Topic: Data Science

The NNSA’s first exascale supercomputer, El Capitan, will have a peak performance of more than 1.5 exaflops (1.5 quintillion calculations per second) and an anticipated delivery in late 2022.

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

Alan Noun, a computer science student at CSU East Bay and the recipient of the Livermore Lab Foundation's first full-year scholarship, is an intern at LLNL’s Data Science Summer Institute.

Ryan Chen, LLNL data analyst and visualization technologist, has developed a model called the RDD Studio that provides a detailed simulation of an optimal response to a radiological dispersal device.

Simulation workflows for Arbitrary Lagrangian–Eulerian (ALE) methods are highly complex and often require a manual tuning process. There is an urgent need to semi-automate this process to reduce user burden and improve productivity. To address this need, we are developing novel predictive analytics for simulations and an in situ infrastructure for integration of analytics. Our ongoing goals are to predict simulation failures ahead of time and proactively avoid them as much as possible.

LLNL recently hosted its first-ever Data Science Challenge Workshop, a two-week crash course in what it’s like to work in data science, with students from UC Merced.

Brothers and Computation teammates Joe and Sam Eklund discuss their multi-hackathon project using Deep Voice 3.

Fred Streitz explains LLNL's work to exploit the relationship between simulation and experiments to build predictive codes.

As demonstrated by CASC computer scientists, LLNL's innovative data-driven machine learning techniques teach computers to solve real-world problems.

According to DOE secretary Rick Perry, "Accelerating artificial intelligence and machine learning is crucial to strengthening our country’s economic and national security."

LLNL’s Center for Applied Scientific Computing looks back at 2018 papers, presentations, and other activities recognizing research and innovation in data science.

For the 2nd straight year, LLNL's HPC Innovation Center hosted to a Women in Data Science (WiDS) regional event, drawing dozens of attendees from LLNL, local universities, and other Bay Area labs.

With nearly 100 publications, CASC researcher Jayaraman “Jay” Thiagarajan explores the possibilities of artificial intelligence and machine learning technologies.

Held in Washington, DC, the Earth System Grid Federation’s 8th annual face-to-face conference was a lively, fruitful affair.

LLNL employees attended a five-part “Deep Learning 101” course, which introduced the basics of neural networks and machine learning to anyone with a basic knowledge of programming in Python.

Highlights include CASC director Jeff Hittinger's vision for the center as well as recent work with PruneJuice DataRaceBench, Caliper, and SUNDIALS.

Rushil Anirudh describes the machine learning field as undergoing a “gold rush.”

AIMS (Analytics and Informatics Management Systems) develops integrated cyberinfrastructure for big climate data discovery, analytics, simulations, and knowledge innovation.

Marisa Torres, software developer with LLNL’s Global Security Computing Applications Division, combines her love of biology with coding.

Highlights include recent LDRD projects, Livermore Tomography Tools, our work with the open-source software community, fault recovery, and CEED.

Highlights include Computation’s annual external review, machine learning for ALE simulations, CFD modeling for low-carbon solutions, seismic modeling, and an in-line floating point compression tool.

SOAR (Stateless, One-pass Adaptive Refinement) is a view-dependent mesh refinement and rendering algorithm.

Highlights include the HYPRE library, recent data science efforts, the IDEALS project, and the latest on the Exascale Computing Project.

At just 5 years old, Marisol Gamboa, the oldest of six siblings to Mexican immigrants, decided she was definitely going to college.

LibRom is a library designed to facilitate Proper Orthogonal Decomposition (POD) based Reduced Order Modeling (ROM).