Nav: Home

Artificial intelligence learns to predict elementary particle signals

March 14, 2019

Scientists from the Higher School of Economics and Yandex have developed a method that accelerates the simulation of processes at the Large Hadron Collider (LHC). The research findings were published in Nuclear Instruments and Physics Research Section A: Accelerators, Spectrometers, Detectors and Associated Equipment.

Experiments in high energy physics require work with big data. For example, at the LHC, millions of collisions occur every second, and detectors register these particles and determine their characteristics. But in order to receive a precise analysis of experimental data, it is necessary to know how the detector reacts to known particles. Typically, this is done using special software that is configured for the geometry and physics of a particular detector.

Such packages provide a fairly accurate description of the medium's response to the passage of charged particles, but the rate of generation of each event can be very slow. In particular, the simulation of the single LHC event may take up to several seconds. Given that millions of charged particles collide every second in the collider itself, an exact description becomes inaccessible.

Researchers from HSE and the Yandex Data Analysis School were able to speed up the simulation using Generative Adversarial Networks. These are comprised of two neural networks that compete with each other during competitive training. This training method is used, for example, to generate photos of people who don't exist. One network learns to create images similar to reality, and the other seeks to find differences between artificial and real representations.

'It's amazing how methods that were developed basically to generate realistic photos of cats, allow us to speed up physical calculations by several orders of magnitude,' notes Nikita Kaseev, a PhD student at HSE and coauthor of the study.

The researchers trained generative competitive networks to predict the behavior of charged elementary particles. The results showed that physical phenomena can be described using neural networks highly accurately.

'Using generative competitive networks to quickly simulate detector behavior will certainly help future experiments,' says Denis Derkach, Assistant Professor in the Faculty of Computer Science and coauthor of the study. 'Essentially, we used the most modern training methods available in data science and our knowledge of the physics of detectors. The diversity of our team, which consisted of data scientists and physicist, also made it possible.'
-end-


National Research University Higher School of Economics

Related Large Hadron Collider Articles:

The Large Hadron Collider -- the greatest adventure in town
World Scientific's latest book, 'The Large Hadron Collider,' homes in on the ATLAs Experiment to illustrate how and why this process happens, why it has an importance well beyond traditional spin-off and how it adds new meaning to the cost of this research and to the value of international collaboration.
Why odds are against a large Zika outbreak in the US
Is the United States at risk for a large-scale outbreak of Zika or other mosquito-borne disease?
Laser R&D focuses on next-gen particle collider
A set of new laser systems and proposed upgrades at Berkeley Lab's BELLA Center will propel long-term plans for a more compact and affordable ultrahigh-energy particle collider.
Physicist offers leading theory about mysterious Large Hadron Collider excess
K.C. Kong's idea: a sequence of particles at different masses -- without a 'resonance' particle at 750 GeV -- triggered the mystery signal at the Large Hadron Collider.
The large-scale stability of chromosomes
A new study led by the SISSA of Trieste and published in PLOS Computational Biology adds detail to the theoretical models used in chromatin simulations and demonstrates that even when made up of a mixture of fibres with different properties chromatin does not alter its three-dimensional structure above a certain spatial resolution.
Syracuse physicists help restart Large Hadron Collider
After months of winter hibernation, the LHC has resumed smashing beams of protons together, in attempt to recreate conditions of the first millionth of a second of the universe, some 13.9 billion years ago.
A quasiparticle collider
Experiments prove that basic collider concepts from particle physics can be transferred to solid-state research.
Physicists offer theories to explain mysterious collision at Large Hadron Collider
Physicists around the world were puzzled recently when an unusual bump appeared in the signal of the Large Hadron Collider, the world's largest and most powerful particle accelerator, causing them to wonder if it was a new particle previously unknown, or perhaps even two new particles.
Inadequate policies for hunting large carnivores
Many policies regulating carnivore hunting do not adequately acknowledge and address the negative effects of hunting on demography and population dynamics, authors of this Policy Forum say.
ALCF helps tackle the Large Hadron Collider's big data challenge
To help tackle the considerable challenge of interpreting data, researchers from the US Department of Energy's (DOE's) Argonne National Laboratory are demonstrating the potential of simulating collision events with Mira, a 10-petaflops IBM Blue Gene/Q supercomputer at the Argonne Leadership Computing Facility (ALCF), a DOE Office of Science User Facility.

Related Large Hadron Collider Reading:

Best Science Podcasts 2019

We have hand picked the best science podcasts for 2019. Sit back and enjoy new science podcasts updated daily from your favorite science news services and scientists.
Now Playing: TED Radio Hour

Digital Manipulation
Technology has reshaped our lives in amazing ways. But at what cost? This hour, TED speakers reveal how what we see, read, believe — even how we vote — can be manipulated by the technology we use. Guests include journalist Carole Cadwalladr, consumer advocate Finn Myrstad, writer and marketing professor Scott Galloway, behavioral designer Nir Eyal, and computer graphics researcher Doug Roble.
Now Playing: Science for the People

#529 Do You Really Want to Find Out Who's Your Daddy?
At least some of you by now have probably spit into a tube and mailed it off to find out who your closest relatives are, where you might be from, and what terrible diseases might await you. But what exactly did you find out? And what did you give away? In this live panel at Awesome Con we bring in science writer Tina Saey to talk about all her DNA testing, and bioethicist Debra Mathews, to determine whether Tina should have done it at all. Related links: What FamilyTreeDNA sharing genetic data with police means for you Crime solvers embraced...