Self learning AI isolates particle jets in simulated ion collisions
Researchers at Brookhaven National Laboratory developed a self-learning artificial intelligence model to isolate high-energy particle jet signals from heavy-ion collision background noise.
FTMQ Science, written by our newsroom1 view

Physicists and computer scientists led by researchers at the United States Department of Energy Brookhaven National Laboratory have developed a new artificial intelligence approach to process particle collisions. Phys.org reported that the algorithm learns on its own to separate high-energy particle jet signals from background particle noise. The system processes data generated during relativistic heavy-ion collisions, where two beams of heavy ions collide at speeds near the speed of light. [1]
High-energy particle jets provide critical data about fundamental subatomic interactions, but massive background noise created during heavy-ion collisions complicates signal identification. The newly designed model relies on self-supervised learning methods. Self-supervised learning is a machine learning framework in which algorithms learn structural patterns directly from unlabeled data without requiring manual data tagging. [1][2]
The development builds on ongoing quantum and computational simulations of fundamental particle physics interactions. As FTMQ Science reported earlier, researchers previously simulated gluon string breaking using trapped ion quantum hardware, which matched results from neutral atom and superconducting quantum systems. The new computational approach addresses processing limits caused by the enormous particle background recorded during accelerator runs. [1][4]
In short
- Brookhaven National Laboratory researchers led the development of a self-learning AI model for particle physics data.
- The algorithm isolates high-energy particle jet signals from background noise in simulated heavy-ion collisions.
- Self-supervised machine learning algorithms extract structural patterns directly from unlabeled datasets.
Sources
Every paragraph above points to the numbered items it rests on. Read the originals here.
- [1]Self-learning AI separates particle jets from background noise in simulated heavy-ion collisionsPhys.org Physics, 4d ago (the report this story comes from)
Background
- [2]Unsupervised learning on Wikipedia
- [3]Self testing improves memory retention more than simple material rereading FTMQ Science, 11d ago
- [4]Researchers simulate gluon string breaking using trapped ion quantum computer FTMQ Science, 35d ago
Our newsroom writes these reports with the help of software, from the 4 sources listed and nothing else, and checks them against those sources. Facts can still be wrong or move on; the originals are the record. Spotted a mistake? Write to daniel@monsterkong.com.
Related from FTMQ Science
Earlier reports of ours on the same people and subjects.
- Neuroscientists report artificial intelligence speeds up brain research and model trainingTop Stories, 3d ago
- Relativistic Heavy Ion Collider concludes operations after twenty five yearsPhysics, 4d ago
- Researchers identify three core genes linking diabetes to poorer bypass outcomesNew Research, 10d ago
- Okinawa researchers develop ultracold diamond microwave amplifier for quantum signalsPhysics, 1d ago
- Oxygen collisions at high speeds recreate primordial matter in smaller interactionsPhysics, 17d ago
More in Physics
- Researchers control individual single molecule spin qubits using light and microwaves4h ago
- Quantum observers can hold different probability estimates within strict limits4h ago
- Physicists control single atom nuclear spin with radio waves1d ago
- Okinawa researchers develop ultracold diamond microwave amplifier for quantum signals1d ago
- TU Wien physicists develop tiny electrical switch with four distinct states1d ago
- Auburn University physicists use laser light to align electrical regions inside crystals2d ago
Get the day in one email
Reports like this one, the top news of the last 24 hours, every morning. Free, one email a day; readers can comment under every report.
By signing up you agree to our terms and privacy policy. Unsubscribe any time.

Comments
Loading
Join the conversation
Comments are open to readers of our daily email: the top news of the last 24 hours, every morning, free. Sign up and the comment box opens.
Already on the list? Enter the same address and we will send a sign-in link.
By signing up you agree to our terms and privacy policy. Unsubscribe any time.