The Department of Energy's Lawrence Berkeley National Laboratory (Berkeley Lab) is at the forefront of a global shift in how science gets done-one driven by artificial intelligence, automation, and powerful data systems. By integrating these tools, researchers are transforming the speed and scale of discovery across disciplines, from energy to materials science to particle physics.
This integrated approach is not just advancing research at Berkeley Lab-it's strengthening the nation's scientific enterprise. By pioneering AI-enabled discovery platforms and sharing them across the research community, Berkeley Lab is helping the U.S. compete in the global race for innovation, delivering the tools and insights needed to solve some of the world's most pressing challenges.
From accelerating materials discovery to optimizing beamlines and more, here are four ways Berkeley Lab is using AI to make research faster, smarter, and more impactful.
Automating Discovery: AI and Robotics for Materials Innovation
At the heart of materials science is a time-consuming process: formulating, synthesizing, and testing thousands of potential compounds. AI is helping Berkeley Lab speed that up-dramatically.
A-Lab
At Berkeley Lab's automated materials facility, A-Lab, AI algorithms propose new compounds, and robots prepare and test them. This tight loop between machine intelligence and automation drastically shortens the time it takes to validate materials for use in technologies like batteries and electronics.
Autobot
Exploratory tools like Autobot, a robotic system at the Molecular Foundry, are being used to investigate new materials for applications ranging from energy to quantum computing, making lab work faster and more flexible.
Smarter Instruments: AI for Real-Time Optimization
Running advanced research facilities-like accelerators and light sources-requires extreme precision. AI is helping tune instruments at Berkeley Lab on the fly, making them more stable, efficient, and productive.
The Berkeley Lab Laser Accelerator (BELLA)
Machine learning models are used at BELLA to optimize and stabilize laser and electron beams, improving performance and reducing manual calibration time, improvements that provide new opportunities for scientific and industrial applications.
The Advanced Light Source Upgrade (ALS-U)
At the ALS, deep-learning AI-based controls are being applied to synchrotron operations to help optimize beam performance. These techniques will be implemented in the upcoming ALS-U, which will provide one of the world's brightest soft x-ray sources, serving American industry and researchers.
Speeding Up Data: Automated Analysis
Modern science generates enormous amounts of data. At Berkeley Lab, AI, automation, and machine learning help analyze this data faster-sometimes in real time-allowing scientists to adjust experiments on the fly and produce useful findings quicker than before.
Supercomputing for On-Demand Insights
Data from light sources, microscopes, and telescopes streams to Berkeley Lab's supercomputing facilities, where it can be processed almost instantly. At the Molecular Foundry's National Center for Electron Microscopy a new, web-based platform called Distiller streams data collected from the microscope directly to the Perlmutter supercomputer at the National Energy Research Scientific Computing Center (NERSC) where it's analyzed within minutes, allowing researchers to refine the experiment while it's still in progress. This new capability enables real-time decision-making during experiments, saving time and money, and has potential for broad applications in many fields of science.
Fusion Research
At NERSC, machine learning is being used to predict particle behavior in fusion plasmas, with the potential to inform live control systems for future fusion reactors.
AI for Network Optimization at ESnet
Berkeley Lab's high-performance network, ESnet, is using AI to predict and troubleshoot network traffic, ensuring seamless, high-speed collaboration across national labs and research partners. As the use of enormous data sets grows, driven by AI, ESnet is improving system innovation to support the future of data-intensive collaborations on a scale we have not seen before.
Generating Breakthroughs: AI as Co-Creator
Probing AI Predictions
AI isn't just an accelerator-it's a collaborator. Berkeley Lab scientists also help validate and critique AI-driven discoveries from beyond the Lab. Recently, medical researchers designed a novel enzyme using AI. To investigate the accuracy of that design, they turned to the Advanced Light Source, where our scientists examined a sample to bridge the gap between the AI prediction and reality. This new approach could speed the development of novel proteins for almost anything, including applications in medical, energy, and other industries.
AI Embedded in the Future of Science
These innovations are part of a growing shift in how we think about the ways we do science. From experimental design to analysis and operations, AI is helping teams at Berkeley Lab do more with less, enabling researchers to focus on discovery while machines handle repetitive tasks, real-time analysis of massive data sets, and more. By integrating AI with robotics, instrumentation, and data systems, Berkeley Lab is building a smarter, faster scientific infrastructure that's ready to solve tomorrow's biggest challenges.
The ALS, NERSC, ESnet, and the Molecular Foundry are DOE Office of Science user facilities.
