April 2, 2026 — As advanced discovery tools flood U.S. Department of Energy (DOE) laboratories with data, scientists are facing a critical challenge: Humans can’t keep up with the sheer volume and speed of information being generated.
Tao Zhou of the CNM explains the capabilities of the 26-ID beamline, jointly operated by CNM and the APS. Image credit: Mark Lopez/Argonne National Laboratory.
Modern X‑ray, microscopy and neutron facilities produce vast streams of high‑value imagery, yet tools to interpret this data at scale have not kept pace. Researchers are increasingly turning to artificial intelligence (AI) to rapidly turn these massive datasets into usable insight.
As part of DOE’s Genesis Mission, a historic national effort to transform American science and innovation through the power of AI, DOE’s Argonne National Laboratory is contributing to several important projects that will strengthen U.S. technological leadership and global competitiveness.
One of those projects is the Synergistic Neutron and Photon Science – Intelligence (SYNAPS-I) AI platform, which will integrate data from neutron, X-ray and microscopy experiments across national labs into a single model. This model will analyze information across scales and accelerate understanding of complex systems in real time.
The SYNAPS-I project is led by Alexander Hexemer, senior scientist at DOE’s Lawrence Berkeley National Laboratory (LBNL). The project also includes members from these DOE national laboratories: Brookhaven National Laboratory, SLAC National Accelerator Laboratory and Oak Ridge National Laboratory (ORNL).
The rapid data analysis platform is built to accelerate breakthroughs in microelectronics, medicine, advanced manufacturing and energy security. The goal is to advance DOE laboratories with next‑generation, AI‑driven research capabilities.
“SYNAPS‑I is envisioned not just as a tool for analysis and automation, but as a cognitive partner for scientists — capable of generating hypotheses, detecting subtle correlations and helping turn DOE facilities into truly intelligent, self‑driving laboratories,” said Mathew Cherukara, an Argonne computational scientist, group leader and leader of the Argonne SYNAPS-I team.
SYNAPS‑I Enables Real‑Time AI Imaging at Beamline Scale
The SYNAPS-I project aims to develop an AI‑driven imaging engine capable of turning vast scientific data streams into rapid insight. One challenge is scale: SYNAPS‑I seeks to train a multimodal, billion‑parameter foundation model on data from more than 100 beamlines across seven DOE facilities, far surpassing today’s archive of 50 billion images. “Multimodal” means the model can process different types of data, such as text and images, and “billion-parameter” refers to the billions of internal variables the system adjusts as it learns.
Beamlines are experiment stations built to deliver and shape X‑ray beams for scientific measurements.
To build and test the platform, the team started with ptychography, an X-ray technique that gathers overlapping diffraction patterns — the distinctive ways X-rays scatter after interacting with a material — and uses computation to reconstruct sharp, high‑resolution images.
“The use of ptychography is expanding rapidly, driven by major light source advances such as Argonne’s Advanced Photon Source (APS) Upgrade and the Advanced Light Source (ALS) Upgrade at Berkeley Lab,” said Alec Sandy, associate director of Argonne’s X-ray Science division. “Converting raw ptychography data into human and AI‑interpretable results in real time maximizes DOE’s investment in these facilities and makes the measurements immediately relevant for technology development.”
Researchers chose ptychography because it “feels almost magical,” said Tao Zhou, a scientist at Argonne’s Center for Nanoscale Materials (CNM) and a member of the SYNAPS-I team. “Scientists have pushed traditional X‑ray optics to their physical limits. Ptychography sidesteps those limits by using physics and computational reconstruction to achieve detail finer than the beam itself can reveal.”
This level of resolution has been achieved before, but not this rapidly.
SYNAPS-I accelerates the entire workflow, delivering high‑resolution ptychographic images fast enough to keep pace with experiments and surpass the limits of conventional optics. The platform uses the advanced computing resources of the Argonne Leadership Computing Facility (ALCF) and the National Energy Research Scientific Computing Center (NERSC) at LBNL. The APS, CNM, ALCF, ALS and NERSC are DOE Office of Science user facilities.
At Argonne’s APS, the world’s brightest synchrotron X-ray source, a coherent beam scans nanoscale samples such as microelectronics and other manufacturing‑relevant materials. SYNAPS‑I captures the resulting diffraction patterns and reconstructs them into high‑resolution images in real time.
“SYNAPS-I is a rapid‑analysis method that delivers insights at the pace data is generated, compressing hours or days of analysis into seconds,” said Aileen Luo, an Argonne assistant computational scientist and lead developer of the SYNAPS-I model for ptychography.
Behind that speed is an AI platform engineered to think like the imaging tools themselves.
“By building the physics of coherent imaging directly into the model, we’re giving AI the same knowledge a scientist would use,” said Emon Dey, a postdoctoral researcher in Argonne’s Mathematics and Computer Science division and member of the SYNAPS-I team. “That built‑in understanding makes it far more accurate and efficient when handling the massive data volumes produced at DOE facilities.”
The platform works across domains, speeding progress in microelectronics, biomedical research, advanced manufacturing and energy security. SYNAPS-I cuts imaging analysis from years to days and enables real‑time, AI‑driven materials design for next‑generation U.S. manufacturing.
The platform could deliver substantial economic gains by using real-time AI to cut research delays, eliminate costly bottlenecks and speed innovation, boosting U.S. competitiveness and driving growth across multiple industries.
Testing Reveals Order-of-Magnitude Gains
Argonne recently successfully tested the new rapid‑analysis data method, running the full SYNAPS‑I workflow on microelectronics and quantum samples at a shared APS/CNM beamline.
The platform captured data and displayed the imaging results instantly for real‑time viewing at the beamline. Simultaneously, the saved data was moved to the ALCF, where high performance computing resources were used to refine the models.
“The test opened the door to real-time identification of defects in materials, for example, to guide manufacturing processes and enable autonomous discovery campaigns to discover new technologically impactful materials,” said Sandy. Autonomous discovery campaigns are largely self-driving research efforts in which AI systems help design experiments, analyze results and determine the next steps, accelerating the search for promising new materials.
The results of the test at the 26-ID beamline of the APS (operated by CNM) showed ptychography capabilities that were 10 times higher in resolution and contrast and 100 times faster than similar experiments without using AI workflows. SYNAPS-I enabled the analysis of 1.3 terabytes of data on one graphical processing unit (GPU) in real time, whereas a similar experiment without AI would take 2,500 GPU hours to process.
SYNAPS‑I: The Road Ahead
As the APS expands its coherent imaging capabilities, the team plans to deploy SYNAPS‑I across the facility and other DOE light‑source and neutron facilities.
The capabilities under development could support 10 APS beamlines and many more across the DOE complex, Sandy said.
The team also aims to extend SYNAPS‑I beyond ptychography, expand it with new partners, test it in real experimental settings and refine it continually as it scales.
To do that, the Argonne team is drawing on the unparalleled strengths of the DOE user facilities, including the APS.
“We’re fortunate to have one of the brightest, most advanced synchrotron facilities in the world at the APS, and that’s a big part of what makes this project possible,” Luo said.
Along with Cherukara, Sandy, Zhou, Dey and Luo, the Argonne SYNAPS-I team includes Ming Du, Peco Myint, Jeffrey Klug, Antonino Miceli, Xiangyu Yin, Sinisa Veseli, Tekin Bicer, Varuni Sastry, Yijiang Li and Kibaek Kim.
SYNAPS-I is a public-private partnership uniting Argonne with LBNL, Brookhaven, ORNL, SLAC, university researchers and AI leaders with key industry innovators.
Work performed at the CNM and APS was supported by the DOE Office of Basic Energy Sciences.
Source: Beth Burmahl, Argonne National Laboratory