rivera-Soto is passionate about artificial intelligence, deep learning, and machine learning technologies. He works in LLNL’s Global Security Computing Applications Division, also known as GSCAD.

People Highlight

New year, new hackathon! The January 30–31 event was Computing’s 23rd hackathon and the 1st scheduled in the winter season.

News Item

Laser-fusion researchers have turned to machine-learning techniques to seek the combinations of laser pulse characteristics and target design needed to optimize target implosions for ICF.

News Item

A multi-institutional consortium aims to speed up the drug discovery pipeline by building predictive, data-driven pharmaceutical models.

News Item

More than 100 researchers from DOE national labs came to LLNL for the inaugural DOE Data Day workshop to discuss challenges and solutions in accessing, curating, and sharing data.

News Item

Livermore teams are applying innovative data analysis and interpretation techniques to advance fundamental science research.

News Item

LLNL researchers and colleagues are using machine learning as a virtual magnifying glass to study interesting regions of RAS protein/lipid simulations in higher detail.

News Item

ADAPD—Advanced Data Analytics for Proliferation Detection—integrates subject-matter expertise from the DOE’s national laboratories to create new capabilities for analyzing growing global data streams and traditional intelligence data, enabling early warning of nuclear proliferation activities.

Project

After years of preparation, LLNL’s upgraded Ares code runs a 98-billion-element simulation on 16,384 GPUs on the Sierra supercomputer.

News Item