How Is Artificial Intelligence (AI) Helping Physicists Working On Particle Accelerators?

 Hussain Kanchwala  1 Min Ago

Experiments at the world’s largest particle accelerator, the LHC (the Large Hadron Collider), at the physics lab CERN, produces more than one million gigabytes of data every minute. Even after compressing this colossal amount of data, the data amassed in just a few hours is tantamount to an entire year’s worth of data that social networking sites like Facebook gather from users—far too much to save and study by mortals like us. This volume of data will also increase multifold in the years to come.

The Large Hadron Collider (LHC) at CERN (Photo Credit : apod.nasa.gov)

Driven by a conscientiousness to efficiently manage these discoveries with such staggering data volumes, physicists working on particle accelerators like the Large Hadron Collider (LHC) have brought in artificial intelligence (AI) experts to tackle the LHC data deluge. For the uninitiated, artificial intelligence (AI) is a specially designed set of software that mimics the way humans learn and solve complex problems. Machines running AI programs learn activities like speech recognition, planning, problem-solving, perception, and planning by themselves and can work efficiently without getting lost in the labyrinth of data.

The next generation of particle-collider experimentswill engage some of the world’s most intelligent thinking machines if the links between particle physicists and AI researchers take off smoothly. Such machines could make incredible discoveries with nearly zero human input.

AI in the Higgs Boson Discovery

Particle physics and artificial intelligence are not strangers. The ATLAS and CMS are two of the popular LHC experiments that paved the way for the discovery of the Higgs Boson a few years back. They were able to do so thanks to machine learning technology, a form of artificial intelligence that trains algorithms to recognize patterns in data and bring out meaningful conclusions from those patterns. The AI algorithms were primed using simulations of the debris from particle collisions and learned to accurately detect the patterns educed from the decay of rare Higgs particles among thousands of other unimportant bits of data.

Depiction of Higgs Boson formation

Deep Learning

Recent advances in the field of artificial intelligence—often called ‘deep learning’—promise to take applications in particle accelerator even further. Deep learning uses structures that are loosely inspired by the human brain—consisting of a set of units (equivalent to neurons in our brain). Each unit combines a set of input values to generate an output value, which in turn is passed on to other neurons in the deeper layer of the network. In other words, deep learning refers to the use of neural networks—computer programs with a structure inspired by a dense network of neurons in the human brain.

An illustration of deep learning. (Photo Credit : CC0 Public Domain/Wikimedia Commons)

Rudimentary AI algorithms are trained with sample data, such as images, and are told (instructed) what each picture shows—a house versus a dog, for example. However, advanced ‘deep learning’ algorithms, such as those used by tech giants like Google (Google Assistant) and Apple (Siri) in their voice recognition systems, typically receive no such supervision and must find their own ways to categorize the data in their respective fields.

Google Assistant responding to user’s query on a Pixel phone (Photo Credit : Maurizio Pesce/Wikimedia Commons)

Until recently, the success of deep learning was limited because training the AI software to supervise themselves for subsequent uses was difficult. Also, earlier, the neural networks employed for deep learning were just a couple of layers deep, but thanks to recent advances in machine learning and neural networks, it is now possible to build and train networks that are thousands of layers deep. Deep Underground Neutrino Experiment (DUNE), an international mega-science project, employs these sophisticated deep learning algorithms to study neutrino science and proton decay.

Computer Vision

AI algorithms are becoming fine-tuned more and more each day, opening up fascinating opportunities to solve problems pertaining to particle physics. Many of the new tasks that AI programs use have their applications in computer vision. Computer vision deals with automatic extraction, analysis, and detection of relevant information from standalone images or a sequence of images. It’s similar to facial recognition, which most high-end camera phones come with these days, except that in particle physics, image features are much more abstract than simple facial features like your eyes, ears or nose.

Some popular neutrino experiments, like Nova and Microboone, produce data that can be easily translated into actual images. Computer vision algorithms can be readily used to discern features in such scenarios.

However, in particle accelerator experiments, images first need to be recreated from a heterogeneous pool of data that is generated by millions of sensor elements. Even if the data doesn’t look like images, physicists can still use computer vision programs if they process the data in the correct way, opines machine learning researcher Alexander Radovic.

One area where this approach could wield great results is in the analysis of particle jets produced in large numbers during particle accelerator experiments, like those at the LHC. Particle jets are narrow suds of particles whose individual tracks are extremely difficult to detect. Computer vision algorithms could help to identify features in jets.

Today, physicists are primarily employing artificial intelligence to find features in the large pool of data generated from particle acceleration experiments that can help us answer the biggest questions concerning particle physics.  Ten years from now, AI algorithms might be able to independently ask their own questions and notify researchers when they come up with groundbreaking new discoveries in physics!

References:

1. International Journal of Science
2. CERN
3. Kaggle.com

The short URL of the present article is: http://sciabc.us/aZQJs

Help us make this article better

About the Author:

Hussain Kanchwala is an Electronic Engineer from University of Mumbai. He is a tech aficionado who loves to explicate on wide range of subjects from applied and interdisciplinary sciences like Engineering, Technology, FinTech, Pharmacy, Psychology and Economics.

RECs in confusion as INEC centralises returning, collation officers’ selection

Published

February 3, 2019

Ademola Oni

The decision of the headquarters of the Independent National Electoral Commission to appoint Returning Officers and Collation Officers for all categories of the 2019 elections appears to be creating confusion among the Resident Electoral Commissioners who regard the recruitment as their responsibilities.

The RECs believed that the responsibility to appoint the returning officers and collation officers for the elections at the ward, local government and state levels belonged to them and had started the process of recruiting the ROs and COs.

In previous elections, the RECs had been saddled with the task of appointing the collation officers and the returning officers.

This is said to be based on the fact that the RECs, who operate at the state levels, know the officers who are credible and could be called upon to handle the collation and announcement of results effectively.

It was learnt that at a meeting between the INEC leadership and the RECs in Abuja in December, the criteria to be adopted in selecting the two categories of officers were outlined.

It was further learnt that the selection was meant to be discussed at another meeting in of the commission in January.

In anticipation of the approval of the names of the vice-chancellors and university lecturers to be appointed in their states, the RECs were said to have started the collation of names to serve as returning and collation officers.

However, a memo from the Office of the Secretary to the Commission, INEC, signed by the Secretary, Mrs. Rose Oriaran-Anthony, on January 30, instructed the RECs that the appointments of the ROs and COs would be done by the headquarters of the agency.

READ ALSO: Obasanjo meets with parties, security chiefs in Ogun

In the memo with ref: INEC/HQ/SEC/809/IV, Oriaran-Anthony stated, “It has been observed that some states have started recruiting Collation Officers for the 2019 general elections, which is not in line with the commission’s approved guidelines for sourcing of ad hoc staff.

“Kindly note that all Collation Officers for the 2019 general elections (i.e. RA, LGA. Federal Constituency and Senatorial) and all Returning Officers are to be recruited and posted by the headquarters.

“Please be guided.”

But some of the RECs, who spoke with SUNDAY PUNCH on condition of anonymity on Saturday, alleged that the leadership of the commission might have other suspicious plans for the elections than had been stated.

One of them said, “It is not the duty of the headquarters to appoint returning officers and collation officers; that has never been the practice. The RECs know the people in the state and in the institutions in the state. How can anybody handpick ROs and COs from 36 states and the FCT for all the elections?”

Another REC, who also spoke to SUNDAY PUNCH on condition of anonymity, said there was a growing concern among the RECs what the leadership of the agency wanted to achieve with the latest development.

“It appears there are more to this move than all of us know. No, we are not even talking about rigging. The officers are to preside over the collation and announcements of results.  Why would the commission choose to appoint people that it does not know,” said the REC.

“If there is violence during the collation, either at ward or local government centre, won’t people suspect that the ‘foreigner’ among them has swapped the original copy of the results with another copy? That’s why we are confused at the moment, especially when we don’t know who we are going to work with just two weeks to the elections.”

But a National Commissioner of INEC and Chairman, Information and Voter Education of the commission, Mr. Festus Okoye, said the electoral umpire decided to centralise the recruitment of the returning officers and the collation officers in order to know the personalities better.

Okoye, who spoke to SUNDAY PUNCH on Saturday, explained that the centralisation of the recruitment had become necessary so that “some people” would not make “advances” to the officers before Election Day.

The national commissioner added, “INEC decided to centralise the recruitment of the officers in order to know them. We want to know who are the returning officers and the collation officers.

“We have contacted the universities directly. The vice-chancellors are sending the list to the chairman of INEC directly under serious cover.

“Each of those to be Returning Officers and Collation Officers will not know their posting until a day to the elections. They will not be exposed to manipulations with such arrangements. We want to be adequately transparent.”

Okoye stated that the greatest challenge of the commission was how to manage the number of party agents and collation officers at the about 120,000 polling units nationwide.

He said, “It’s going to be tough. If we have 91 political parties and 73 presidential candidates, how do you manage the number, especially when we are going to have all the candidates participating in the elections?”

YOU MAY ALSO LIKE: If anybody hits my car now, I can’t fight anymore —Afeez Oyetoro (Saka)

Okoye, who disclosed that INEC had stopped giving grants to political parties, added that a special arrangement had also been made to ensure that the Internally Displaced Persons in Benue and the North-East states could vote during the elections.

“The IDPs will vote, either those in the camp or those who ran away from their places because of attacks. We will conduct elections where it is safe to do so,” he added.