Indian American scientist Abhirami Harilal employs machine learning to advance the search for dark matter and enhance particle detection at CERN’s Large Hadron Collider.
Abhirami Harilal, an Indian American applied scientist, is making significant strides in the quest to unravel one of the universe’s greatest enigmas: dark matter. Specializing in machine learning and statistical modeling for large-scale, real-world systems, Harilal is leveraging artificial intelligence to assist physicists in their search for new particles.
Harilal earned her Bachelor’s and Master’s degrees from the Indian Institute of Science Education and Research (IISER) in Kolkata, India, before completing her PhD in Physics at Carnegie Mellon University. Her academic journey has equipped her with the skills necessary to contribute to groundbreaking research at CERN, the European Organization for Nuclear Research.
During her four-year tenure at CERN, Harilal utilized machine learning techniques to enhance the detection of rare particle signatures, thereby refining the Large Hadron Collider’s (LHC) search capabilities. According to a feature from Carnegie Mellon University, her work has been instrumental in advancing the understanding of particle physics.
In addition to improving detection methods, Harilal has played a pivotal role in upgrading CERN’s detector technology. She developed algorithms that are now employed within the Compact Muon Solenoid (CMS) experiment, enabling the autonomous identification of anomalies with unprecedented accuracy.
“There are still many fundamental questions about the universe that current physics can’t fully explain,” Harilal stated. “At the Large Hadron Collider, we’re searching for signs of new particles that could help answer them.”
Astrophysical research indicates that only about 5% of the universe is composed of matter that is visible or detectable by scientific instruments. The remaining 95% consists primarily of dark matter and dark energy, which, despite being invisible, exert significant influence on the movement of galaxies, stars, and planets.
Researchers at CERN are actively investigating the properties and behaviors of these elusive particles. In 2012, the discovery of the Higgs boson marked a significant milestone in particle physics, representing a physical manifestation of a quantum field that permeates the universe.
<p”The Higgs boson takes a very special role in what we know about fundamental particles, and many theories suggest that if new particles exist, they could be connected to the Higgs boson,” Harilal explained. “I was trying to see if this Higgs boson would give way or decay into a new particle called an A particle, which could be connected to dark matter or other hidden sectors.”
To enhance the detection of the A particle, Harilal employed machine learning models to simulate thousands of particle collisions akin to those produced at the LHC. Her innovative approach has improved the experiment’s sensitivity to particles with unusual or difficult-to-detect signatures, including the potential A particle.
In addition to her research, Harilal has contributed to the automation of CERN’s CMS detector’s data monitoring system using similar machine learning techniques. Her model not only alerts researchers to unusual activity but also aids in identifying discrepancies between observed data and expected results. This advancement has streamlined the process for CERN scientists to diagnose potential issues as they collect data.
“I’m particularly proud about it because this was actually deployed and used during live data taking,” Harilal remarked, highlighting the practical impact of her work.
Currently based in Pittsburgh, Harilal continues to assist with various projects related to the CMS. Upon completing her research, she intends to apply her machine learning expertise to other fields, whether in research or industry.
“A big part of my work is recognizing meaningful patterns in large amounts of noisy data, which is also relevant in many other applications,” Harilal noted. “Similar ideas apply in areas like medical imaging, financial data, and drug discovery. I’m looking forward to finding other opportunities to use these skills.”
Harilal’s contributions to the field of particle physics exemplify the vital role of machine learning in advancing scientific discovery, particularly in the ongoing quest to understand the universe’s fundamental components.
According to Carnegie Mellon University, her innovative work at CERN continues to pave the way for future breakthroughs in the understanding of dark matter and beyond.