Topic: Scientific ML

LLNL researchers collaborated with Washington University in St. Louis to devise a state-of-the-art, machine learning ML–based reconstruction tool for when high-quality computed tomography data is in low supply.

Merlin is an open-source workflow orchestration and coordination tool that makes it easy to build, run, and process large-scale workflows.

Using explainable artificial intelligence techniques can help increase the reach of machine learning applications in materials science, making the process of designing new materials much more efficient.

This issue highlights some of CASC’s contributions to making controlled laboratory fusion possible at the National Ignition Facility.

The “crystal ball” that provided increased pre-shot confidence in LLNL's fusion ignition breakthrough involved a combination of detailed HPC design and a suite of methods combining physics-based simulation with machine learning—called cognitive simulation, or CogSim.

The report lays out a comprehensive vision for the DOE Office of Science and NNSA to expand their work in scientific use of AI by building on existing strengths in world-leading high performance computing systems and data infrastructure.

The addition of the spatial data flow accelerator into LLNL’s Livermore Computing Center is part of an effort to upgrade the Lab’s cognitive simulation (CogSim) program.

Open-source software has played a key role in paving the way for LLNL's ignition breakthrough, and will continue to help push the field forward.

A principal investigator at LLNL shares how machine learning on the world’s fastest systems catalyzed the lab’s breakthrough.

Adding machine learning and other artificial intelligence methods to the feedback cycle of experimentation and computer modeling can accelerate scientific discovery.

High performance computing was key to the December 5 breakthrough at the National Ignition Facility.

Two supercomputers powered the research of hundreds of scientists at Livermore’s NNSA National Ignition Facility, which recently achieved ignition.

The award recognizes progress in the team's ML-based approach to modeling ICF experiments, which has led to the creation of faster and more accurate models of ICF implosions.

The Adaptive Computing Environment and Simulations (ACES) project will advance fissile materials production models and reduce risk of nuclear proliferation.

LLNL held its first-ever Machine Learning for Industry Forum (ML4I) on August 10–12, co-hosted by the Lab’s High-Performance Computing Innovation Center and Data Science Institute.

New research debuting at ICLR 2021 demonstrates a learning-by-compressing approach to deep learning that outperforms traditional methods without sacrificing accuracy.

The ATOM consortium, of which LLNL is part, announced the DOE’s Argonne, Brookhaven, and Oak Ridge national labs are joining the consortium to develop ATOM’s AI-driven drug discovery platform.

Three papers address feature importance estimation under distribution shifts, attribute-guided adversarial training, and uncertainty matching in graph neural networks.

Lawrence Livermore National Lab has named Stefanie Guenther as Computing’s fourth Sidney Fernbach Postdoctoral Fellow in the Computing Sciences. This highly competitive fellowship is named after LLNL’s former Director of Computation and is awarded to exceptional candidates who demonstrate the potential for significant achievements in computational mathematics, computer science, data science, or scientific computing.

Highlights include perspectives on machine learning and artificial intelligence in science, data driven models, autonomous vehicle operations, and the OpenMP standard 5.0.