High Performance Computing for Energy Innovation

In partnership with industry, leveraging world-class computational resources to advance the national energy agenda.

Don't Miss This Upcoming Event

HPC4 Energy Innovation Online Colloquium:
Machine Learning

Friday, March 22, 2019 9:00 am, PST

   Register Now

Our Programs

Solving challenges using HPC modeling using HPC modeling, simulation, and data analysis. Outcomes range from improved product quality to acceleration or elimination of product testing.

Visit Site

Accelerating the discovery and adoption of new materials that operate in extreme conditions for energy applications. Examples range from high-temperature, corrosion-resistant metals to new catalysts for hydrogen production.

Visit Site

Speeding up the discovery, design, and development of energy efficient mobility systems. Resulting impacts on transportation include reduced energy consumption, lowered costs, and improved accessibility.

Visit Site

How the HPC4 Program Works for Demonstration Projects

Program Basics and Cost Sharing

The program pays labs up to $300K for industry access to HPC resources and expertise; industry pays at least 20% of project costs (cash or in-kind).

Concept Submissions

During a semiannual solicitation process, companies may submit two-page concept papers describing ideas for projects of up to one year duration.


Lab Principal Investigator

If a concept is accepted, a lab principal investigator is assigned to help the company develop a full proposal.


Selection Criteria

  • Advancing the state of the art
  • Technical feasibility and strength of team
  • Industry impact
  • Need for HPC systems


Signed Agreement

Following proposal approval, DOE provides the company with a short-form cooperative research and development agreement (CRADA) to initiate the project.




Participating Labs


Projects Awarded

$22 million

Funds Invested

650 million

Computer Core Hours

Success Stories

Next-Generation LEDs

Livermore is working with light-emitting-diode (LED) manufacturer SORAA to create a new computer model of the company’s research-scale process for growing gallium nitride (GaN) crystals.

Read More

Energy Efficiency in Paper Processing

Agenda 2020 partnered with Lawrence Livermore and Lawrence Berkeley national laboratories to optimize one of the most energy-intensive steps in the papermaking process—drying the wet paper pulp. 

Read More

Partner Labs

Argonne National Laboratory Berkeley National Laboratory Lawrence Livermore National Laboratory
Los Almos National Laboratory Oak Ridge National Laboratory Pacific Northwest National Laboratory
National Renewable Energy Laboratory National Energy Technology Laboratory Sandia National Laboratory

Contact Us

For additional information on the HPC4 Energy Innovation Program, email hpc4ei@llnl.gov.


Subscribe to Our Mailing List

hpc4ei-info (hpc4ei-info@llnl.gov)
Action: Subscribe   Unsubscribe

Online Colloquium: Machine Learning

Friday, March 22, 2019

9:00 am, Pacific Daylight Time (San Francisco, GMT-07:00)
12:00 pm, Eastern Daylight Time (New York, GMT-04:00)
11:00 am, Central Daylight Time (Chicago, GMT-05:00)

Machine Learning tools are accelerating in their sophistication and utility. Industry is utilizing and incorporating these tools to enhance product and process optimization, real time process control and material discovery.

This online colloquium is designed to introduce machine learning concepts; show examples of applications of machine learning tools; and discuss potential pitfalls in applying these tools. HPC4EnergyInnovation Program is currently executing projects that combine machine learning tools with physics-based simulation tools and/or sensor-based data for both process and product enhancement.

View Agenda

Register Now

Speaker Bios

Robin Miles photoRobin Miles
Lawrence Livermore National Laboratory

"HPC4EnergyInnovation Program Overview: National Laboratories Partner with U.S. Manufacturers to Increase Innovation and Energy Efficiency"

Robin Miles is the High Performance Computing for Energy Innovation (HPC4EI) Director. Robin earned a B.S. in mechanical engineering from the Massachusetts Institute of Technology, a M.S. in mechanical engineering from Stanford University, and a M.B.A. from the University of California at Berkeley. Robin started working at Lawrence Livermore National Laboratory (LLNL) after working at several Silicon Valley start-up companies such as Redwood Microsystems and K2 Optronics where she led product development teams. At LLNL Robin developed micro-fluidic-based instrumentation for the chemical and biological detection programs. She was also involved in building targets for fusion experiments and led the team working on target manufacture and delivery for concept fusion electric plants. She is currently the Deputy Division Leader for LLNL’s National Security Engineering Division (NSED) and was formerly the HPC4Manufacturing and HPC4Materials project manager. She is the author of several patents and publications.

David Womble photoDavid Womble, Ph.D.
Oak Ridge National Laboratory

“Motivation for Machine Learning in Product and Process Development”

David Womble is currently the Director of Artificial Intelligence Programs at Oak Ridge National Laboratory (ORNL). Before joining ORNL in 2017, David spent thirty years at Sandia National Laboratory in both management and technical roles. As a manager, David served as the Program Deputy for Advanced Simulation and Computing (ASC), responsible for developing and deploying modeling and simulation capabilities, including hardware and software, in support of Sandia nuclear weapons program. David also served as the senior manager for the Computational Simulation Group and for the Computer Science and Mathematics Group. David earned his Ph.D. in Applied Mathematics and M.S. in Electrical Engineering at Georgia Tech in 1986. He also earned a B.S. in Mathematics and Computer Science from Rose-Hulman Institute of Technology in 1982. His technical interests include high performance computing with contributions in numerical mathematics, linear solvers, scalable algorithms and I/O. He established the Computer Science Research Institute currently located in Sandia Science and Technology Park and led Sandia’s seismic imaging project in DOE’s Advanced Computational Technologies Initiative. David has also worked closely with Energy Efficiency & Renewable Energy’s Atmosphere to Electrons Program for the past two years. His recognitions include two R&D100 awards and the Gordon Bell Award in high performance computing.

Brenda Ng photoBrenda Ng, Ph.D.
Lawrence Livermore National Laboratory

“What Can Deep Learning Do For You?”

Brenda is the Machine Learning Group Leader in the Computational Engineering Division of Lawrence Livermore National Laboratory. All her projects to date are tied to a single theme: how do we exploit our knowledge and sensing capabilities to take optimal actions in a world plagued with uncertainty. Her research interests include machine learning, uncertainty quantification, and decision-making under uncertainty. Currently, she is involved in various machine learning projects that apply deep learning for multimodal data fusion in intelligence retrieval and healthcare prediction, and design of experiments for physics-based simulation studies. Brenda received her Ph.D. in computer science from Harvard with specialization in artificial intelligence.


Dongwon Shin photoDongwon Shin, Ph.D.
Oak Ridge National Laboratory

“Modern Data Analytics Approach to Predict Creep of High-Temperature Alloys”

Dongwon Shin is a research and development staff member at Oak Ridge National Laboratory (ORNL). He received his Ph.D. from the Pennsylvania State University in 2007 and spent two years at Northwestern University as a post-doc before joining ORNL. His research expertise is computational thermodynamics (widely known as CALPHAD) and first-principles calculations based density functional theory, and recently became interested in modern data analytics and supercomputing for the design of high-temperature alloys.

Tess Smidt photoTess Smidt, Ph.D.
Lawrence Berkeley National Laboratory

“Machine Learning for Material Property Design at the Atomic Level”

Tess Smidt is the 2018 Alvarez Fellow in Computing Sciences. Her current research interests include intelligent computational materials discovery and deep learning for atomic systems. She is currently designing algorithms that can propose new hypothetical atomic structures.

Tess earned her PhD in physics from UC Berkeley in 2018 working with Professor Jeff Neaton. As a graduate student, she used quantum mechanical calculations to understand and systematically design the geometry and corresponding electronic properties of atomic systems. She's helped discover two new crystal classes and designed an automated computational workflow for identifying ferroelectric materials.

During her PhD, Tess spent a year as an intern on Google’s Accelerated Science Team where she developed a new type of convolutional neural network, called Tensor Field Networks, that can naturally handle 3D geometry and properties of physical systems.

Victor Castillo photoVictor Castillo, Ph.D.
Lawrence Livermore National Laboratory

“Machine Learning for Better Understanding and Control of Complex Processes”

Victor is a scientist and former group leader in the Computational Engineering Division at Lawrence Livermore National Laboratory with a background in Computational Physics, Machine Learning, and System Dynamics and over 30 years of experience in industry and government research. He is passionate about using computers – from low-power embedded systems to world-class supercomputers – to solve problems. Victor received a Ph.D. in Engineering, Applied Science from University of California at Davis. His current work at LLNL includes simulation modeling and analysis, development of fluid dynamics applications, and enterprise modeling. Victor was also honored with the national 2013 Community Service award from Great Minds in STEM.


Brian Valentine photoBrian Valentine, Ph.D.
Department of Energy, Energy Efficiency and Renewable Energy, Advanced Manufacturing Office

“Error Analysis of System Modeling using Artificial Intelligence and Machine Learning”

Brian G Valentine, Ph.D. PE is a technical research manager within the US Department of Energy’s Office of Energy Efficiency and Renewable Energy (EERE), and part-time faculty member at the Office of Advanced Engineering Education at the University of Maryland at College Park. Brian has worked for EERE for over thirty years, as technology manager for the Solar Thermal Technology program, the Advanced Manufacturing program, and as consultant to DOE’s Office of Basic Energy Sciences for applied engineering science. Brian worked for the US Government’s Iraq reconstruction mission from 2003 through 2006. Brian is a Bachelor of Science in Physics and Chemistry from Siena College, a PhD of Engineering from the Rensselaer Polytechnic Institute, and a registered professional engineer in Virginia.

Turab Lookman photoTurab Lookman, Ph.D.
Los Alamos National Laboratory

“Accelerated Search for Materials with Targeted Properties”

Turab Lookman is a Laboratory Fellow (2018), Fellow of the American Physical Society (2012), recipient of the Japan Society for the Promotion of Science (JSPS) award in 2010, and the Los Alamos National Laboratory (LANL) Fellows prize for Outstanding Research in Science or Engineering in 2009. He recently led an Laborary Directed Research and Development - Directed Research (LDRD-DR) effort at LANL on Information driven approaches to materials design. His interests span the study of hard and soft structural and functional materials, and aspects of applied mathematics and computation.