Argonne scientists create chatty X-ray microscope that zooms in where you tell it to
Talking to an X-ray nanoprobe beamline is far better than talking to a toaster, we assume
Scientists at Argonne National Laboratory have developed an advanced X-ray microscope equipped with an AI platform, enabling researchers to pinpoint specific areas of interest with natural language commands. Initially tested on integrated circuit devices, the microscope successfully located the interface between two regions by simply instructing the AI to determine the target.
Argonne's 26-ID hard X-ray nanoprobe beamline, which uses tightly focused X-ray beams for nanoscale imaging and measurements, generates vast amounts of data. Traditional ptychographic reconstruction and analysis can take hours or days, but the AI system can process the data in real time. The second phase of the project, which integrates natural language agentic AI, enables researchers to ask the microscope to examine specific areas of interest without needing to manually adjust the beam.
This conversational AI not only handles data collection and processing but also analyzes results, identifies additional points of interest, and investigates them independently. Tao Zhou, an Argonne scientist, emphasized the potential of this new, interactive microscope to make advanced scientific research more accessible to researchers who lack the expertise to operate complex instruments.
The Argonne X-ray nanoprobe beamline is part of President Trump's Administration's Genesis Mission, which aims to leverage AI in scientific research, including the SYNAPS-I project led by the Department of Energy in collaboration with Lawrence Berkeley National Laboratory, Brookhaven National Laboratory, SLAC National Accelerator Laboratory, and Oak Ridge National Laboratory.
Written by urgent.news from The Register Science's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.
