PRESS-NEWS.org - Press Release Distribution
PRESS RELEASES DISTRIBUTION

Machine learning could help reveal undiscovered particles within data from the Large Hadron Collider

The study marks the first use of a neural network to analyze data from a collider experiment

2024-04-15
(Press-News.org) Scientists used a neural network, a type of brain-inspired machine learning algorithm, to sift through large volumes of particle collision data.

Particle physicists are tasked with mining this massive and growing store of collision data for evidence of undiscovered particles. In particular, they’re searching for particles not included in the Standard Model of particle physics, our current understanding of the universe’s makeup that scientists suspect is incomplete.

As part of the ATLAS collaboration, scientists at the U.S. Department of Energy’s (DOE) Argonne National Laboratory and their colleagues recently used a machine learning approach called anomaly detection to analyze large volumes of ATLAS data. The method has never before been applied to data from a collider experiment. It has the potential to improve the efficiency of the collaboration’s search for something new. The collaboration involves scientists from 172 research organizations.

The team leveraged a brain-inspired type of machine learning algorithm called a neural network to search the data for abnormal features, or anomalies. The technique breaks from more traditional methods of searching for new physics. It is independent of — and therefore unconstrained by — the preconceptions of scientists.

“Rather than looking for very specific deviations, the goal is to find unusual signatures in the data that are completely unexplored, and that may look different from what our theories predict.” — Physicist Sergei Chekanov

Traditionally, ATLAS scientists have relied on theoretical models to help guide their experiment and analysis in the directions most promising for discovery. This often involves performing complex computer simulations to determine how certain aspects of collision data would look according to the Standard Model. Scientists compare these Standard Model predictions to real data from ATLAS. They also compare them to predictions made by new physics models, like those attempting to explain dark matter and other phenomena unaccounted for by the Standard Model.

But so far, no deviations from the Standard Model have been observed in the billions of billions of collisions recorded at ATLAS. And since the discovery of the Higgs boson in 2012, the ATLAS experiment has yet to find any new particles.

“Anomaly detection is a very different way of approaching this search,” said Sergei Chekanov, a physicist in Argonne’s High Energy Physics division and a lead author on the study. ​“Rather than looking for very specific deviations, the goal is to find unusual signatures in the data that are completely unexplored and that may look different from what our theories predict.”

To perform this type of analysis, the scientists represented each particle interaction in the data as an image that resembles a QR code. Then, the team trained their neural network by exposing it to 1% of the images.

The network consists of around 2 million interconnected nodes, which are analogous to neurons in the brain. Without human guidance or intervention, it identified and remembered correlations between pixels in the images that characterize Standard Model interactions. In other words, it learned to recognize typical events that fit within Standard Model predictions.

After training, the scientists fed the other 99% of the images through the neural network to detect any anomalies. When given an image as input, the neural network is tasked with recreating the image using its understanding of the data as a whole.

“If the neural network encounters something new or unusual, it gets confused and has a hard time reconstructing the image,” said Chekanov. ​“If there is a large difference between the input image and the output it produces, it lets us know that there might be something interesting to explore in that direction.”

Using computational resources at Argonne’s Laboratory Computing Resource Center, the neural network analyzed around 160 million events within LHC Run-2 data collected from 2015 to 2018.

Although the neural network didn’t find any glaring signs of new physics in this data set, it did spot one anomaly that the scientists think is worth further study. An exotic particle decay at an energy of around 4.8 teraelectronvolts results in a muon (a type of fundamental particle) and a jet of other particles in a way that does not fit with the neural network’s understanding of Standard Model interactions.

“We’ll have to do more investigation,” said Chekanov. ​“It is likely a statistical fluctuation, but there’s a chance this decay could indicate the existence of an undiscovered particle.”

The team plans to apply this technique to data collected during the LHC Run-3 period, which began in 2022. ATLAS scientists will continue to explore the potential of machine learning and anomaly detection as tools for charting unknown territory in particle physics.

The results of the study were published in Physical Review Letters. This work was funded in part by the DOE Office of Science’s Office of High Energy Physics and the National Science Foundation.

Argonne National Laboratory seeks solutions to pressing national problems in science and technology. The nation’s first national laboratory, Argonne conducts leading-edge basic and applied scientific research in virtually every scientific discipline. Argonne researchers work closely with researchers from hundreds of companies, universities, and federal, state and municipal agencies to help them solve their specific problems, advance America’s scientific leadership and prepare the nation for a better future. With employees from more than 60 nations, Argonne is managed by UChicago Argonne, LLC for the U.S. Department of Energy’s Office of Science.

The U.S. Department of Energy’s Office of Science is the single largest supporter of basic research in the physical sciences in the United States and is working to address some of the most pressing challenges of our time. For more information, visit https://​ener​gy​.gov/​s​c​ience.

END


ELSE PRESS RELEASES FROM THIS DATE:

metaphacts and Dimensions launch the Dimensions Knowledge Graph, powered by metaphactory

2024-04-15
Digital Science solutions metaphacts and Dimensions are excited to announce the highly anticipated launch of the Dimensions Knowledge Graph, a large ready-made knowledge graph powering AI solutions in the pharmaceutical and life sciences industries.  The Dimensions Knowledge Graph, powered by metaphactory, is an all-in-one knowledge graph solution, ready-made for easy integration with customers’ data infrastructure and existing internal knowledge graphs. At its core is an explicitly defined and flexible semantic model that can be easily extended to include internal data (which can range from domain expert knowledge or data from internal documents) ...

Parent perceptions of school meals influence student participation in school meal programs

2024-04-15
Philadelphia, April 15, 2024 – Since the implementation of the Healthy, Hunger-Free Kids Act in 2010, school meals in the United States have significantly improved. Several factors have been reported to impact student participation in school meals, including parental perceptions of school breakfast and lunch. A recent research article in the Journal of Nutrition Education and Behavior, published by Elsevier, assessed the association between parent perspectives on the school meal program and student participation. Researcher ...

Hydrogen recombination found to be most plausible explanation for high levels of energy in stellar superflares

2024-04-15
Although their primary purpose is to look for exoplanets, observatories like the Kepler Space Telescope and the Transiting Exoplanet Survey Satellite (TESS) have supplied a vast amount of data on stellar flares, detected with high-precision photometry by broadband filters in the visible light spectrum. The stars are so far away that they appear only as points of light to these telescopes, and the phenomena interpreted as stellar flares are abrupt increases in the brightness of these points. There is also a lack of data in other parts of the electromagnetic spectrum, and most studies of these events focus on irradiated ...

Microplastics make their way from the gut to other organs, UNM researchers find

2024-04-15
It’s happening every day. From our water, our food and even the air we breathe, tiny plastic particles are finding their way into many parts of our body. But what happens once those particles are inside? What do they do to our digestive system? In a recent paper published in the journal Environmental Health Perspectives, University of New Mexico researchers found that those tiny particles – microplastics – are having a significant impact on our digestive pathways, making their way from the gut and into the tissues of the kidney, liver and brain. Eliseo Castillo, PhD, an associate professor in the Division of Gastroenterology ...

Unlocking the secrets of forest heights: the role of GEDI LiDAR technology

Unlocking the secrets of forest heights: the role of GEDI LiDAR technology
2024-04-15
A team of researchers has unveiled a novel approach to accurately characterizing tree height composition in forests using the Global Ecosystem Dynamics Investigation (GEDI) Light Detection and Ranging (LiDAR) technology. This study marks a significant advancement in our understanding of forest ecosystems, shedding light on the intricacies of tree height variability and its implications for ecological studies and climate change mitigation efforts. Tree height composition, a vital ecological attribute, plays a significant role in influencing forest ecosystems, impacting biodiversity, carbon ...

Canada likely to miss WHO's Hepatitis C elimination target, research shows

2024-04-15
Canada will not reach the original World Health Organization's (WHO) target of eliminating the Hepatitis C virus (HCV) by 2030 and lags in comparison to other developed countries, a new study led by researchers at the University of Waterloo has found.  HCV is an infection that poses a major public health threat that affects an estimated 250,000 Canadians – despite having a highly effective medication.   When gone unscreened, HCV is a highly debilitating infection that causes liver failure and could lead to death. Due ...

Pyrite, also known as fool’s gold, may contain valuable lithium, a key element for green energy

2024-04-15
There’s a reason airlines won’t let you put your laptop in your checked luggage; the lithium-ion battery poses a serious fire hazard. But why? Lithium is incredibly reactive. For instance, pure lithium violently interacts with seemingly innocuous water, releasing heat and forming highly flammable hydrogen. This reactivity, however, is exactly why lithium makes a great material for batteries, and why it is a critical mineral for the green energy transition. Lithium-ion batteries are widely used in electric vehicles. Plus, they can store energy produced by renewable resources like solar and wind.   In recent years, lithium demand has skyrocketed. Primary ...

Is there a quick fix for ocean acidification? (video)

Is there a quick fix for ocean acidification? (video)
2024-04-15
WASHINGTON, April 15, 2024 — Acidification is threatening the ocean’s ability to pull carbon dioxide out of our atmosphere, so scientists and startups are looking to ocean-sized antacids to raise its pH. While they might not be the ultimate solution to our climate crisis problem, the antacids could have a hand in helping our oceans rebound. https://youtu.be/PqFwRMgvMVY?si=1VSbf7zaWbZQ3d25 Reactions is a video series produced by the American Chemical Society and PBS Digital Studios. Subscribe to Reactions at http://bit.ly/ACSReactions and follow us on X, formerly Twitter @ACSReactions. The American Chemical ...

Reducing CO2 emissions by 20% with only a 2% economic loss

Reducing CO2 emissions by 20% with only a 2% economic loss
2024-04-15
[Vienna, April 15 2024] — A “rapid and far-reaching change” is necessary to prevent catastrophic climate change, according to the Intergovernmental Panel on Climate Change (IPCC). "However, the transformation of the economy towards climate neutrality always involves a certain amount of economic stress -- some industries and jobs disappear while others are created," explains Johannes Stangl from the Complexity Science Hub (CSH). When it comes to climate policy measures, how can economic damage be minimized? A ...

Antibiotics aren’t effective for most lower tract respiratory infections

2024-04-15
WASHINGTON – Use of antibiotics provided no measurable impact on the severity or duration of coughs even if a bacterial infection was present, finds a large, prospective study of people who sought treatment in U.S. primary or urgent care settings for lower-respiratory tract infections. The study by researchers at Georgetown University Medical Center and colleagues appeared April 15, 2024, in the Journal of General Internal Medicine. “Upper respiratory tract infections usually include the common cold, sore throat, sinus infections and ear infections and have well established ways to determine if antibiotics should be given,” says the study’s ...

LAST 30 PRESS RELEASES:

Novel treatment combination improves progression-free survival in metastatic, estrogen-receptor-positive HER-2-negative breast cancer

ESMO 2025: Trial results show belzutifan shrinks rare neuroendocrine tumors and improves symptoms in patients

ESMO 2025: Dual targeted therapy shows promise in previously treated advanced kidney cancer patients

New generation of Antibody-Drug Conjugates (ADCs) shows unprecedented promise in early-stage disease

Sylvester Cancer Tip Sheet for October 2025

Three science and technology leaders elected to Hertz Foundation Board of Directors

Jump Trading CSO Kevin Bowers elected to Hertz Foundation Board of Directors

Former Inscripta CEO Sri Kosaraju elected to Hertz Foundation Board of Directors

Citadel’s Jordan Chetty elected to Hertz Foundation Board of Directors

McGill research flags Montreal snow dump, inactive landfills as major methane polluters

A lightweight and rapid bidirectional search algorithm

Eighty-five years of big tree history available in one place for the first time

MIT invents human brain model with six major cell types to enable personalized disease research, drug discovery

Health and economic air quality co-benefits of stringent climate policies

How immune cells deliver their deadly cargo

How the brain becomes a better listener: How focus enhances sound processing

Processed fats found in margarines unlikely to affect heart health

Scientists discover how leukemia cells evade treatment

Sandra Shi MD, MPH, named 2025 STAT Wunderkind

Treating liver disease with microscopic nanoparticles

Chemicals might be hitching a ride on nanoplastics to enter your skin

Pregnant patients with preexisting high cholesterol may have elevated CV risk

UC stroke experts discuss current and future use of AI tools in research and treatment

The Southern Ocean’s low-salinity water locked away CO2 for decades, but...

OHSU researchers develop functional eggs from human skin cells

Most users cannot identify AI bias, even in training data

Hurricane outages: Analysis details the where, and who, of increased future power cuts

Craters on surface of melanoma cells found to serve as sites for tumor killing

Research Spotlight: Mapping overlooked challenges in stroke recovery

Geographic and temporal patterns of screening for breast, cervical, and colorectal cancer in the US

[Press-News.org] Machine learning could help reveal undiscovered particles within data from the Large Hadron Collider
The study marks the first use of a neural network to analyze data from a collider experiment